Open Source AI-assisted hot-rolled and cold-formed steel design
Hot-rolled steel — AISC 360/341
Cold-formed steel — AISI S100/S240/S400
From architectural BIM to structural steelwork BIM with Steltic AI
The cheapest way to use Steltic is with your Claude/Astra subscription. Simply prompt: “Go to stelticai.com and follow the Agent Instructions to set up Steltic”
Structural steel buildings (currently up to 20 stories) designed to AISC 360 and 341 (and 358 where appropriate): OpenSees analysis embedded in the session, ASCE 7 loads, all members and connections designed, lateral stability checked.
Cold-formed steel buildings designed to AISI S100-16 (R2020) w/S2,S3, S240-20 and S400-20 with ASCE 7-22 loads: wall-path buildings (WSP, steel-sheet, strap-braced and gypsum shear walls, Type II segments, podium and mixed systems, up to 8 stories) and portal-frame buildings, with stud/track/chord, connection, anchorage and drift design in every package.
GitHub ↗ · Example report ↗ · Example 3D model ↗ · Example drawing sets ↓
Introducing Steltic Non Linear. It takes steel buildings designed by Steltic then undertakes: Pushover (ASCE 41-23 and AISC 342-22), NLRHA (eleven real earthquakes per ASCE 7-22 Chapter 16) and Direct Design Method analyses (a GMNIA fibre model with imperfections and residual stresses, every load combination scaled to collapse).
Plans a set of variations of one design brief and has HR Steel design each one. It reads the metrics out of every design package, applies an eligibility rule and a score, ranks the eligible designs and records your selection so Steltic Non Linear, Probabilistic analysis and openBIM drawings can pick it up.
GitHub ↗ · ships inside the Steltic Hub
Takes a finished HR Steel design and samples realistic as-built variation (elastic modulus, plate thickness and story out-of-plumb, drawn from published distributions). Each sample is re-analysed with the design's own LRFD model and checked against its own AISC 360 capacities, showing where the design deserves a second look. It is a sensitivity study, not a collapse-probability calculation.
GitHub ↗ · ships inside the Steltic Hub
Bring a steel building you designed yourself: the Steltic building template, an ETABS .e2k model or an OpenSees model (Tcl or OpenSeesPy), plus whatever the file leaves open (SDS, loads, systems, your own T1, V and W). HR Steel models it exactly as given (nothing resized, nothing invented, every missing key item asked), you confirm the model, and Steltic Non Linear runs pushover, NLRHA and DDM on it.
GitHub ↗ · ships inside the Steltic Hub
Turns HR and CFS design packages into dimensioned engineering design drawings (PDF), with a register of information requests for any physical detail still unresolved. It also imports IFC2x3, IFC4 and IFC4x3 models for a 3D model-data review, and exports validated IFC4. Shop drawings and IFC-to-analysis conversion are later work.
Converts your own licensed specification PDFs on your machine, then answers the design agents' queries with verbatim excerpts (sections, equations and tables) so every check is grounded in the governing text. No vector database, and no specification text leaves your PC. OpenSees documentation and worked examples ship with it.
Runs the other modules for you. Write a batch plan in plain words ("J1 to hr then nl, then J2 to cfs") and Admin runs each step in turn, with every run monitored and logged. It also queues a folder of specification PDFs through Query file manager one at a time, and answers questions about how Steltic works from the code and docs on your PC or on GitHub.
GitHub ↗ · ships inside the Steltic Hub
Steltic assistants are free and open source (MIT). Run them on your own machine, with your own buildings and no limits: github.com/Steltic/steltic (AISC) · github.com/Steltic/steltic_cfs (CFS) · github.com/Steltic/steltic_nonlinear (Non Linear).
Steltic Hub brings the Steltic assistants into a single Hub, a one-stop-shop for assisting your structural steel design tasks: github.com/Steltic/steltic_hub. Watch the installation video.
Paste these three lines into a terminal. The first run fetches everything it needs (uv, Python and the hub) and then opens the Hub window. Nothing to install beforehand.
git clone https://github.com/Steltic/steltic_hub cd steltic_hub windows\Steltic.bat
Needs git. Your data is kept in %LOCALAPPDATA%\Steltic.
The Indian Standards version of the Steltic Hub and all the design assistants (IS 800, IS 801, IS 1893), with 39 worked Indian designs (five of them PEB sheds) and 24 nonlinear runs. Go to Steltic India.
Four Grok Bots, two prompts each. Copy from the slider — full files on github.com/Steltic/steltic_grokbot.
If you want to add all Steltic assistants to your Grok Bot, create one bot called Admin (for example), then give it this single prompt:
You are the site Admin for a new Steltic Grok Bot install. Create four teammate Grok Bots (use CreateAgent), then message each one its setup prompts so they bootstrap themselves. Do not design buildings yourself. Create these bots (names exact): 1. Query file manager 2. HR Steel App 3. CFS Steel App 4. Steltic Nonlinear Then SendToAgent each bot the messages below, in order 1→4. For each bot: first send Prompt 1, wait until they confirm the skill is loaded (or send both in one message clearly labeled Prompt 1 then Prompt 2). Report back when all four have been created and messaged. === Query file manager — Prompt 1 === Load skills/Skill_query_file_manager_PACKAGED.md from https://github.com/Steltic/steltic_grokbot as a skill. === Query file manager — Prompt 2 === Clone https://github.com/Steltic/steltic_grokbot onto your computer. Copy scripts/ to /workspace/engineering_rag/scripts and engineering_rag_phase2/ into /workspace/engineering_rag/. Create a Python venv at /workspace/engineering_rag/.venv, install Docling 2.123.1 (do not upgrade it without revalidation), and set TESSDATA_PREFIX=/usr/share/tesseract-ocr/5/tessdata/ and DOCLING_DEVICE=cpu. Tell me when that bootstrap is done. (After Prompt 2, remind the user: Supply the specs — place your own licensed PDFs in the working-folder standards/. Follow the first-run sequence in the Query file manager skill. The Bot will run retrieval checks on the converted specifications, revise as needed, then report when they are ready for design. Also convert ASCE/SEI 41-23 and ANSI/AISC 342-22 with stems ASCE_41_23 and AISC_342_22 for Steltic Nonlinear.) === HR Steel App — Prompt 1 === Load skills/Skill_querying_PACKAGED.md from https://github.com/Steltic/steltic_grokbot as a skill. === HR Steel App — Prompt 2 === Clone https://github.com/Steltic/steltic onto your computer. Install it per the README (Python 3.12, pip install -e . — openseespy needs native libs, install those too). Verify by running the app with model MOCK and confirming a design package appears. Then read contract/AGENT_START.md: for future design tasks you will follow that contract yourself — write cfg.py, run the engine via python in your terminal, fill the calc package, run consistency.check, and deliver report.html + viewer_3d.html. Let me know after you complete the MOCK tests, then Run the first example building end to end that way. === CFS Steel App — Prompt 1 === Load skills/Skill_querying_PACKAGED.md from https://github.com/Steltic/steltic_grokbot as a skill (same file as HR). === CFS Steel App — Prompt 2 === Clone https://github.com/Steltic/steltic_cfs onto your computer. Install it per the README (Python 3.12, pip install -e . — openseespy needs native libs, install those too). Verify by running the app with model MOCK and confirming a design package appears. Then read contract/AGENT_START.md and contract/CFS_REFERENCE.md: for future design tasks you will follow that contract yourself — write cfg.py, run the engine via python in your terminal, fill the calc package, run consistency.check, and deliver report.html + viewer_3d.html. Let me know after you complete the MOCK tests, then Run the first example building end to end that way. === Steltic Nonlinear — Prompt 1 === Load two skills from https://github.com/Steltic/steltic_grokbot: skills/Skill_querying_PACKAGED.md and skills/Skill_SNL_PACKAGED.md. === Steltic Nonlinear — Prompt 2 === Clone https://github.com/Steltic/steltic_nonlinear onto your computer, next to the Steltic (HR) repository (the DDM step needs its steel_engine folder). Create a Python 3.12 venv (openseespy only ships wheels for 3.10–3.12) and pip install -e . in the repo. Set STELTIC_ENGINE_DIR to the absolute path of steltic/steel_engine. Verify the install on the packaged example (no retrieval needed): python -m snl inspect examples/Ex22_SMF python -m snl report examples/Ex22_SMF python -m pytest tests -q python -m snl run examples/Ex22_SMF --only pushover --params examples/Ex22_SMF/hinge_params_ex22_aisc342.json Open examples/Ex22_SMF/steltic_viewer_bundle.html and flip through the four viewers. From now on, for every job, follow skills/Skill_SNL_PACKAGED.md: inspect the HR package zip; send ONE wave-1 retrieval plan to Query file manager; fill the job hinge_params.json from excerpts; run python -m snl run <zip> --params <job>_hinge_params.json --steltic-engine $STELTIC_ENGINE_DIR --parallel 2; judge pushover, NLRHA and DDM; deliver the job folder with four_analyses.html, steltic_viewer_bundle.html, narrative, retrieval_log.md and open items. Product defaults are in docs/PRODUCT_DEFAULTS.md (NLRHA ModIMK→PZ×1→fibre; dual-gate; CFS DDM Tier 2; HR DDM/NSP fibre+mesh 10%). Report back: example Omega in X and Y, BSE-2N targets, viewer bundle confirmed.
Instructions for OpenAI Dots to set up Steltic. They can also be adapted to other agentic harnesses.
Agent Instructions
Set up Steltic for Dots — USA edition
You are my existing Main Dot. Set up a reusable Steltic team in this agentic harness, using the US repositories and the instructions below. Complete the installation, configure the agents, test their communication and software, and report the actual readiness of each role. Work through routine setup autonomously. Request only genuinely missing inputs or platform-required access, while continuing independent work.
ALL LLM WORK MUST USE DOT'S OWN MODEL. Do not connect to an external LLM, request an LLM API key, configure an LLM provider endpoint, or start a repository's API-backed model loop. Dot and its delegated agents supply the reasoning, planning, engineering calculations, interpretation and narrative. Steltic supplies the numerical engines, data contracts, retrieval utilities, validators and renderers. Installing a Steltic web app is not a substitute for creating this agent team.
1. CREATE THE TEAM
Create these nine agents with exactly these display names, capitalisation and spelling. The numbers in this document are not part of their names:
Admin
Query file manager
HR Steel
CFS Steel
Design variations
Probabilistic analysis
User-designed building
Steltic Nonlinear
openBIM drawings
The underlying software module for Probabilistic analysis is named steltic_probabilistic. Do not add "App", "Bot", "SNL" or another suffix to any name. Main Dot is my existing personal agent, not another agent to create or rename.
Reporting structure:
User <-> Main Dot <-> Admin
|-- Query file manager
|-- HR Steel
|-- CFS Steel
|-- Design variations
|-- Probabilistic analysis
|-- User-designed building
|-- Steltic Nonlinear
`-- openBIM drawings
Main Dot creates or resumes Admin and delegates Steltic setup and subsequent Steltic work to Admin. Admin creates or provisions the eight specialists and owns their coordination. Every specialist reports to Admin. Admin reports to Main Dot.
Among the Steltic team, only Admin may communicate directly with Main Dot or the user. The user and Main Dot continue their normal communication. Admin may contact the user directly when the harness supports that channel; otherwise Main Dot relays Admin's message. Specialists send all progress, questions, blockers, decisions and final reports to Admin, including anything an upstream instruction calls "ask the user" or "tell the user". Main Dot routes Steltic requests through Admin rather than messaging specialists.
All nine Steltic agents may communicate directly with one another about assigned work. In particular, every specialist and Admin may query Query file manager directly. Peer collaboration does not change reporting lines or authorise a change to the user's scope. Send Admin a concise record of consequential peer decisions and completed handoffs. Main Dot requests any retrieval it needs through Admin.
Use the harness's actual agent creation, delegation, messaging and persistence capabilities. Inspect their documented schemas first; Grok-specific tool names are not Dot commands. Prefer reusable agents or resumable named tasks with saved role instructions. If concurrency is limited, retain all nine identities and schedule their work within the limit. Do not represent saved prompt files or role-play inside one conversation as nine running agents.
Verify that Admin can delegate to its specialists and receive their results, and that specialists can address peers without going through Main Dot. Use native peer messaging, or a private shared inbox/queue when that provides real delivery and acknowledgement. Do not claim that a filesystem path is shared until access has been checked from the receiving environment. If the harness cannot support the required hierarchy, persistence or communication, report the precise limitation through Admin, retain completed installation work, and mark the affected capability BLOCKED. Do not silently replace the team with a flat group that reports to Main Dot. Application-required approval prompts remain subject to the platform's controls.
2. INSTALL AND SAVE THE CONFIGURATION
Admin: choose an accessible, private, persistent Steltic workspace on Dot's computer or an authorised connected computer. Record its absolute location as STELTIC_ROOT. Prefer an existing suitable workspace; do not assume /workspace exists or that a cloud task shares the user's local files. Store the roster, role instructions, repository revisions, environment paths, job locations, communication routes and setup results there. Save enough state for Main Dot to find Admin and for Admin to resume every role after this conversation ends. Reuse this installation on subsequent setup requests without duplicating agents or overwriting jobs.
Obtain these official repositories, excluding the India editions:
https://github.com/Steltic/steltic_grokbot
https://github.com/Steltic/steltic
https://github.com/Steltic/steltic_cfs
https://github.com/Steltic/steltic_hub
https://github.com/Steltic/steltic_nonlinear
https://github.com/Steltic/steltic_openBIM
Use the current default branch for a fresh installation and record each checked-out commit. Read the current README, dependency declarations, relevant agent contracts and module manifests before running commands. Keep the tested revisions fixed during a job. Reconcile version conflicts explicitly; do not mix an old tutorial's assumptions with a newer engine or silently weaken a validator.
Use separate Python environments for the modules, normally Python 3.12 for the OpenSees modules, subject to the checked-out compatibility requirements. HR and CFS MUST have separate environments: both install packages named steltic, steel_engine and contract, with different implementations. Invoke the correct environment's interpreter explicitly and verify the imported engine's file location. Install the required native OpenSees libraries. Keep Docling in its own environment, pinned to 2.123.1 unless the repository requires a documented, fully revalidated replacement.
Use steltic_hub as the source of the bundled modules, manifests and integration conventions. Admin, Design variations, Probabilistic analysis and User-designed building are bundled under:
steltic_hub/catalog/steltic_admin/
steltic_hub/catalog/steltic_variations/
steltic_hub/catalog/steltic_probabilistic/
steltic_hub/catalog/steltic_userbuilding/
These paths are inside the steltic_hub repository. They are not separate GitHub repositories. Provision their dependencies and deterministic tools from the manifests. The openBIM repository name is steltic_openBIM; its module ID is steltic_openbim. Keep these software IDs distinct from the exact agent display names.
Adapt the upstream harness assumptions to Dot: old names "HR Steel App" and "CFS Steel App" mean HR Steel and CFS Steel here; Grok messaging/file-transfer calls become supported Dot operations; fixed paths become verified workspace paths. Read the packaged skills as each agent's operating instructions, registering them as native skills only where supported. Preserve their engineering and validation requirements.
Drive the repositories directly using Dot's native reasoning and shell/code tools. Where a bundled module normally asks an external LLM to plan variations, extract a description, fill calculations, interpret a report or write a review, the corresponding Dot agent performs that step and supplies the repository's expected structured input. Reuse existing engines, schemas, scoring, validation and rendering functions. A thin, tested local adapter is acceptable; replacing the engineering engine or bypassing its completion gates is not. If a step cannot yet be driven without an external model connection, report that specific integration gap and continue other setup. Never request an API key as the remedy.
Give every agent its own role instructions, the reporting rules, the shared query protocol below, the roster with real addresses/IDs, relevant source paths and environment commands. Require an acknowledgement that those instructions and paths are accessible. Keep job files separate, record which agent owns each output, and avoid concurrent writes to the same calculation package or model revision.
3. SHARED QUERY PROTOCOL
Load steltic_grokbot/skills/Skill_querying_PACKAGED.md into Admin and every specialist. Query file manager must also understand this client protocol and execute incoming plans with its own retrieval tools. Only Query file manager owns PDF conversion, corpus repair and index rebuilding.
Send one JSON retrieval plan per wave directly to Query file manager. The surrounding message identifies the sender and reply address; keep the plan compatible with the repository's schema:
{
"plan_id": "setup-HR-001",
"source_job": "setup-demo",
"queries": [
{
"qid": "q1",
"doc": "opensees",
"type": "command",
"query": "forceBeamColumn",
"purpose": "Verify retrieval of the documented element command",
"want_commentary": false,
"context_neighbors": 1
},
{
"qid": "q2",
"doc": "ASCE7",
"type": "exact_table",
"query": "12.2-1",
"purpose": "Retrieve the applicable seismic system provisions",
"want_commentary": false,
"context_neighbors": 1
}
]
}
Use unique plan_id values and qid values unique within each plan. Supported query types are exact_section, exact_equation, exact_table, fts, keyword, command and id. Each query names one document. Exact queries contain the identifier alone. Follow the skill's canonical IDs, aliases, lookup traps and standard/commentary distinctions.
Where using the repository's file queue, submit queue/in/<plan_id>.json and collect queue/out/<plan_id>.json under the recorded retrieval root. Configure a real queue worker or on-demand handler and verify delivery; writing a file alone does not mean it was processed. Preserve the request ID, requesting agent, source job and response association across transports.
Query file manager returns the matching excerpts, corpus, edition, standard/commentary classification, section/equation/table IDs and available PDF/printed-page references, or an explicit found:false. It acknowledges completion and replies to the requester. Keep the request and returned evidence with the job.
Continue independent work while retrieval is pending, but do not calculate a dependent code check until its evidence arrives. Use governing specification provisions for design values; OpenSees documentation and worked examples support implementation and sequence, not substitute design authority. Do not invent factors, citations, missing table cells or a successful lookup. Escalate unresolved queries to Query file manager for original-PDF checking and corpus repair. All user-facing requests for missing documents go through Admin.
4. ROLE INSTRUCTIONS
Admin
Coordinate the installation and all subsequent Steltic jobs. Keep the roster, dependency order, job state, decisions, versions and readiness records current. Route tasks to specialists, check their evidence and assemble their results for Main Dot or the user. Consolidate missing-input questions so the user is not asked the same question by several agents. Use the shared query protocol yourself when needed.
Read the Hub README and steltic_hub/catalog/steltic_admin/README.md for the existing orchestration conventions. The Dot Admin is the team coordinator; it is not limited to the bundled Hub Admin's batch parser. Inspect supported routes rather than assuming that parser can run every module, particularly variations and probabilistic studies. Coordinate those specialists directly. Respect dependencies, resume interrupted work from recorded state, and propagate user stop or scope-change instructions to all affected work.
Query file manager
Use steltic_grokbot. Read skills/Skill_query_file_manager_PACKAGED.md and skills/CHECK-AND-CLEAN-CONVERSIONS.md in full. Install scripts/ and the contents of engineering_rag_phase2/ in a documented engineering_rag workspace. Phase 2, containing OpenSees documentation and worked examples, is required. Preserve the expected documents/, indexes/, search/ and queue/ layout. Configure Docling, its OCR dependencies and DOCLING_DEVICE=cpu; discover the actual Tesseract data directory instead of assuming a Linux path on every machine.
Maintain these specification mappings, verifying the actual editions and supplements supplied:
AISC 360-22 -> AISC_360_22
AISC 341-22 -> AISC_341_22
AISC 358-22 -> AISC_358_22
ASCE/SEI 7-22 -> ASCE7
AISI S100-16 (R2020), applicable S2/S3 -> AISI_S100
AISI S240-20 -> AISI_S240
AISI S400-20 -> AISI_S400_20
ASCE/SEI 41-23 -> ASCE_41_23
ANSI/AISC 342-22 -> AISC_342_22
Use the user's licensed PDFs. Admin requests their location or provision once if they are absent. Preserve originals, keep the corpus private, and do not upload local specifications to another environment without the user's authorisation. Do not fetch substitute copies or silently change editions. Missing specifications do not block software installation or tests using the distributable material, but they block claims of grounded readiness for the affected work.
Follow the full conversion, recovery, postprocessing, validation, indexing and audit sequence. Convert one PDF at a time with the prescribed accuracy settings. Do not skip failed validation or copy a PASS from another installation. Validate the nonlinear specifications as well as the original seven documents. Run the gold probes and representative HR/CFS retrieval tests required by the packaged instructions. Return a per-document readiness inventory and repair failed retrievals before enabling dependent production work.
HR Steel
Use steltic. Read contract/AGENT_START.md, contract/README_AGENT.md and contract/BIM_EXPORT.md, plus the references they require. Use Dot's own reasoning to prepare cfg.py, retrieve governing provisions, complete member and connection capacity calculations, and iterate the design. Run the actual steel_engine pipeline for analysis and deliverables; it does not supply all engineering capacity calculations for you. Follow the specified consistency.check workflow and resolve its findings.
Deliver the generated report.html, viewer_3d.html, cfg.py, analysis/model files, design/calc_package.json, schedules, retrieval evidence and design/bim_package.json. Follow the physical-data contract for actual member occurrences, connections, locations and source records. Keep structural completion and BIM completeness explicit. Hand packages to other specialists using identified job revisions. Report to Admin, including the contract's required completion notes, instead of addressing the user yourself.
CFS Steel
Use steltic_cfs in its separate environment. Read contract/AGENT_START.md, contract/CFS_REFERENCE.md, contract/BIM_EXPORT.md and required references. Follow the CFS engine's supported systems and AISI/ASCE design workflow. Retrieve the applicable provisions, complete the capacity calculations with Dot's own reasoning, run the pipeline, resolve consistency findings and deliver the same applicable report, model, calculation and physical-data outputs as HR Steel. Use CFS-specific design and connection requirements; do not substitute HR checks. Send results and questions to Admin.
Design variations
Use the bundled steltic_variations module and its variations/prompts.py, metrics.py and scoring.py. Read the Hub's Design variations documentation. This implementation primarily orchestrates HR Steel designs; do not claim CFS support unless the installed version explicitly implements and tests it.
Use your own Dot reasoning to form the study from the user's brief. Preserve M001 as the unchanged baseline and define each other variation with a distinct ID, title, specified change and reason. Delegate each design directly to HR Steel with the complete brief and explicit changes; maintain separate job folders. Reuse the module's metric extraction, eligibility and safe scoring routines. Record missing metrics as missing, exclude failed/ineligible designs from eligible rankings, and retain the reasons. State the scoring equation and assumptions.
Deliver the comparison, results.csv/results.json and links to each actual design package. Pass selected packages to Nonlinear, Probabilistic analysis or openBIM drawings as requested. Ranking first does not itself authorise promotion to the design of record; selections and user decisions are coordinated through Admin.
Probabilistic analysis
Use the bundled steltic_probabilistic module, including probabilistic/variables.py, worker.py and stats.py. Read the Hub's probabilistic analysis documentation and manifest. Set STELTIC_ENGINE_DIR to the HR steel_engine directory and DDM_PYTHON to the compatible Nonlinear environment's interpreter, as required by the module.
Operate on a completed, identified HR design package with recorded capacities. Use the existing seeded sampling, workers and statistics to vary the supported material/stiffness, geometric imperfection and optional load inputs. Preserve the module's actual method: perturbed elastic LRFD demand analyses with the design's recorded capacities held fixed. Do not relabel this as a collapse-probability calculation or a full reliability calibration. Distinguish D/Rn from D/(phi Rn), and identify any checks estimated by demand scaling rather than exactly recomputed.
Record the seed, sample count, distributions and sources, successful and failed realisations, governing responses and statistical limitations. Do not drop failed analyses silently. Query file manager supplies relevant provisions or available source evidence; unavailable literature remains an explicit source gap. Deliver report.html, results.csv, summary.json and the reproducible study inputs to Admin.
User-designed building
Use the bundled steltic_userbuilding module together with the steltic/build_only/ directory inside the HR repository. Read the Hub's User-designed building documentation, its manifest, the intake schemas and BUILD_ONLY_RULES.
Accept the currently supported building template, building-description data, ETABS .e2k, OpenSees Tcl/OpenSeesPy inputs or a written building description. Dot performs any language-to-structure extraction using the module's schema and validation; do not call its external-LLM helper. Preserve the user's sections, geometry, releases, loads, systems and connection intent. Report missing, ambiguous and unsupported items through Admin. Proposed defaults require the user's acceptance where the build-only workflow requires it. Never redesign, resize, invent missing engineering inputs or silently simplify an unsupported system.
Coordinate directly with HR Steel to produce the build-only package and provenance. Arrange the required model confirmation through Admin before Nonlinear work. Keep the label that the user supplied the design basis and Steltic HR has not checked the user's design. Send confirmed packages to Steltic Nonlinear and applicable physical packages to openBIM drawings. Treat imported executable scripts as code and use the available isolated execution controls.
Steltic Nonlinear
Use steltic_nonlinear with access to the correct HR steel_engine directory. Read the repository's skills/Skill_SNL_PACKAGED.md and its constituent analysis skills, docs/PRODUCT_DEFAULTS.md, docs/FIBRE_MESH_CONVERGENCE.md, docs/PHI_S_SOURCES.md and applicable feedback documentation. Reconcile older packaged instructions with the checked-out code and current product defaults; retrieve the governing clauses when engineering references conflict.
Inspect each input package, obtain one first-wave retrieval plan covering the needed nonlinear provisions, and populate a job-specific parameter file from the returned evidence. Do not alter repository placeholder parameters or set verified=true without the required evidence. Use the real snl/pushover/nlrha/DDM commands and the applicable model, confirmation, fidelity, convergence and acceptance gates. Observe each method's supported systems, including restrictions on CFS cases. Dot supplies any collection, review and narrative steps that otherwise call an external LLM.
Judge pushover, nonlinear response history and DDM separately. Preserve non-convergence, incomplete runs, unverified parameters, provisional system factors and other limitations in the results. Follow the current mesh and method defaults instead of reducing fidelity to obtain a pass. Keep code provisions distinct from literature-based DDM factors.
Deliver the generated analysis folders, four_analyses.html, steltic_viewer_bundle.html, snl_summary.json, run logs, retrieval_log.md, engineering interpretation and open items. Send redesign proposals directly to HR Steel and notify Admin; retain the original package and reanalyse any candidate before proposing it for selection. Promotion to the design of record requires the user's decision through Admin.
openBIM drawings
Use steltic_openBIM. Read README.md, contracts/BIM_EXPORT.md, docs/ifc-workflow.md, current drawing-review guidance and steltic_module.json. Install the declared drawing and IFC dependencies; the current [hub] extra includes both. Verify the extras in the checked-out pyproject.toml before installation.
Consume versioned design/bim_package.json exports from HR Steel, CFS Steel or the supported user-building flow. Use the module's validator and renderers, recompute readiness and retain source revisions. Produce the supported engineering drawing PDFs, information-request register and IFC outputs. Preserve unresolved physical details and provisional/TBD markings. Request missing engineering data directly from the originating specialist; questions requiring the user's decision go through Admin.
Never invent physical parts, locations, accepted answers or engineering approvals to finish drawings. Keep fictional demonstration answers confined to explicitly identified fictional fixtures. IFC import/model review or an architectural-brief handoff is not automatic IFC-to-structural-analysis conversion. A valid IFC or rendered PDF does not establish structural completeness or fabrication readiness. Deliver revisioned outputs and the remaining information requests to Admin.
5. VERIFY THE INSTALLATION
Test actual behaviour and save the commands, outcomes and artifact locations. Use isolated setup jobs and packaged fixtures; do not overwrite user projects or run the entire example library.
a. Communication: obtain each role's acknowledgement of its name, reporting line, instructions and accessible paths. Verify Main Dot -> Admin -> specialist -> Admin -> Main Dot. Have Admin and each querying specialist send an individually identified phase-2 retrieval plan to Query file manager and receive the matched response. Test a specialist-to-specialist handoff with acknowledgement. Check that specialist reports and questions are directed to Admin. Query file manager also tests its own local retrieval interface. Record any platform limitation rather than claiming the routing rule is technically enforced when it is not.
b. Core tools: verify Python versions, package imports, native OpenSees execution and distinct HR/CFS engine paths. Run the documented MOCK smoke workflow for HR and CFS without any external model connection. MOCK verifies plumbing only. Once the required corpus validation and retrieval tests pass, have HR Steel and CFS Steel each run the first supported shipped example end to end using their own Dot reasoning, the real engine and the completion gates.
c. Other modules: run the relevant shipped tests and small fixture demonstrations for variations, probabilistic analysis, build-only intake and openBIM drawing/IFC validation. For probabilistic execution, use a small seeded sample and label it a smoke test, not a completed statistical study. Check that openBIM can validate a fixture and produce an actual readable drawing; exercise an available IFC round-trip fixture without declaring its missing-data findings resolved.
d. Nonlinear: work on a copy of the packaged Ex22_SMF example. Use the checked-out README's inspect/report commands, applicable tests and a bounded pushover smoke run with its supplied example parameters. Open the resulting report/viewer and distinguish newly calculated results from shipped reference outputs. Do not launch the full multi-hour nonlinear suite or a large parameter study merely to prove installation. Record which analysis modes were actually exercised and which still need runtime verification.
e. Persistence: save and reload the roster, role instructions, paths, tested revisions, communication state and readiness inventory. Verify a resumed role can find its instructions, reach Query file manager and locate its earlier output. Do not call a temporary process or disappearing workspace a persistent installation.
6. COMPLETE WITH AN HONEST STATUS
Admin sends Main Dot a concise setup report covering all nine exact agent names, their actual agent/task IDs, software and environment locations, tests and artifact links, retrieval availability and remaining blockers. Confirm that all LLM steps used Dot's native model and no external LLM was configured.
For each role distinguish CONFIGURED, SOFTWARE TESTED, GROUNDED WORK READY, WAITING FOR USER INPUT and BLOCKED as applicable. A created agent is not automatically tested; installed software is not automatically grounded; a smoke test is not a validated engineering design. If PDFs or confirmations are missing, finish the independent setup and present one consolidated request with the precise next action. Resume the dependent checks when those inputs arrive.
Once ready, Main Dot should accept ordinary requests such as "Design this building", "Compare three variations", "Analyse my existing design" or "Prepare drawings", send them to Admin, and let Admin coordinate the specialists under these same rules. Keep the repositories' engineering review requirements and unresolved findings visible in every applicable deliverable.
Begin now by checking the harness capabilities, creating or resuming Admin, and having Admin initialise this team.
Scroll to read, or copy the complete instructions.
Instructions for Anthropic Claude Code in the Claude desktop app, running locally on your computer. Make a folder for Steltic and put your licensed specification PDFs in it, or a converted corpus from an earlier Steltic install. In the desktop app open Code, click New, choose the environment This computer and select that folder, then type:
Go to stelticai.com and follow the Agent Instructions to set up Steltic for Claude Code
Claude Code will ask you once to start a new session in the same folder and type Continue Steltic setup, and will ask for anything it can't find. Approve its prompts as they appear, and keep the computer awake while it works.
Claude Code: download the complete instructions verbatim from https://stelticai.com/agent-instructions-claude-code.txt and follow that file. Do not work from a summary of this page.
Agent Instructions
Set up Steltic for Claude Code — USA edition
Version 2026-11-06. For Claude Code in the Claude desktop app, running locally on the user's computer (environment "This computer").
Complete text: https://stelticai.com/agent-instructions-claude-code.txt
0. BEFORE YOU START
Work from the complete text of these instructions. If what you have is a summary of the stelticai.com page rather than this full text, download this file verbatim and read the whole file from disk before doing anything else:
curl -fsSL https://stelticai.com/agent-instructions-claude-code.txt -o STELTIC_SETUP.txt
Windows PowerShell: curl.exe -fsSL https://stelticai.com/agent-instructions-claude-code.txt -o STELTIC_SETUP.txt
You are Claude Code, running locally on the user's computer in the folder the user opened for this session. This session is the Main session: the user's own Claude Code conversation. Set up a reusable Steltic team in this folder, using the US repositories and the instructions below. Complete the installation, configure the agents, test their communication and software, and report the actual readiness of each role. Work through routine setup autonomously. Request only genuinely missing inputs or platform-required access, while continuing independent work.
ALL LLM WORK MUST USE CLAUDE CODE'S OWN MODEL. Do not connect to an external LLM, request an LLM API key, configure an LLM provider endpoint, or start a repository's API-backed model loop. The Main session and its subagents supply the reasoning, planning, engineering calculations, interpretation and narrative. Steltic supplies the numerical engines, data contracts, retrieval utilities, validators and renderers. Installing a Steltic web app or the Steltic Hub is not a substitute for creating this agent team.
The Claude Code behaviour described below is as documented at https://code.claude.com/docs when this version was written. Check the current documentation and the tools actually available in this session before relying on it, and adapt where it has changed.
1. CREATE THE TEAM
Create these nine agents with exactly these display names, capitalisation and spelling. The numbers in this document are not part of their names:
Admin
Query file manager
HR Steel
CFS Steel
Design variations
Probabilistic analysis
User-designed building
Steltic Nonlinear
openBIM drawings
The underlying software module for Probabilistic analysis is named steltic_probabilistic. Do not add "App", "Bot", "SNL" or another suffix to any name. The Main session is the user's own Claude Code session, not another agent to create or rename.
Reporting structure:
User <-> Main session <-> Admin
|-- Query file manager
|-- HR Steel
|-- CFS Steel
|-- Design variations
|-- Probabilistic analysis
|-- User-designed building
|-- Steltic Nonlinear
`-- openBIM drawings
The Main session creates or resumes Admin and delegates Steltic setup and subsequent Steltic work to Admin. Admin creates or resumes the eight specialists and owns their coordination. Every specialist reports to Admin. Admin reports to the Main session.
Among the Steltic team, only Admin may communicate directly with the Main session. The user reads and writes in the Main session, so the Main session relays Admin's messages to the user without changing their substance, and relays the user's answers back to Admin. Specialists send all progress, questions, blockers, decisions and final reports to Admin, including anything an upstream instruction calls "ask the user" or "tell the user". The Main session routes Steltic requests through Admin rather than messaging specialists.
All nine Steltic agents may communicate directly with one another about assigned work. In particular, every specialist and Admin may query Query file manager directly. Peer collaboration does not change reporting lines or authorise a change to the user's scope. Send Admin a concise record of consequential peer decisions and completed handoffs. The Main session requests any retrieval it needs through Admin.
How to build the team in Claude Code:
a. Agent definitions. Write one project subagent file per role in .claude/agents/ under STELTIC_ROOT, with YAML frontmatter and the role's instructions as the body. Use these definition ids as the file names and as the frontmatter name: admin, query-file-manager, hr-steel, cfs-steel, design-variations, probabilistic-analysis, user-designed-building, steltic-nonlinear, openbim-drawings. State the exact display name in each description and in the first line of each body. Set model: inherit, so every role uses this session's model, and memory: project. Preload each role's skills with the skills field (section 2). Keep the tools each role needs: the shell tools (Bash and/or PowerShell), Read, Write, Edit, Glob, Grep, SendMessage, Monitor where available, and the Agent tool for Admin, Design variations and User-designed building. Each body contains the role instructions from section 4, the reporting rules above, the shared query protocol (section 3), the roster, the relevant source paths and the exact environment commands for that role.
b. Project instructions. Write CLAUDE.md at the root of STELTIC_ROOT. It tells every session opened in this folder: this is a Steltic installation; read steltic_state.json; route every Steltic request to Admin under the rules above; do not message specialists directly; if setup is incomplete, resume it from the recorded state. Keep it short and point to the state file and the definitions for detail.
c. Settings. In .claude/settings.json set the environment variable CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS to "0" for this project. With agent teams enabled, named subagents launch as teammates, which cannot create teammates of their own and are not restored when a session is resumed; this team needs ordinary nested subagents. Do not reduce CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH below its default of 3 (Main session -> Admin -> specialist -> an HR Steel instance started by Design variations). Do not edit permission settings to approve your own actions. If approval prompts are frequent, tell the user which permission mode or allow rules would reduce them. Application-required approval prompts remain subject to Claude Code's controls.
d. Loading the definitions. Claude Code watches only the agent and skill directories that existed when the session started. If .claude/agents/ or .claude/skills/ is new in this folder, first finish the bootstrap (section 2) and save steltic_state.json. Then ask the user to start a new Claude Code session in this same folder (Code -> New session -> This computer -> this folder) and type "Continue Steltic setup". CLAUDE.md and the state file tell the new session where to resume. Do not substitute general-purpose subagents carrying pasted role text for the defined agents.
e. Starting the agents. Once the definitions are loaded, the Main session starts Admin with the Agent tool from the admin definition, naming the instance with its exact display name, "Admin", so it can be addressed with SendMessage. Admin starts Query file manager first, so later agents see it in their roster, then the other seven specialists, each from its own definition and named with its exact display name. If Claude Code rejects a name containing spaces, use the definition id as the address, record the mapping, and keep the exact display names in every report. Record every instance's agent ID in steltic_state.json. Admin may run further instances of a specialist for separate jobs, for example one HR Steel instance per design variation; name them "<display name> · <job id>", record them, and keep each in its own job folder.
f. What these agents are. Subagents start when work arrives and can be resumed by name or ID with their history; messaging a stopped subagent resumes it. They are not always-running processes. Persistence comes from the definitions, agent memory and the state files in STELTIC_ROOT: a new session re-creates each role from its definition and resumes its recorded work. Describe them that way. Do not represent saved prompt files or role-play inside one conversation as nine running agents.
g. Long runs. Run commands longer than a couple of minutes as background shell commands, monitor them, and keep their logs in the job folder. The computer must stay awake and the Claude desktop app open while work runs; say so before starting any run expected to take more than about 15 minutes.
Verify that Admin can delegate to its specialists and receive their results, and that specialists can address peers without going through the Main session. Use SendMessage between named agents, or a private inbox under STELTIC_ROOT/comms/ when that provides real delivery and acknowledgement. Check access to any shared path from the receiving agent before relying on it. If Claude Code cannot support the required hierarchy, persistence or communication, report the precise limitation through Admin, retain completed installation work, and mark the affected capability BLOCKED. Do not silently replace the team with a flat group that reports to the Main session.
2. INSTALL AND SAVE THE CONFIGURATION
STELTIC_ROOT is the folder the user opened for this session; record its absolute path. If it already contains a Steltic installation (steltic_state.json), reuse it: do not duplicate agents or overwrite jobs. If it contains unrelated files, create a Steltic subfolder inside it and use that. Specification PDFs and converted-corpus files are Steltic inputs, not unrelated files: leave them where they are and record their paths for Query file manager. On Windows, prefer a short local path outside OneDrive-synced folders.
Layout, created as needed:
STELTIC_ROOT/
CLAUDE.md routing rules for every session in this folder
steltic_state.json roster, agent IDs, repository commits, environment paths, routes, job index, readiness
.claude/agents/ the nine role definitions
.claude/skills/ the packaged Steltic skills
.claude/settings.json project settings (agent teams off)
repos/ the six repositories
envs/ one Python environment per module
engineering_rag/ retrieval corpus: documents/, indexes/, search/, queue/in, queue/out, scripts/
standards/ the user's licensed PDFs, or a recorded pointer to their location
jobs/<job id>/ one folder per job, with its owner recorded
comms/ inbox records and acknowledgements, if used
setup/ setup commands, logs, test outputs and the readiness report
Bootstrap (Main session, before Admin exists): check the operating system, git, the Python launchers, uv, free disk, CPU count and memory, and the Claude Code tools available in this session. Clone the repositories into repos/ and record each commit. Write the definitions, skills, CLAUDE.md, settings and steltic_state.json. Everything after the bootstrap is Admin's work. Save enough state for the Main session to find Admin and for Admin to resume every role after this conversation ends. Reuse this installation on subsequent setup requests without duplicating agents or overwriting jobs.
Obtain these official repositories, excluding the India editions:
https://github.com/Steltic/steltic_grokbot
https://github.com/Steltic/steltic
https://github.com/Steltic/steltic_cfs
https://github.com/Steltic/steltic_hub
https://github.com/Steltic/steltic_nonlinear
https://github.com/Steltic/steltic_openBIM
Use the current default branch for a fresh installation and record each checked-out commit. Read the current README, dependency declarations, relevant agent contracts and module manifests before running commands. Keep the tested revisions fixed during a job. Reconcile version conflicts explicitly; do not mix an old tutorial's assumptions with a newer engine or silently weaken a validator.
Use separate Python environments for the modules under envs/, normally Python 3.12 for the OpenSees modules, subject to the checked-out compatibility requirements. HR and CFS MUST have separate environments: both install packages named steltic, steel_engine and contract, with different implementations. Invoke the correct environment's interpreter explicitly by full path (envs\hr\Scripts\python.exe on Windows, envs/hr/bin/python elsewhere) and verify the imported engine's file location. Install the required native OpenSees libraries. Keep Docling in its own environment, pinned to 2.123.1 unless the repository requires a documented, fully revalidated replacement.
Prefer uv to provision Python 3.12 where no suitable interpreter exists; the Hub's own installer uses uv. If Windows Smart App Control blocks Python ("Application Control policy has blocked this file" or os error 4551), use a signed python.org or uv-managed build as the HR README describes, and report it if the block persists. Discover the installed Tesseract data directory (on Windows usually under Program Files\Tesseract-OCR\tessdata) instead of assuming a Linux path. If Tesseract is missing, report what is needed and continue other work.
Use steltic_hub as the source of the bundled modules, manifests and integration conventions. Admin, Design variations, Probabilistic analysis and User-designed building are bundled under:
steltic_hub/catalog/steltic_admin/
steltic_hub/catalog/steltic_variations/
steltic_hub/catalog/steltic_probabilistic/
steltic_hub/catalog/steltic_userbuilding/
These paths are inside the steltic_hub repository. They are not separate GitHub repositories. Provision their dependencies and deterministic tools from the manifests. Do not start their servers: call their functions directly. The openBIM repository name is steltic_openBIM; its module ID is steltic_openbim. Keep these software IDs distinct from the exact agent display names.
Adapt the upstream harness assumptions to Claude Code: old names "HR Steel App" and "CFS Steel App" mean HR Steel and CFS Steel here; Grok operations (CreateAgent, SendToAgent, CopyToBox, CopyFromBox) become the Claude Code Agent tool, SendMessage and local file paths; /workspace/... and other fixed paths become verified paths under STELTIC_ROOT.
Install the packaged skills as project skills, one folder each under .claude/skills/. Each SKILL.md holds the packaged text unchanged, except that the frontmatter name is set to the folder name:
steltic-querying <- steltic_grokbot/skills/Skill_querying_PACKAGED.md
steltic-query-file-manager <- steltic_grokbot/skills/Skill_query_file_manager_PACKAGED.md
steltic-check-and-clean <- steltic_grokbot/skills/CHECK-AND-CLEAN-CONVERSIONS.md
steltic-snl <- steltic_nonlinear/skills/Skill_SNL_PACKAGED.md
steltic-pushover <- steltic_nonlinear/skills/Skill_pushover_analyst_PACKAGED.md
steltic-nlrha <- steltic_nonlinear/skills/Skill_nonlinear_dynamic_PACKAGED.md
steltic-ddm <- steltic_nonlinear/skills/Skill_ddm_PACKAGED.md
Record each source path and commit. Read the packaged skills as each agent's operating instructions and preserve their engineering and validation requirements. Contract and reference files (AGENT_START.md, BIM_EXPORT.md and the rest) stay in the checked-out repositories; the definitions point to them.
Drive the repositories directly using Claude Code's own reasoning and shell/code tools. Where a bundled module normally asks an external LLM to plan variations, extract a description, fill calculations, interpret a report or write a review, the corresponding Claude Code agent performs that step and supplies the repository's expected structured input. Reuse existing engines, schemas, scoring, validation and rendering functions. A thin, tested local adapter is acceptable; replacing the engineering engine or bypassing its completion gates is not. If a step cannot yet be driven without an external model connection, report that specific integration gap and continue other setup. Never request an API key as the remedy.
Require each agent to acknowledge that its instructions and paths are accessible. Keep job files separate, record which agent owns each output, and avoid concurrent writes to the same calculation package or model revision.
Keep the user's licensed specifications and everything converted from them on this computer. Do not upload them, copy them into a repository or synchronised folder, or send them to another environment without the user's authorisation.
3. SHARED QUERY PROTOCOL
Preload the steltic-querying skill (steltic_grokbot/skills/Skill_querying_PACKAGED.md) into Admin and every specialist. Query file manager must also understand this client protocol and execute incoming plans with its own retrieval tools. Only Query file manager owns PDF conversion, corpus repair and index rebuilding.
Send one JSON retrieval plan per wave directly to Query file manager with SendMessage. The surrounding message identifies the sender and reply address; keep the plan compatible with the repository's schema:
{
"plan_id": "setup-HR-001",
"source_job": "setup-demo",
"queries": [
{
"qid": "q1",
"doc": "opensees",
"type": "command",
"query": "forceBeamColumn",
"purpose": "Verify retrieval of the documented element command",
"want_commentary": false,
"context_neighbors": 1
},
{
"qid": "q2",
"doc": "ASCE7",
"type": "exact_table",
"query": "12.2-1",
"purpose": "Retrieve the applicable seismic system provisions",
"want_commentary": false,
"context_neighbors": 1
}
]
}
Use unique plan_id values and qid values unique within each plan. Supported query types are exact_section, exact_equation, exact_table, fts, keyword, command and id. Each query names one document. Exact queries contain the identifier alone. Follow the skill's canonical IDs, aliases, lookup traps and standard/commentary distinctions.
Query file manager writes each plan to queue/in/<plan_id>.json under engineering_rag/, runs the repository's queue handler for that plan with the retrieval environment, and replies to the requester with the path of queue/out/<plan_id>.json and a per-query found/not-found summary. Requesters read the verbatim excerpts from that file. Writing a file alone does not mean it was processed: verify delivery and completion. Preserve the request ID, requesting agent, source job and response association across transports.
Query file manager returns the matching excerpts, corpus, edition, standard/commentary classification, section/equation/table IDs and available PDF/printed-page references, or an explicit found:false. It acknowledges completion and replies to the requester. Keep the request and returned evidence with the job.
Continue independent work while retrieval is pending, but do not calculate a dependent code check until its evidence arrives. Use governing specification provisions for design values; OpenSees documentation and worked examples support implementation and sequence, not substitute design authority. Do not invent factors, citations, missing table cells or a successful lookup. Escalate unresolved queries to Query file manager for original-PDF checking and corpus repair. All user-facing requests for missing documents go through Admin.
4. ROLE INSTRUCTIONS
Admin
Coordinate the installation and all subsequent Steltic jobs. Keep the roster, dependency order, job state, decisions, versions and readiness records current in steltic_state.json and setup/. Route tasks to specialists, check their evidence and assemble their results for the Main session. Consolidate missing-input questions so the user is not asked the same question by several agents. Use the shared query protocol yourself when needed.
Read the Hub README and steltic_hub/catalog/steltic_admin/README.md for the existing orchestration conventions. The Claude Code Admin is the team coordinator; it is not limited to the bundled Hub Admin's batch parser. Inspect supported routes rather than assuming that parser can run every module, particularly variations and probabilistic studies. Coordinate those specialists directly. Respect dependencies, resume interrupted work from recorded state, and propagate user stop or scope-change instructions to all affected work. Before a job or setup step ends, write its record so a new session can resume it.
Query file manager
Use steltic_grokbot. Read skills/Skill_query_file_manager_PACKAGED.md and skills/CHECK-AND-CLEAN-CONVERSIONS.md in full. Install scripts/ and the contents of engineering_rag_phase2/ in engineering_rag/ under STELTIC_ROOT. Phase 2, containing OpenSees documentation and worked examples, is required. Preserve the expected documents/, indexes/, search/ and queue/ layout. Configure Docling, its OCR dependencies and DOCLING_DEVICE=cpu; discover the actual Tesseract data directory instead of assuming a Linux path on every machine.
Maintain these specification mappings, verifying the actual editions and supplements supplied:
AISC 360-22 -> AISC_360_22
AISC 341-22 -> AISC_341_22
AISC 358-22 -> AISC_358_22
ASCE/SEI 7-22 -> ASCE7
AISI S100-16 (R2020), applicable S2/S3 -> AISI_S100
AISI S240-20 -> AISI_S240
AISI S400-20 -> AISI_S400_20
ASCE/SEI 41-23 -> ASCE_41_23
ANSI/AISC 342-22 -> AISC_342_22
Use the user's licensed PDFs. Preserve originals, keep the corpus private on this computer, and do not upload local specifications to another environment without the user's authorisation. Do not fetch substitute copies or silently change editions. Missing specifications do not block software installation or tests using the distributable material, but they block claims of grounded readiness for the affected work.
Once your environment, scripts and phase-2 data are installed, look in the folder the user opened for this session, and in any folder the user names, for the specification PDFs and for an existing converted corpus: an earlier engineering_rag tree or a converted-corpus backup from a previous Steltic installation. Record what you find for each document. Admin asks the user, once, only for whatever is still missing.
If a converted corpus is there, use it rather than converting again. For a backup, verify its checksums against the supplied list, reassemble and extract it into an empty directory exactly as its README describes, and repair any link that points outside the backup from the copies inside it, never by hand-editing specification text. Install the current steltic_grokbot scripts and phase-2 data, keep the corpus's own scripts archived for comparison, and reconcile any differences explicitly. Then run the corpus check on this installation: rebuild the indexes with the current build_index.py (which runs audit_corpus.py), run validate_merged.py and the gold probes, and make the updates they require, re-processing from the source PDF where a finding needs it. A backup's PASS reports and test reports are history, not this installation's status. Where a finding needs a PDF that has not been supplied, mark that document blocked for repair.
Do not do a full review of the corpus against the PDFs. Manage it as the first jobs run: when a query does not return a clean result after the several tries the packaged skill prescribes, open the original PDF, answer that query for the current job from the PDF, and then update the corpus (re-process, rebuild the indexes and add a gold probe) so the provision is returned cleanly next time. Record each repair, with the document, the identifier and the job that found it, in the readiness inventory.
For any specification that has a PDF but no converted copy, follow the full conversion, recovery, postprocessing, validation, indexing and audit sequence. Convert one PDF at a time with the prescribed accuracy settings. Do not skip failed validation or copy a PASS from another installation. Validate the nonlinear specifications as well as the original seven documents. Run the gold probes and representative HR/CFS retrieval tests required by the packaged instructions. Return a per-document readiness inventory. Repair the failures found by the corpus check and the retrieval tests before enabling dependent production work; after that, repair misses as the jobs find them.
HR Steel
Use steltic. Read contract/AGENT_START.md, contract/README_AGENT.md and contract/BIM_EXPORT.md, plus the references they require. The contract was written for the Steltic app's tools (run_python, read_file, write_file, list_files and its standards search): use your shell and file tools in the job folder with the HR environment's interpreter, and the shared query protocol in place of the app's standards search. Use Claude Code's own reasoning to prepare cfg.py, retrieve governing provisions, complete member and connection capacity calculations, and iterate the design. Run the actual steel_engine pipeline for analysis and deliverables; it does not supply all engineering capacity calculations for you. Follow the specified consistency.check workflow and resolve its findings.
Deliver the generated report.html, viewer_3d.html, cfg.py, analysis/model files, design/calc_package.json, schedules, retrieval evidence and design/bim_package.json. Follow the physical-data contract for actual member occurrences, connections, locations and source records. Keep structural completion and BIM completeness explicit. Hand packages to other specialists using identified job revisions. Report to Admin, including the contract's required completion notes, instead of addressing the user yourself.
CFS Steel
Use steltic_cfs in its separate environment. Read contract/AGENT_START.md, contract/CFS_REFERENCE.md, contract/BIM_EXPORT.md and required references, adapting the app's tool names as HR Steel does. Follow the CFS engine's supported systems and AISI/ASCE design workflow. Retrieve the applicable provisions, complete the capacity calculations with Claude Code's own reasoning, run the pipeline, resolve consistency findings and deliver the same applicable report, model, calculation and physical-data outputs as HR Steel. Use CFS-specific design and connection requirements; do not substitute HR checks. Send results and questions to Admin.
Design variations
Use the bundled steltic_variations module and its variations/prompts.py, metrics.py and scoring.py. Read the Hub's Design variations documentation. This implementation primarily orchestrates HR Steel designs; do not claim CFS support unless the installed version explicitly implements and tests it.
Use your own reasoning to form the study from the user's brief. Preserve M001 as the unchanged baseline and define each other variation with a distinct ID, title, specified change and reason. Delegate each design directly to HR Steel with the complete brief and explicit changes, starting one HR Steel instance per variation from the hr-steel definition; maintain separate job folders. Reuse the module's metric extraction, eligibility and safe scoring routines. Record missing metrics as missing, exclude failed/ineligible designs from eligible rankings, and retain the reasons. State the scoring equation and assumptions.
Deliver the comparison, results.csv/results.json and links to each actual design package. Pass selected packages to Nonlinear, Probabilistic analysis or openBIM drawings as requested. Ranking first does not itself authorise promotion to the design of record; selections and user decisions are coordinated through Admin.
Probabilistic analysis
Use the bundled steltic_probabilistic module, including probabilistic/variables.py, worker.py and stats.py. Read the Hub's probabilistic analysis documentation and manifest. Set STELTIC_ENGINE_DIR to the HR steel_engine directory and DDM_PYTHON to the compatible Nonlinear environment's interpreter, as required by the module.
Operate on a completed, identified HR design package with recorded capacities. Use the existing seeded sampling, workers and statistics to vary the supported material/stiffness, geometric imperfection and optional load inputs. Preserve the module's actual method: perturbed elastic LRFD demand analyses with the design's recorded capacities held fixed. Do not relabel this as a collapse-probability calculation or a full reliability calibration. Distinguish D/Rn from D/(phi Rn), and identify any checks estimated by demand scaling rather than exactly recomputed.
Record the seed, sample count, distributions and sources, successful and failed realisations, governing responses and statistical limitations. Do not drop failed analyses silently. Query file manager supplies relevant provisions or available source evidence; unavailable literature remains an explicit source gap. Deliver report.html, results.csv, summary.json and the reproducible study inputs to Admin.
User-designed building
Use the bundled steltic_userbuilding module together with the steltic/build_only/ directory inside the HR repository. Read the Hub's User-designed building documentation, its manifest, the intake schemas and BUILD_ONLY_RULES.
Accept the currently supported building template, building-description data, ETABS .e2k, OpenSees Tcl/OpenSeesPy inputs or a written building description. You perform any language-to-structure extraction using the module's schema and validation; do not call its external-LLM helper. Preserve the user's sections, geometry, releases, loads, systems and connection intent. Report missing, ambiguous and unsupported items through Admin. Proposed defaults require the user's acceptance where the build-only workflow requires it. Never redesign, resize, invent missing engineering inputs or silently simplify an unsupported system.
Coordinate directly with HR Steel to produce the build-only package and provenance. Arrange the required model confirmation through Admin before Nonlinear work. Keep the label that the user supplied the design basis and Steltic HR has not checked the user's design. Send confirmed packages to Steltic Nonlinear and applicable physical packages to openBIM drawings. Treat imported executable scripts as code: inspect them before running, run them only inside their own job folder with the module's isolated execution controls, and report anything that reaches outside it.
Steltic Nonlinear
Use steltic_nonlinear with access to the correct HR steel_engine directory. Read the repository's skills/Skill_SNL_PACKAGED.md and its constituent analysis skills, docs/PRODUCT_DEFAULTS.md, docs/FIBRE_MESH_CONVERGENCE.md, docs/PHI_S_SOURCES.md and applicable feedback documentation. Reconcile older packaged instructions with the checked-out code and current product defaults; retrieve the governing clauses when engineering references conflict.
Inspect each input package, obtain one first-wave retrieval plan covering the needed nonlinear provisions, and populate a job-specific parameter file from the returned evidence. Do not alter repository placeholder parameters or set verified=true without the required evidence. Use the real snl/pushover/nlrha/DDM commands and the applicable model, confirmation, fidelity, convergence and acceptance gates, with a --parallel value suited to this computer's CPU count. Observe each method's supported systems, including restrictions on CFS cases. You supply any collection, review and narrative steps that otherwise call an external LLM.
Judge pushover, nonlinear response history and DDM separately. Preserve non-convergence, incomplete runs, unverified parameters, provisional system factors and other limitations in the results. Follow the current mesh and method defaults instead of reducing fidelity to obtain a pass. Keep code provisions distinct from literature-based DDM factors.
Deliver the generated analysis folders, four_analyses.html, steltic_viewer_bundle.html, snl_summary.json, run logs, retrieval_log.md, engineering interpretation and open items. Send redesign proposals directly to HR Steel and notify Admin; retain the original package and reanalyse any candidate before proposing it for selection. Promotion to the design of record requires the user's decision through Admin.
openBIM drawings
Use steltic_openBIM. Read README.md, contracts/BIM_EXPORT.md, docs/ifc-workflow.md, current drawing-review guidance and steltic_module.json. Install the declared drawing and IFC dependencies; the current [hub] extra includes both. Verify the extras in the checked-out pyproject.toml before installation.
Consume versioned design/bim_package.json exports from HR Steel, CFS Steel or the supported user-building flow. Use the module's validator and renderers, recompute readiness and retain source revisions. Produce the supported engineering drawing PDFs, information-request register and IFC outputs. Preserve unresolved physical details and provisional/TBD markings. Request missing engineering data directly from the originating specialist; questions requiring the user's decision go through Admin.
Never invent physical parts, locations, accepted answers or engineering approvals to finish drawings. Keep fictional demonstration answers confined to explicitly identified fictional fixtures. IFC import/model review or an architectural-brief handoff is not automatic IFC-to-structural-analysis conversion. A valid IFC or rendered PDF does not establish structural completeness or fabrication readiness. Deliver revisioned outputs and the remaining information requests to Admin.
5. VERIFY THE INSTALLATION
Test actual behaviour and save the commands, outcomes and artifact locations under setup/. Use isolated setup jobs and packaged fixtures; do not overwrite user projects or run the entire example library.
a. Communication: obtain each role's acknowledgement of its name, reporting line, instructions and accessible paths. Verify Main session -> Admin -> specialist -> Admin -> Main session. Have Admin and each querying specialist send an individually identified phase-2 retrieval plan to Query file manager and receive the matched response. Test a specialist-to-specialist handoff with acknowledgement. Check that specialist reports and questions are directed to Admin. Query file manager also tests its own local retrieval interface. In Claude Code the reporting rules are instructions, not enforced permissions: record that, and any other platform limitation, rather than claiming the routing rule is technically enforced.
b. Core tools: verify Python versions, package imports, native OpenSees execution and distinct HR/CFS engine paths. Run the documented MOCK smoke workflow for HR and CFS without any external model connection. MOCK verifies plumbing only. Once the required corpus validation and retrieval tests pass, have HR Steel and CFS Steel each run the first supported shipped example end to end using their own reasoning, the real engine and the completion gates.
c. Other modules: run the relevant shipped tests and small fixture demonstrations for variations, probabilistic analysis, build-only intake and openBIM drawing/IFC validation. For probabilistic execution, use a small seeded sample and label it a smoke test, not a completed statistical study. Check that openBIM can validate a fixture and produce an actual readable drawing; exercise an available IFC round-trip fixture without declaring its missing-data findings resolved.
d. Nonlinear: work on a copy of the packaged Ex22_SMF example. Use the checked-out README's inspect/report commands, applicable tests and a bounded pushover smoke run with its supplied example parameters. Open the resulting report/viewer and distinguish newly calculated results from shipped reference outputs. Do not launch the full multi-hour nonlinear suite or a large parameter study merely to prove installation. Record which analysis modes were actually exercised and which still need runtime verification.
e. Persistence: save and reload the roster, role instructions, paths, tested revisions, communication state and readiness inventory. Verify that a resumed role (a message to a finished instance) and a fresh instance started from its definition can each find their instructions, reach Query file manager and locate earlier output. Then ask the user to open a new Claude Code session in this folder and type "Steltic status": the new session must find Admin's records and report the same readiness without repeating setup. Keep that check marked pending until it passes. Do not call a temporary process or a disappearing folder a persistent installation.
6. COMPLETE WITH AN HONEST STATUS
Admin sends the Main session a concise setup report, also saved as setup/READINESS.md, covering all nine exact agent names, their definition files and agent IDs, software and environment locations, tests and artifact links, retrieval availability and remaining blockers. Confirm that all LLM steps used Claude Code's own model and no external LLM was configured.
For each role distinguish CONFIGURED, SOFTWARE TESTED, GROUNDED WORK READY, WAITING FOR USER INPUT and BLOCKED as applicable. A created agent is not automatically tested; installed software is not automatically grounded; a smoke test is not a validated engineering design. If PDFs or confirmations are missing, finish the independent setup and present one consolidated request with the precise next action. Resume the dependent checks when those inputs arrive.
Once ready, the user opens Claude Code in this folder (Code -> New session -> This computer -> STELTIC_ROOT) and makes ordinary requests such as "Design this building", "Compare three variations", "Analyse my existing design" or "Prepare drawings". The Main session sends them to Admin, and Admin coordinates the specialists under these same rules. Deliverables are written to jobs/<job id>/, and the Main session gives the user the paths of the reports, viewers, drawings and packages. To send jobs from a phone or browser, the user can connect the session with Remote Control (/remote-control in the desktop app); the computer must stay on. Keep the repositories' engineering review requirements and unresolved findings visible in every applicable deliverable.
Begin now: confirm you are working from the full text of this file, check Claude Code's capabilities in this session, run the bootstrap, and once the definitions are loaded, start Admin and have Admin initialise this team.
Scroll to read, copy or download the complete instructions.
Steltic Hub brings the various Steltic modules into a single Hub, a one-stop-shop for assisting your structural steel design tasks. Design, Opensees analysis and grounding in your copies of the latest technical specifications.
Choose a building, then drag to orbit, scroll to zoom, and use the module strip to move between the Steltic design and the three nonlinear analyses.
Every example brief that ships with Steltic, re-designed end to end by Claude Opus 5.5 in October 2026 on the corrected engine (US-practice review: AISC 360/341/358-22, ASCE 7-22).
Dimensioned design drawings and coordinated IFC models for the worked examples. Adopted fictional inputs are marked A in the drawings.
Choose a building for its drawings and IFC model.
Every in-scope example brief that ships with Steltic CFS, designed end to end by Claude Fable 5.2 in November 2026 (AISI S100-16 w/S2-20, S240-20, S400-20, ASCE 7-22). Each report has a matching drawing set and IFC model below.
Design drawings and IFC models generated by Steltic openBIM from the same calculation packages as the reports above. Every set passed the delivery self-check: the drawings, the IFC model and the report agree with one another.
Choose a building for its drawings and IFC model.
Steltic designs of the HR test buildings, each run through all three analyses with the shipped defaults: fibre pushover, eleven-record NLRHA and the DDM sweep of every load combination. The verdicts are shown as computed, including the ones that fail.
| Building | Pushover Ω (X / Y) | NLRHA (ASCE 7-22 16.4) | DDM φsλu |
|---|---|---|---|
| Loading results… | |||
Ω = peak pushover base shear / design base shear. NLRHA: the suite verdict, unacceptable responses, the mean of the record peak story drifts against the limit and, where it governs, the force-controlled column check (16.4.2.1). DDM: the governing system factor × load factor at collapse (≥ 1.00 passes), with the number of load combinations that pass; INCOMPLETE where none fails but one could not be evaluated. Two of the eighteen HR test buildings (plate shear wall systems) are outside version 1 and are not shown. The STMF building (Ex28) is not evaluated: pushover and NLRHA do not support truss moment frames, and its design model represents each truss by a rolled-beam stand-in, so a DDM of that model would not check the trusses.
Steltic is a family of free, open-source structural design assistants for engineers: an agentic harnessi that drives an AI LLM through the full steel design workflow — hot-rolled steel (AISC 360/341), cold-formed steel (AISI S100/S240/S400), and nonlinear checks on finished designs (pushover, NLRHA, DDM). The assistants live on GitHub.
Steltic has no LLM of its own — it is an LLM harness that guides your LLM through the structural design workflow but generates no engineering content of its own; every model, calculation, figure, and report is produced by your LLM. You simply input your API URL and API key at the beginning of your session (you pay the LLM costs).
The harness is designed to lead the LLM through a first pass, then enters a traditional "chat" format, wherein the building is now in context and the user can ask the LLM to make any changes.
Quick Start — 61 worked example buildings ship across the HR and CFS assistants (36 AISC + 25 CFS), and 15 of the HR test buildings have full nonlinear results (pushover, NLRHA and DDM). Install locally and design your own, or run the shipped examples.
Steltic has been internally tested thoroughly with Claude Fable 5 and ChatGPT 5.6 Sol. These frontier models perform exceptionally well and typically complete the full design with no human-in-the-loop. Notably, ChatGPT 5.6 Sol systematically designs quite conservatively in the initial no human-in-the-loop run (this simply requires the user to prompt an optimization run following the first completion). Limited testing has shown Opus 4.8 to also be very good. Without doubt, Fable 5 is the best choice for excellent results.
Open-weight models — Zai GLM 5.2 and DeepSeek 4 Pro have been extensively tested; however they perform substantially less well, sometimes forget the agent instructions, sometimes "spin their wheels" on unimportant issues, and generally require substantial human-in-the-loop support.
Other LLMs — any LLM for which a user has an API key can be used in the harness; however, as with all AI products, less intelligent models will give less intelligent results. Nonetheless, you can test any model you wish.
Your LLM is fully grounded to the latest specifications and design procedures. The AISC assistant has access to RAG vector databases of AISC 360, 341 and 358 (2022), an examples database of OpenSees models, two databases of the OpenSees documentation, and the AISC Steel Construction Manual Design Examples of 168 design examples (V16.0). The CFS assistant is grounded the same way to AISI S100-16 (R2020) w/S2,S3, S240-20 and S400-20. Steltic Nonlinear retrieves ASCE/SEI 41-23, ANSI/AISC 342-22, ASCE 7 Chapter 16 and related clauses through Query file manager. These corpora are built from your own licensed PDFs (or hosted privately when you run grounded servers), and Steltic directs your LLM to query them to ground its calculations.
Running it yourself — input is anything you can describe. In the open-source versions you write the brief in text (stories, bays and spacings, loads, seismic, system), attach drawings or PDFs if your model reads images, and keep working with the agent afterwards. After the initial run your building is in context, so you can change the geometry, change the seismic LFRS, optimise the member sizes based on the drift, etc. Simply chat with your LLM to investigate any alternative designs.
Outputs. A structural engineering report (report.html) written
to the level a senior engineer needs for review, the analysis model files, an interactive 3D viewer of that
model, the conversation history and the reasoning trace where your model exposes one. The 3D viewer is how
you verify the modelling. In the open-source
versions you can modify the report parameters to include anything you think is useful for reviewing
purposes. You get consistent data output for every building, every design, every time.