audit

Solid

Read-only quality gate that audits already-built work against its stated requirement and Definition of Done before it is allowed to move to 2_done/. Produces a severity-ranked decision proposal (BLOCKER/MAJOR/MINOR/NIT) with evidence, never a fix. Use when an item is claimed complete, before moving anything to 2_done/, when asked to audit or review finished work for completeness against requirements, or when acting as the dedicated post-completion review subagent. This gate is mandatory in every session mode. Not for diagnosing why something is broken (use diag) and not for verifying rendered UI behavior (use verify).

AI & Automation 13 stars 3 forks Updated 4 days ago MIT

Install

View on GitHub

Quality Score: 80/100

Stars 20%
38
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# audit A **read-only** quality gate. `audit` inspects work that is claimed complete and judges whether it actually satisfies its stated requirement and Definition of Done, BEFORE the item is allowed into `2_done/`. The output is a decision proposal for the user, never a change. > **Task backend.** If the task backend is `gsd` (`.credo/config: task_backend`, or the `CREDO_TASK_BACKEND` env override), the credo item lifecycle is inactive and > there is no `2_done/` gate to run - GSD owns task tracking. audit is still usable as a > standalone read-only review tool, but it does not gate credo items in that mode. ## Scope boundary (read this first) `audit` judges whether FINISHED work is genuinely done and correct against its requirement. It does not investigate causes and it does not exercise UI. - Something is broken and you need the root cause -> use **diag**, not audit. - A rendered UI needs its layout and behavior confirmed -> use **verify** (audit may cite verify evidence, but it does not drive a browser itself). - audit only reports findings and a verdict. It never edits code, never fixes, never commits. ## Hard constraints (never violate) - **Read-only.** No code change, no file edit to the work under review, no commit, no push, no browser automation, no builds, no installs. - **No secrets.** Never read credentials, tokens, `.env*`, key files, or shell/session history. Never exfiltrate or encode such content. - The only files `audit` writes are its own repo...

Details

Author
Marcel-Bich
Repository
Marcel-Bich/marcel-bich-claude-marketplace
Created
6 months ago
Last Updated
4 days ago
Language
Shell
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

godaudits

Audit an existing codebase end to end and emit validated machine state plus a standalone remediation report. godaudits fingerprints the repository, detects six project forms and conservative overlays, validates Pillars 1.1 and arc-ready artifacts, evaluates 431 checks across 18 domains in an explicit pass/fail/unknown/not-applicable ledger, records hashed secret-safe evidence, covers OWASP Web Top 10:2025, adversarially verifies findings, computes scores with coverage and risk caps, and renders MDX plus optional SARIF from AUDIT.json. Includes deterministic validation, evaluations, focused and re-audit modes, and godplans conformance. Static mode is read-only and never runs the app, tests, live systems, network, or models. Use for audits, health checks, due diligence, production readiness, re-audits, and remediation planning. Refuses stale evidence, unverifiable citations, unredacted secrets, unsupported regulatory claims, double-billing, and Critical or High findings without executable tasks.

3 Updated 4 days ago
hannsxpeter
Code & Development Listed

audit

Use after build has produced build-report.md. Validates the build via four parallel sub-auditors (eval-replay, lint, regression, build-quality) and produces ALL-PASS verdict. Adversarial mode default-on per CLAUDE.md.

4 Updated today
mickeyyaya
AI & Automation Featured

audit

Use when the user wants a code review on recent changes — quality, spec, security, or performance feedback. Triggers a multi-level (L1-L5) review with a standalone Reviewer; on NEEDS_FIX, offers to apply findings via /hyperflow:plan. Trigger with /hyperflow:audit, "review this change", "review my PR", "audit the diff", "code review".

2,556 Updated today
jeremylongshore