원클릭으로
auto-resume
Recover active change and next action from artifacts. Use on fresh session with existing work.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Recover active change and next action from artifacts. Use on fresh session with existing work.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Optional engineering go/no-go on a plan. Use when execution safety needs review before implementation.
Implement approved plan slices. Use as the execute-stage entry point.
Bound and de-risk a request into SPEC.md. Use when the objective is clear but scope needs constraining.
Sharpen a vague idea into a bounded objective. Use before framing when scope is undefined.
Build project truth from repo evidence. Use when steering is missing or stale.
Turn an approved spec into ordered slices. Use when framing is accepted and planning begins.
| name | auto-resume |
| description | Recover active change and next action from artifacts. Use on fresh session with existing work. |
| metadata | {"stage":"resume"} |
Session recovery. Rebuilds context from durable artifacts, not memory or guessing.
First action: run node .agent/.automaton/scripts/get-context.mjs from the project root.
auto-resume rebuilds context from durable artifacts, not from the user's description or the agent's training data. It does not modify artifacts, advance the stage, or start new work. It loads canonical artifacts in dependency order (spec first, then design, then plan) and reports what it found, what was blocked, and what comes next.
Loading discipline: start with artifacts needed for the current stage. Read project files when understanding the codebase helps rebuild accurate context for the next action. Read .agent/.automaton/references/CONTEXT-BUDGET.md when wider reads threaten context pressure.
Before producing the recovery summary:
references/quality.md when the summary becomes narrative recap.Read .agent/.automaton/references/ARTIFACT-LIFECYCLE.md for recovery order, stale-pointer handling, and stage handoffs.
Halt and report when:
.agent/ does not exist or current.json is missing.Recommend auto-onboard and stop. Do not attempt recovery without a state file.
If work is complete or absent, read .agent/steering/ROADMAP.md only to surface pending phases as context.
Check that canonical_spec, canonical_design, and canonical_plan resolve when present. If any pointer is stale, report it plainly; recommend auto-onboard for missing steering, auto-frame for missing SPEC.md, or auto-plan for missing PLAN.md.
Treat current.json as the only source for active change, stage, and canonical artifact pointers. Load artifacts in dependency order and stop at the current stage; read references/artifact-order.md for the full stage table.
When stage is execute or verify and the project is a git repo, read the execution ledger before summarizing: git log --oneline -15 and git status --porcelain. Per-slice commits (slice N: ..., slice N gap-fix: ...) mark verified slices; match them against PLAN.md slice evidence. A dirty tree on top of the last slice commit is in-flight work for the next slice, not noise: name the touched files. When commits and PLAN.md evidence disagree, trust the commits and report the mismatch. Also run git worktree list: a stray worktree is the fingerprint of an interrupted parallel dispatch. Report it; do not remove it.
If current.json contains engineering_review, read the ## Review: Engineering section from the canonical plan and include it in the resume summary.
Produce a concise summary in this shape:
**Active change:** [name]
**Stage:** [frame|plan|execute|verify|verified|resume]
**Artifacts loaded:** [list]
**What was done:** [1-2 sentences]
**What was blocked:** [1-2 sentences, or "nothing"]
**What comes next:** [specific next action, or "none - change complete"]
**Execution ledger:** [last slice commit + in-flight files, "clean", or "n/a"]
**Review verdicts:** [engineering: X, or "none"]
**Missing state:** [list or "none"]
**Roadmap:** [N pending / M total, or "not tracked"]
The goal is orientation, not transcription.
Use references/recovery-scenarios.md for the full routing table. The invariant: recommend the next lifecycle skill only when recovered state is incomplete or blocked. For verified completion, report no next lifecycle skill; if ROADMAP.md has pending items, surface them as optional future work, not an automatic auto-office-hours handoff.
.agent/.automaton/state/current.json is read-only for auto-resume; stale pointers are reported, not silently repairedNext: <skill>; none when the active change is verified complete. The user picks the direction.auto-onboard.auto-office-hours handoff.