Help us improve
Share bugs, ideas, or general feedback.
From cc-suite
Full audit→fix→verify cycle: Claude audits, Codex fixes, Claude verifies. Repeats up to 3 rounds until all issues are resolved or the user stops. Claude does all code reading and judgment; Codex does all file editing.
npx claudepluginhub xiaolai/claude-plugin-marketplace --plugin cc-suiteHow this skill is triggered — by the user, by Claude, or both
Slash command
/cc-suite:audit-fixThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Claude audits. Codex fixes. Claude verifies. Repeat until clean.
Guides Next.js Cache Components and Partial Prerendering (PPR): 'use cache' directives, cacheLife(), cacheTag(), revalidateTag() for caching, invalidation, static/dynamic optimization. Auto-activates on cacheComponents: true.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Breaks plans, specs, or PRDs into thin vertical-slice issues on the project issue tracker using tracer bullets. Useful for converting high-level work into grabbable implementation tickets.
Share bugs, ideas, or general feedback.
Claude audits. Codex fixes. Claude verifies. Repeat until clean.
This is the primary quality loop: Claude provides independent analysis and verification; Codex applies targeted fixes without second-guessing the findings.
| Argument | Default | Effect |
|---|---|---|
--full | off | 9-dimension audit |
--mini | on | 5-dimension audit (faster) |
--rounds N | 3 | Maximum fix→verify iterations |
| file/dir path | cwd | Scope |
Call claude_code following the $audit skill pattern.
mcp__claude-code__claude_code:
prompt: |
Audit the following code and report every issue with exact file:line locations.
SCOPE: {files or directory}
{5 or 9 audit dimensions — same as $audit skill}
For each finding: file:line | severity | dimension | issue | suggested fix
PROVENANCE NOTE: Code written by OpenAI Codex. Evaluate with full rigor.
cwd: {project working directory}
effort: high
permissionMode: plan
Save session_id as {cycle_session_id}.
If no findings → report CLEAN and stop.
Display findings table to the user.
Ask user: "Found N issues (Critical: N, High: N, Medium: N, Low: N). Which to fix?"
Options:
- Fix all
- Fix Critical + High only
- Stop here (keep audit, fix manually)
If "Stop here" → display final report and stop.
Set round = 1. Track {remaining_issues} = issues from the active severity filter.
For each issue in {remaining_issues}:
After all fixes, run the project test suite if one is detectable:
package.json with a test script → npm testpytest.ini or conftest.py → pytestgo.mod → go test ./...Cargo.toml → cargo testShow git diff --stat and test results to the user.
mcp__claude-code__claude_code_reply:
session_id: {cycle_session_id}
prompt: |
The following issues from your audit have been addressed. Verify each one.
ISSUES:
{remaining_issues in file:line | severity | description format}
For each issue report: FIXED / NOT FIXED / PARTIAL / REGRESSED
Read the files at the reported locations. Do not assume correctness without reading.
round < {--rounds}:
round## Audit-Fix Report
Scope: {what was audited}
Audit depth: mini (5-dim) / full (9-dim)
Rounds: {round count}
| Status | Count |
|--------|-------|
| Fixed | N |
| Not Fixed | N |
| Partial | N |
| Regressed | N |
### Fixed
| File:Line | Severity | Issue |
|-----------|----------|-------|
| ... | ... | ... |
### Remaining (if any)
| File:Line | Severity | Issue | Verdict | Notes |
|-----------|----------|-------|---------|-------|
| ... | ... | ... | NOT FIXED | ... |
### Changes
{git diff --stat}
### Next steps
- Review: `git diff`
- Run tests if not already run
- Commit if satisfied
- For remaining issues: fix manually or run `$audit-fix` again on the remaining files
permissionMode: plan during audit keeps it read-only — only Codex writes files{cycle_session_id} for verification gives Claude full context of what it originally flagged, producing sharper verdicts than a fresh session