Menu
Use when you want to safely remove code — finds symbols that are statically unreferenced, never covered by tests, and never executed in production, by intersecting dead-code, coverage, and trace evidence.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Audit whether an AI agent edit to a file is safe — composes secret-surface, taint-flow, change-impact, and API-surface analysis into an agent-edit safety report. Use before letting an agent modify a sensitive or high-blast-radius file.
Execute structural decompositions based on an architectural analysis report. Use when breaking circular dependencies, splitting god classes, reducing coupling between modules, extracting interfaces at seam boundaries, or executing any large-scale structural change identified in an architectural analysis. Requires a prior architecture audit (the architecture-audit skill) that produced project-map.md and a run report.
Use when asked to audit architecture, produce a comprehensive architectural overview, get the full structural picture of a codebase, assess overall health and porting readiness, find module boundaries, circular dependencies, coupling hotspots, dead code, or code patterns. Depth 3 — full audit with hypothesis-driven investigation. Optionally enriches the structural audit with runtime and git evidence (coverage, churn, co-change coupling, ownership) when those overlays are available. Replaces the architectural-analysis and architecture-audit-plus skills.
Use when looking for extraction candidates, planning a module split, analyzing module boundaries, or before decomposing a large component. Also use when asked "where should I split this?" or "find natural module boundaries". Depth 2 — investigate. Produces extraction candidates with cut costs, layer violations, interface width assessment, orphan types, and a recommended decomposition sequence.
Use before modifying a file or symbol, or when asked "what breaks if I change X?". Depth 0 — fast, no follow-up queries, returns immediately. Two modes: inline (no artifacts, default for agent-initiated use) and artifact (writes to docs/act/, triggered for human-initiated requests or Critical risk verdicts).
Traverse large repositories efficiently using act's query tools. Use when exploring unfamiliar code, mapping dependencies, understanding API surfaces, analyzing side effects before modifying functions, or following call chains across files. Avoids reading entire files by querying only the structure needed.
| name | dead-in-production |
| description | Use when you want to safely remove code — finds symbols that are statically unreferenced, never covered by tests, and never executed in production, by intersecting dead-code, coverage, and trace evidence. |
Find code that is safe to delete with high confidence by requiring three independent signals to agree: it is statically unreachable, untested, and never runs in production.
A git repo, an lcov coverage report, and an OTLP/JSON trace export from production. All overlays are MCP tools (Architecture tier).
analyze_dead_code to find symbols unreferenced from any entry point.coverage_overlay with the lcov report; a symbol with covered: false (or zero hits) is untested.trace_overlay with the production trace; a symbol absent from the hits (zero span_count) never ran in prod.unmapped counts so the user can judge.A ranked deletion list: high-confidence (3/3) first, then 2/3 with the missing signal named, then 1/3. For each, cite the symbol id and which signals fired. Include the trace/coverage unmapped counts and the trace time window as caveats.
Respect modeled_kinds and unmapped: a symbol that mapped to no coverage/trace fact is "no evidence," not "dead." Never recommend deleting on a single signal. Coverage/trace are facts about the captured window only.