From Codebase Auditor
The severity taxonomy for audit findings — how to assign HIGH / MEDIUM / LOW / ADVISORY so the release gate enforces the right things and never false-blocks. Use when an auditor sub-agent or /auditor:run records a finding.
How this skill is triggered — by the user, by Claude, or both
Slash command
/auditor:classify-findingsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Severity decides what GATES. The pipeline release gate enforces **0 HIGH**; MEDIUM/LOW are
Severity decides what GATES. The pipeline release gate enforces 0 HIGH; MEDIUM/LOW are recorded but do not block; ADVISORY is informational and excluded from the tally. Assign deliberately — an inflated HIGH blocks a clean release; a buried HIGH ships a broken gate.
Use for: security, fail-open, data-loss, path traversal, and anything that makes a safety gate not run / not block while appearing healthy.
set -e, or trusts a stub interpreter). [D1]../backslash escape. [D2]source that doesn't resolve → plugin won't load. [D7]Use for: portability, false-block (a gate that wrongly blocks), and contract drift.
NotebookEdit) → a coverage gap. [D3]cat with no [ -t 0 ]). [D4]timeout → a hang can stall the turn. [D6b]Use for: line endings, exec bit, lint.
.sh that ships CRLF, or a non-hook .sh not tracked 100755. [D9]Use for the "fuzzy" findings whose static signal is too weak to gate on without false-blocking, and for purely stylistic notes:
tools: and disallowedTools: (redundant, F12)..claude/explorer/index.json paths that no longer resolve (F13).npx claudepluginhub hafizmirhamza276-lab/backend-agentic-marketplace --plugin auditorGuides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.
Dispatches multiple subagents concurrently for independent tasks without shared state. Use when facing 2+ unrelated failures or subsystems that can be investigated in parallel.