forge-arch
Skill2 starsChanged 5 months agoMITView on GitHub
Run Stage 3 of the Forge pipeline — system architecture. Use when the
In this repository46 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- forge-opencode/CLAUDE.mdCLAUDE.md
- forge-adoptSkill
- forge-arch-proSkill
- forge-autopilotSkill
- forge-autopilot-stopSkill
- forge-build-proSkill
- forge-buildSkill
- forge-deploySkill
- forge-doctorSkill
- dreamer-runSkill
- forge-evalSkill
- forge-feedbackSkill
- flowSkill
- forge-force-advanceSkill
- graduateSkill
- health-checkSkill
- forge-initSkill
- forge-monitorSkill
- forge-orchestrateSkill
- forge-plan-proSkill
- forge-planSkill
- preflightSkill
- forge-product-proSkill
- forge-productSkill
- forge-releaseSkill
- forge-resolveSkill
- forge-resumeSkill
- forge-retroSkill
- forge-reviewSkill
- forge-rulesSkill
- forge-set-profileSkill
- skill-creatorSkill
- forge-spec-proSkill
- forge-specSkill
- forge-sprint-proSkill
- forge-sprintSkill
- forge-srs-proSkill
- forge-srsSkill
- forge-statusSkill
- forge-trace-matrixSkill
- forge-uninstallSkill
- forge-validateSkill
- watchSkill
- watch-stopSkill
- forge-whySkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 1 is distinctive, and 8 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 26
If it exits non-zero, STOP: present its message verbatim and do not proceed — the prior stage must be completed first (or use …
- Very specific: line 30
Read pipeline/state.md — confirm Forge project.
- Distinctive: line 33
If stage > 3, ask if the user wants to revise architecture.
- Very specific: line 34
Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/load-profile.py --cwd .
- Very specific: line 38
Read agents/system-architect.md to load the System Architect persona.
- Very specific: line 40
Read pipeline/01-srs/srs.md and pipeline/02-product-ux/prd.md.
- Very specific: line 41
Follow the System Architect workflow: C4 diagrams, data model, API surface, security model, ADRs.
- Very specific: line 42
Write pipeline/03-architecture/architecture.md, ADR files, and any profile-specified extra artifacts per the Output Contract.
- Very specific: line 43
Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/state-manager.py advance --to 3 to mark Stage 3 active.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/forge:arch — System Architecture
When to Use
- User says
/forge:architectureor/forge:arch - User wants system design, C4 diagrams, data model, API contracts, or ADRs
- Working in a Forge project at Stage 2 or 3
Pre-flight Check
Entry gate (REQ-GATE-ENTRY-001) — before adopting the persona, verify the prior stage's artifact exists:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/state-manager.py preflight --stage 3If it exits non-zero, STOP: present its message verbatim and do not proceed —
the prior stage must be completed first (or use /forge:force-advance to skip
intentionally).
- Read
pipeline/state.md— confirm Forge project. - Confirm
pipeline/01-srs/srs.mdexists. If not: "Complete Stage 1 first (/forge:srs)." - Confirm
pipeline/02-product-ux/prd.mdexists (warn if missing but don't block). - If stage > 3, ask if the user wants to revise architecture.
- Run
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/load-profile.py --cwd . --stage 3to load project-type overrides. Note anyadditional_concerns(e.g., ML: training/inference path, checkpoint format; fullstack: SSR/SSG strategy, BFF boundary; API: versioning, pagination, idempotency) andadditional_artifacts(e.g., openapi-spec.yaml, route-manifest.md).
Steps
- Read
agents/system-architect.mdto load the System Architect persona. - Adopt that persona — you are now the System Architect.
- Read
pipeline/01-srs/srs.mdandpipeline/02-product-ux/prd.md. - Follow the System Architect workflow: C4 diagrams, data model, API surface, security model, ADRs. Address every
additional_concernsitem from the profile in the architecture doc, and produce anyadditional_artifactslisted. - Write
pipeline/03-architecture/architecture.md, ADR files, and any profile-specified extra artifacts per the Output Contract. - Run
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/state-manager.py advance --to 3to mark Stage 3 active.
Verification
After running, confirm:
pipeline/03-architecture/architecture.mdexists with C4 diagrams and data model- At least one ADR exists in
pipeline/03-architecture/adr/ pipeline/state.mdshowscurrent_stage: 3
Next Step
Derive the hint from the canonical stage table — never hardcode it (REQ-NEXTHINT-001, single source of truth). Run the helper and present its output to the user verbatim:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/state-manager.py next-hint --stage 3Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

