audit-fix

audit-fix is a skill for Claude Code from SienkLogic/plan-build-run. It costs 22 tokens per session (2,265 once invoked), scanned A, original, MIT.

An automated workflow that reviews past sessions, selects findings that can be fixed automatically, applies those fixes through small tasks, runs tests, and commits the results.

In plain words
What is it for?
It is for finding workflow problems, applying eligible corrections, verifying them with tests, and recording each change in Git.
Why use it?
It turns an audit report into a controlled fix-and-test process, stopping when a test fails.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

Part of the pbr plugin — 44 skills, 71 commands, 18 agents, 3 hooks shipped together

Good fit It is for finding workflow problems, applying eligible corrections, verifying them with tests, and recording each change in Git.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sienklogic/plan-build-run/audit-fix
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.

Any agent
npx skills add SienkLogic/plan-build-run --skill audit-fix
Clone the repo
git clone --depth 1 https://github.com/SienkLogic/plan-build-run

Made for: Claude Code.

Or install pbr, the plugin that ships this one along with the rest of its 44 skills, 71 commands, 18 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/skills/sienklogic/plan-build-run/audit-fix.svg)](https://agentmods.dev/skills/sienklogic/plan-build-run/audit-fix)
Your own site
<a href="https://agentmods.dev/skills/sienklogic/plan-build-run/audit-fix"><img src="https://agentmods.dev/badge/skills/sienklogic/plan-build-run/audit-fix.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,265 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00022 $0.02265
Opus 5 $0.00011 $0.01132
Sonnet 5 $0.00004 $0.00453
Haiku 4.5 $0.00002 $0.00227

Measured 4d ago against content hash f336bceaf8f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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.

plugins/pbr/skills/audit-fix/SKILL.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

STOP -- DO NOT READ THIS FILE. You are already reading it. This prompt was injected into your context by Claude Code's plugin system. Using the Read tool on this SKILL.md file wastes tokens. Begin executing Step 0 immediately.

/pbr:audit-fix -- Autonomous Audit-to-Fix Pipeline

You are running the audit-fix skill. Your job is to run a session audit, parse findings, classify which are auto-fixable, and spawn executor agents to fix them one-by-one with atomic commits. The pipeline stops on the first test failure.

This skill chains audit -> prioritize -> fix -> test -> commit in a single command.


Step 0 -- Immediate Output

Before ANY tool calls, display this banner:

+--------------------------------------------------------------+
|  PLAN-BUILD-RUN > AUDIT-FIX                                  |
+--------------------------------------------------------------+

Then proceed to Step 1.

Context Budget

Reference: skills/shared/context-budget.md for the universal orchestrator rules. Reference: skills/shared/agent-type-resolution.md for agent type fallback when spawning Task() subagents.

Additionally for this skill:

  • Delegate ALL code changes to executor subagents -- do NOT make fixes yourself
  • Main context handles: argument parsing, audit orchestration, finding classification, executor dispatch, reporting
  • Read only the audit report findings section, not full session details
  • Target: main context stays under 25% utilization

Step 1 -- Parse Arguments

Parse $ARGUMENTS for:

Argument Default Description
--max N 5 Maximum number of findings to fix
--severity LEVEL medium Minimum severity threshold: high = Critical+High only, medium = +Medium, all = +Low
--dry-run false List fixable findings without executing fixes
--from DATE Start of today Passed through to audit agent
--to DATE Now Passed through to audit agent
--today true (default) Shorthand for today's audit window

Read the full file on GitHub · 327 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 · 327 lines · 22 tokens per session scan A f336bceaf8f1

Subscribe to this mod's changes

audit-fix is a skill published in the GitHub repository SienkLogic/plan-build-run (17 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 2,265 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 2026-09-03.