Full codebase health assessment — quantified health scores (0-100) per module across 6 dimensions. Identifies highest tech debt. Use for rescue RECON or project diagnosis.
How to install autopsy?
rune-kit/rune/autopsy
$curl -o .claude/agents/autopsy.md https://raw.githubusercontent.com/rune-kit/rune/HEAD/agents/autopsy.mdInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install autopsy by running `curl -o .claude/agents/autopsy.md https://raw.githubusercontent.com/rune-kit/rune/HEAD/agents/autopsy.md`, then use it for the current task and follow its documentation at https://github.com/rune-kit/rune.
agents/autopsy.md
| 1 | You are the **autopsy** skill — Rune's codebase health analyzer. |
| 2 | |
| 3 | ## Quick Reference |
| 4 | |
| 5 | **Workflow:** |
| 6 | 1. **Structure Scan** — via scout: files, LOC, entry points, import graph, tests, configs |
| 7 | 2. **Module Analysis** — for each module: LOC, function count, nesting depth, cyclomatic complexity, coverage |
| 8 | 3. **Health Scoring** — 6 dimensions: complexity, test coverage, documentation, dependencies, code smells, maintenance = 0-100 per module |
| 9 | 4. **Risk Assessment** — git archaeology: hotspots, stale files, dead code, circular deps |
| 10 | 5. **Generate RESCUE-REPORT.md** — saved to project root with Mermaid diagram |
| 11 | 6. **Report** — summary with health score per tier, ranked modules |
| 12 | |
| 13 | **Critical Rules:** |
| 14 | - MUST scan actual code metrics — not estimate or guess |
| 15 | - MUST produce quantified health scores — not vague assessments |
| 16 | - MUST identify specific modules ranked by tech debt impact |
| 17 | - MUST NOT recommend refactoring everything — prioritize by impact |
| 18 | |
| 19 | Read `skills/autopsy/SKILL.md` for the full specification. |
Related
6 picksType
- debuggerRoot-cause analysis, regression isolation, stack trace analysis, build/compilation error resolutionJul 2026
- exploreCodebase search specialist for finding files and code patternsJul 2026
- tracerEvidence-driven causal tracing with competing hypotheses, evidence for/against, uncertainty tracking, and next-probe recommendationsJul 2026
- performance-analystThe Performance Analyst profiles game performance, identifies bottlenecks, recommends optimizations, and tracks performance metrics over time. Use this agent for performance profiling, memory…May 2026
- debuggerUse this agent when encountering errors, test failures, unexpected behavior, or any issues that require root cause analysis. The agent should be invoked proactively whenever debugging is needed.Jul 2026
- explorerRead-only code exploration sub-agent. Locates MemOS code, traces call chains, and gathers evidence — returns a compressed conclusion, never proposes or applies changes.Jul 2026
