New command that investigates failed or stuck GSD workflows by analyzing git history, .planning/ artifacts, and file system state. Detects 6 anomaly types: stuck loops, missing artifacts, abandoned work, crash/ interruption, scope drift, and test regressions. Inspired by gsd-build/gsd-2's forensics feature, adapted for gsd-1's markdown-prompt architecture. Uses heuristic (LLM-judged) analysis against available data sources rather than structured telemetry. - commands/gsd/forensics.md: command with success_criteria + critical_rules - get-shit-done/workflows/forensics.md: 8-step investigation workflow - tests/forensics.test.cjs: 21 tests (command, workflow, report, fixtures) - tests/copilot-install.test.cjs: bump expected skill count 55→56 Generates report to .planning/forensics/, offers interactive investigation, and optional GitHub issue creation from findings. Closes #1303 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
57 lines
2.3 KiB
Markdown
57 lines
2.3 KiB
Markdown
---
|
|
type: prompt
|
|
name: gsd:forensics
|
|
description: Post-mortem investigation for failed GSD workflows — analyzes git history, artifacts, and state to diagnose what went wrong
|
|
argument-hint: "[problem description]"
|
|
allowed-tools:
|
|
- Read
|
|
- Write
|
|
- Bash
|
|
- Grep
|
|
- Glob
|
|
---
|
|
|
|
<objective>
|
|
Investigate what went wrong during a GSD workflow execution. Analyzes git history, `.planning/` artifacts, and file system state to detect anomalies and generate a structured diagnostic report.
|
|
|
|
Purpose: Diagnose failed or stuck workflows so the user can understand root cause and take corrective action.
|
|
Output: Forensic report saved to `.planning/forensics/`, presented inline, with optional issue creation.
|
|
</objective>
|
|
|
|
<execution_context>
|
|
@~/.claude/get-shit-done/workflows/forensics.md
|
|
</execution_context>
|
|
|
|
<context>
|
|
**Data sources:**
|
|
- `git log` (recent commits, patterns, time gaps)
|
|
- `git status` / `git diff` (uncommitted work, conflicts)
|
|
- `.planning/STATE.md` (current position, session history)
|
|
- `.planning/ROADMAP.md` (phase scope and progress)
|
|
- `.planning/phases/*/` (PLAN.md, SUMMARY.md, VERIFICATION.md, CONTEXT.md)
|
|
- `.planning/reports/SESSION_REPORT.md` (last session outcomes)
|
|
|
|
**User input:**
|
|
- Problem description: $ARGUMENTS (optional — will ask if not provided)
|
|
</context>
|
|
|
|
<process>
|
|
Read and execute the forensics workflow from @~/.claude/get-shit-done/workflows/forensics.md end-to-end.
|
|
</process>
|
|
|
|
<success_criteria>
|
|
- Evidence gathered from all available data sources
|
|
- At least 4 anomaly types checked (stuck loop, missing artifacts, abandoned work, crash/interruption)
|
|
- Structured forensic report written to `.planning/forensics/report-{timestamp}.md`
|
|
- Report presented inline with findings, anomalies, and recommendations
|
|
- Interactive investigation offered for deeper analysis
|
|
- GitHub issue creation offered if actionable findings exist
|
|
</success_criteria>
|
|
|
|
<critical_rules>
|
|
- **Read-only investigation:** Do not modify any project files during forensics. Only write the report.
|
|
- **Redact sensitive data:** Strip absolute paths, API keys, tokens from reports and issues.
|
|
- **Ground findings in evidence:** Every anomaly must cite specific commits, files, or state data.
|
|
- **No speculation without evidence:** If data is insufficient, say so — do not fabricate root causes.
|
|
</critical_rules>
|