audit-fix

audit-fix is a command for coding agents from xiaolai/cc-suite. It costs 22 tokens per session (3,639 once invoked), scanned A, original, ISC.

An automated review-and-repair loop that finds issues, applies fixes, checks the results, and repeats when needed.

In plain words
What is it for?
Use it to fix selected findings by severity, choose Claude or Codex as the fixer, and continue until the issues are resolved or you stop.
Why use it?
It reduces the manual work of switching between auditing, fixing, and verifying each problem.

Command

Part of the cc-suite plugin — 13 skills, 39 commands, 4 agents, 3 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/xiaolai/cc-suite/audit-fix
Clone the repo
git clone --depth 1 https://github.com/xiaolai/cc-suite

Or install cc-suite, the plugin that ships this one along with the rest of its 13 skills, 39 commands, 4 agents, 3 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for audit-fix

README.md
[![agentmods](https://agentmods.dev/badge/commands/xiaolai/cc-suite/audit-fix.svg)](https://agentmods.dev/commands/xiaolai/cc-suite/audit-fix)
Your own site
<a href="https://agentmods.dev/commands/xiaolai/cc-suite/audit-fix"><img src="https://agentmods.dev/badge/commands/xiaolai/cc-suite/audit-fix.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,639 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.03639
Opus 5 $0.00011 $0.01819
Sonnet 5 $0.00004 $0.00728
Haiku 4.5 $0.00002 $0.00364

Measured 4d ago against content hash 7550f8834044, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-fix scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/audit-fix.md · 310 lines

How it starts

The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Input

$ARGUMENTS

What This Does

Runs a complete audit→fix→verify cycle:

  1. Audit — find issues (full 9-dimension or mini 5-dimension)
  2. Fix — Claude fixes by default (or Codex with --fixer=codex)
  3. Verify — check that each fix actually resolved the issue
  4. Repeat — if issues remain, loop back to fix

Continues until all issues are resolved or the user decides to stop.

Arguments

By default this command runs non-interactively: fixes all findings using Claude, and stops at the end of the first round if any issues remain. Override the defaults with flags, or pass --ask to restore the interactive prompts.

  • --severity=all|high — which findings to fix (default all). high means "High severity and above": Critical+High on a full audit, High-only on a mini audit.
  • --fixer=claude|codex — who applies the fix (default claude).
  • --ask — show interactive AskUserQuestion prompts for fix scope, fixer choice, and the partial-iteration continue/switch decision.

The danger-full-access sandbox warning below is always shown regardless of --ask.

Model & Settings Selection

Follow the instructions in commands/shared/model-selection.md to discover available models and present choices.

  • Recommended model: first available from preflight
  • Recommended reasoning effort: high
  • Recommended sandbox level: workspace-write
  • Include sandbox question: Yes (fixes require write access)

Warning: If the user selects danger-full-access sandbox, display a confirmation before proceeding: "You chose danger-full-access with no approval prompts — Codex will have unrestricted access. Continue?" Use AskUserQuestion with "Continue" and "Switch to workspace-write" options.

Workflow

Step 1: Determine audit type and scope

Follow the audit type selection logic in commands/audit.md Step 1 to parse --full/--mini flags from $ARGUMENTS, check {config_default_audit_type}, and ask the user if neither is set.

Read the full file on GitHub · 310 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 310 lines · 22 tokens per session scan A 7550f8834044

Subscribe to this mod's changes

audit-fix is a command published in the GitHub repository xiaolai/cc-suite (44 stars, last pushed 2d ago), licensed ISC. It adds 22 tokens to every session and 3,639 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.