forge-deploy
Skill2 starsChanged 5 months agoMITView on GitHub
Run Stage 8 of the Forge pipeline — deployment. Use when the user says
In this repository46 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- forge-opencode/CLAUDE.mdCLAUDE.md
- forge-adoptSkill
- forge-arch-proSkill
- forge-archSkill
- forge-autopilotSkill
- forge-autopilot-stopSkill
- forge-build-proSkill
- forge-buildSkill
- 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
10 rules. About 0 are common, 2 are distinctive, and 8 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 32
If eval-report is missing or shows failures: "Stage 7 evaluation must pass before deploying."
- Very specific: line 33
Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/check-gate.py --stage 7 to check gate status.
- Very specific: line 34
Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/load-profile.py --cwd .
- Very specific: line 43
Read agents/devops.md to load the DevOps persona.
- Very specific: line 45
Read pipeline/03-architecture/architecture.md for topology and pipeline/04-spec/technical-spec.md for config needs.
- Distinctive: line 46
Follow the DevOps workflow: pre-deployment checklist, ordered steps, health checks, rollback plan.
- Very specific: line 47
Write pipeline/08-deploy/deploy-plan.md and pipeline/08-deploy/runbook.md — or pipeline/08-deploy/package-spec.md when replace_with: …
- Very specific: line 50
Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/state-manager.py advance --to 8 after successful deploy/publish.
≈ “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:deploy — Deployment
When to Use
- User says
/forge:deploy - User wants to deploy to staging or production, write a deployment plan, or create a runbook
- Working in a Forge project at Stage 7 or 8
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 8If 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/07-evaluation/eval-report.mdexists and shows overall pass. If eval-report is missing or shows failures: "Stage 7 evaluation must pass before deploying." - Run
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/check-gate.py --stage 7to check gate status. - Run
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/load-profile.py --cwd . --stage 8to load project-type overrides. If the profile setsskip: true(CLI, library) the conventional service-deploy is replaced bypackage-publish— produce a package-spec artifact instead of a deployment runbook. - Run
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/check_docker_readiness.py --cwd .unconditionally — every project gets this, regardless of profile (it self-no-ops with no Docker artifacts). This is advisory only: it exits 0 even with findings, and anyWARN:lines it prints must be relayed to the user as advisory notes — it never blocks and does not gate this stage.
Steps
- Read
agents/devops.mdto load the DevOps persona. - Adopt that persona — you are now the DevOps Engineer.
- Read
pipeline/03-architecture/architecture.mdfor topology andpipeline/04-spec/technical-spec.mdfor config needs. - Follow the DevOps workflow: pre-deployment checklist, ordered steps, health checks, rollback plan. If the profile specifies
replace_with: package-publish, follow that flow instead (build artifacts, registry credentials, version verification, publish, post-publish smoke). - Write
pipeline/08-deploy/deploy-plan.mdandpipeline/08-deploy/runbook.md— orpipeline/08-deploy/package-spec.mdwhenreplace_with: package-publish. - Execute deployment (or publish) steps (with user confirmation for destructive operations),
recording what happened in
pipeline/08-deploy/deploy-log.md. - Run
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/state-manager.py advance --to 8after successful deploy/publish.
Verification
After running, confirm:
pipeline/08-deploy/deploy-plan.mdexists with rollback procedurepipeline/08-deploy/deploy-log.mdrecords the deployment outcomepipeline/08-deploy/runbook.mdexists- Health checks pass post-deployment
pipeline/state.mdshowscurrent_stage: 8
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 8Does 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.

