en un clic
build
Plan, approve, implement, verify, and record a software change.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Menu
Plan, approve, implement, verify, and record a software change.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Turn a repetitive manual procedure into a proven, repeatable mechanism. Use when the user explicitly invokes the automation pipeline.
Plan, approve, implement, verify, and record a software change. Use when the user explicitly invokes the build pipeline.
Record a durable architecture decision with alternatives and consequences.
Discover, approve, implement, prove, review, and record a software change. Use when the user explicitly invokes the delivery pipeline.
Leave unfinished repository work safe for another human or agent to resume.
Evaluate whether retained evidence supports the delivery claims being made.
| name | build |
| description | Plan, approve, implement, verify, and record a software change. |
| disable-model-invocation | true |
| argument-hint | <task> |
Use this pipeline for repository changes that should leave an auditable plan, result, and history entry. Treat the user's invocation text as the task; do not invent a separate objective.
Task: $ARGUMENTS
Record harness as claude in the run ledger.
Clarify the requested outcome from available context. Inspect the repository before asking
questions that the files can answer. Create the run folder and write task.md containing the
outcome, constraints, assumptions, and acceptance checks. Reserve an empty evidence/ folder.
Write plan.md in the run folder. Name the files or components to change, the intended behavior,
the verification commands, and material risks. Keep the plan executable by another capable agent.
STOP after completing this stage. Do not execute until the user explicitly approves the written plan. Request the verdict by writing approvals/plan-approval.md.request in the run folder describing what needs approval, then stop. The verdict is recorded from outside the session: base approve <run-slug> plan-approval (or --deny) writes approvals/plan-approval.md — a standing directive counts only when recorded that way, with --note citing it. Never create the verdict artifact yourself. If the recorded verdict is denied, skip to record with outcome aborted.
Implement the approved plan without widening scope. Run the planned checks and capture a concise
result.md with changed paths, verification results, and any remaining limitations. Put durable
proof files under evidence/ when useful.
Run the acceptance checks named in task.md and the approved plan. Capture the commands and their
real output as files under evidence/; reference them from result.md with a pass or fail verdict
per check. A failing check means the run is not completed — fix it or record the honest outcome.
Never substitute a claim for a captured result.
Run base verify base --run <run-slug>. A fail or inconclusive verdict is not passing evidence and must be reported before proceeding.
Always run this stage, including after rejection, failure, or abort. Append exactly one compact JSON
object line to .base/history.jsonl with slug, date, pipeline, harness, outcome, and
paths. Use completed, aborted, or failed for outcome; never rewrite previous lines.