원클릭으로
forensics
Post-mortem investigation for failed or stuck workflows. Analyzes git history and planning artifacts.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Post-mortem investigation for failed or stuck workflows. Analyzes git history and planning artifacts.
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
Run multiple phases hands-free. Chains discuss, plan, build, and verify automatically.
Start a new project. Deep questioning, research, requirements, and roadmap.
Execute all plans in a phase. Spawns agents to build in parallel, commits atomically.
Configure settings: depth, model profiles, features, git, and gates.
Execute the next logical step automatically. No prompts, no decisions — just do it.
Systematic debugging with hypothesis testing. Persistent across sessions.
| name | forensics |
| description | Post-mortem investigation for failed or stuck workflows. Analyzes git history and planning artifacts. |
| allowed-tools | Read, Bash, Glob, Grep, Write, AskUserQuestion |
| argument-hint | [description of what went wrong] |
STOP — DO NOT READ THIS FILE. You are already reading it.
Read-only investigation for failed or stuck workflows. Analyzes git history, .planning/ artifacts, and file system state to detect anomalies. Writes a diagnostic report. Does NOT modify project files.
╔══════════════════════════════════════════════════════════════╗
║ PLAN-BUILD-RUN ► FORENSICS ║
╚══════════════════════════════════════════════════════════════╝
If $ARGUMENTS is empty, ask: "What went wrong? Describe the issue — e.g., 'autonomous mode got stuck on phase 3', 'execute-phase failed silently', 'commits seem wrong'."
Collect data from all available sources. Missing sources are fine — adapt.
git log --oneline -30
git log --format="%H %ai %s" -30
git log --name-only --format="" -20 | sort | uniq -c | sort -rn | head -20
git status --short
git diff --stat
Record: commit timeline, most-edited files, uncommitted changes.
Read if they exist: STATE.md, ROADMAP.md, config.json. Extract current phase, last session, blockers.
For each phase in .planning/phases/*/, check which artifacts exist vs expected (PLAN, SUMMARY, VERIFICATION, CONTEXT, RESEARCH).
git worktree list
Check for orphaned worktrees from crashed agents.
Same file in 3+ consecutive commits within a short time window. HIGH confidence if commit messages are similar.
Phase appears complete (has commits, past in roadmap) but lacks PLAN, SUMMARY, or VERIFICATION.
Large gap between last commit and now, with STATE.md showing mid-execution.
Uncommitted changes + STATE.md active + orphaned worktrees.
Recent commits touch files outside current phase's expected scope (from PLAN.md).
Commit messages containing "fix test", "revert", or re-commits of test files.
mkdir -p .planning/forensics
Write to .planning/forensics/report-{YYYYMMDD-HHMMSS}.md:
# Forensic Report
**Generated:** {ISO timestamp}
**Problem:** {user's description}
## Evidence Summary
### Git Activity
- **Last commit:** {date} — "{message}"
- **Commits (last 30):** {count}
- **Uncommitted changes:** {yes/no}
- **Active worktrees:** {count}
### Planning State
- **Current phase:** {N} — {name} ({status})
- **Last session:** {date}
- **Blockers:** {list or "none"}
### Artifact Completeness
| Phase | PLAN | SUMMARY | VERIFICATION | Status |
|-------|------|---------|-------------|--------|
| {N} | {Y/N} | {Y/N} | {Y/N} | {complete/incomplete} |
## Anomalies Detected
### {Anomaly Name}
**Confidence:** {HIGH/MEDIUM/LOW}
**Evidence:** {specific data points}
**Impact:** {what this caused}
**Recommendation:** {what to do}
## Recommendations
1. {Prioritized action items}
Display a summary of findings inline, point to the full report on disk:
Report: .planning/forensics/report-{timestamp}.md
Anomalies found: {count}
- {anomaly 1}: {brief}
- {anomaly 2}: {brief}
Recommended: {top action item}
Optionally offer to create a GitHub issue with the findings.