full-audit

Full Audit — Exhaustive Area Review (v1.2)

Dominant Variable

Accuracy of the coverage claim — the word "exhaustive" ships with a method label or it doesn't ship at all. The moment an unreviewed area gets reported as reviewed, this skill has failed its own purpose.

Trigger

• /full-audit [area] · "audit everything" · "exhaustive audit" · "full audit" · "double-check everything"
• Default mode on any of the above: AUDIT_ONLY. These are analysis requests, not execution requests — see Execution Modes below. Advancing to PROPOSE or APPLY_APPROVED in the same invocation requires the user to say so explicitly (e.g. "audit everything and apply the fixes", "전수감사하고 바로 고쳐줘").

Discard If

• Single file / single question needs checking → use a regular code review instead
• The goal is a harness-maturity score against a fixed checklist → use a fixed-checklist scoring tool instead
• The goal is a single docs-vs-code drift check → too narrow a scope for this
• An identical-scope full audit finished within the last 7 days and nothing has changed → just diff against the existing coverage map instead

---

Key Assumptions

1. Target area is agreed in Phase 0 — if not, don't start without an area table.
2. Deterministic sweeping (scripts/grep) is available for the target — if not, skip Phase 1 and never claim "exhaustive" from Phase 2 (LLM review) alone.
3. A prior coverage map can shrink the scope via diff — if not, do a full re-scan.

Execution Modes: AUDIT_ONLY / PROPOSE / APPLY_APPROVED

This skill keeps analysis and execution in separate, explicitly-named modes. A trigger phrase like "audit everything" or "분석해줘" selects a mode — it does not, by itself, authorize any file write.

Mode	When active	What runs	Writable scope
AUDIT_ONLY (default)	Any bare audit/analysis trigger, with no separate execution request	Phase 0-3 (scope, deterministic sweep, content review, judgment) + Phase 5 (coverage map)	None — read-only. No Edit/Write to any target file, protected or not.
PROPOSE	User asks for fix proposals (after an AUDIT_ONLY pass, or up front)	AUDIT_ONLY output + a listed fix/addition bucket (Phase 4 framing, nothing applied)	None — still read-only, output is a proposal list
APPLY_APPROVED	User explicitly approves specific items or the fix bucket as a whole ("이 항목들 적용해", "fix bucket 적용해")	Applies only the items the user named as approved	Limited to the approved items. A deny-listed path (rules/CLAUDE.md/settings — see Safety Layers) is reachable only here, only for that one named item, with its deny lifted for that single edit and restored immediately after — never as a routine step of "the edit procedure."