auto-audit

auto-audit is a skill for Claude Code, Codex from mr-tbot/Auto-Everything. It costs 98 tokens per session (2,988 once invoked), scanned A, original, MIT.

An iterative project audit process that checks every platform a project targets, fixes issues, builds, verifies, and repeats the review. A platform can be an operating system, browser, server runtime, device, or distribution channel.

In plain words
What is it for?
Use it before calling a feature complete, when auditing a release, or when checking whether a capability works across all declared platforms.
Why use it?
It helps prevent declaring a project finished after checking only one environment or one pass. It keeps testing focused on the environments the project actually supports.

Skill for Claude CodeCodex

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 skills/mr-tbot/auto-everything/auto-audit
Any agent
npx skills add mr-tbot/Auto-Everything --skill auto-audit
Clone the repo
git clone --depth 1 https://github.com/mr-tbot/Auto-Everything

Made for: Claude Code, Codex.

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 auto-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/mr-tbot/auto-everything/auto-audit.svg)](https://agentmods.dev/skills/mr-tbot/auto-everything/auto-audit)
Your own site
<a href="https://agentmods.dev/skills/mr-tbot/auto-everything/auto-audit"><img src="https://agentmods.dev/badge/skills/mr-tbot/auto-everything/auto-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,988 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 $0.00098 $0.02988
Opus 5 $0.00049 $0.01494
Sonnet 5 $0.00020 $0.00598
Haiku 4.5 $0.00010 $0.00299

Measured yesterday against content hash d9048ce0fa9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto-audit 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 yesterday.

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.

skills/auto-audit/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/auto-audit

Iterative audit → fix → build → verify → adversarially review → audit again, until a full pass turns up nothing. "Doesn't exist yet" is a research task, not a stopping point.

Step 0 — Enumerate The Targets

Before the first pass, write down every platform this project targets, and keep the list visible. It is the checklist every later stage runs against. Sources: build config, CI matrix, packaging scripts, README install section, the user.

Targets are whatever the project actually ships to — mobile OSes, desktop OSes, browsers (and the ones you don't develop in), server runtimes and their versions, CPU architectures, containers, embedded boards, CLI shells, plugin hosts, store/distribution channels.

Include the platform you are running on right now. It is a target too, not the neutral place you build from. The host is where verification is cheapest and therefore the one most often declared done on inspection alone — verify it like any other.

If the project targets exactly one platform, say so explicitly and move on. If you can't determine the list, ask — guessing the target set undermines every pass that follows.

The Loop

Run every stage against every target from Step 0. Never skip to the end because the last pass looked clean.

  1. Audit — walk every feature the project claims. For each, name the exact runtime path that makes it work, file:line, on each target. A feature with no traceable runtime path is not implemented. Platform-conditional code (#ifdef, Platform.OS, os.name, feature detection, per-target build flavors) gets audited per branch — one branch working says nothing about its sibling.
  2. Fix — implement what the audit found. Be thorough and precise; no stubs, no TODO-and-move-on.
  3. Build — every target, every time. A green build on one target proves nothing about the rest.
  4. Verify in the real environment — run the actual thing on each target and read the actual logs. See below.
  5. Adversarially review, by team — hunt for what the fix pass missed, assuming it missed something. One reviewer wearing one hat finds one class of defect; the team colours below are how you get the other classes.
  6. Go to 1. Stop only when a complete pass finds nothing new on any target.

Read the full file on GitHub · 201 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. yesterday Changed · +39 lines · +19 tokens per session d9048ce0fa9d
  2. 5d ago First seen · 162 lines · 79 tokens per session scan A c5ff1dad720c

Subscribe to this mod's changes

auto-audit is a skill published in the GitHub repository mr-tbot/Auto-Everything (7 stars, last pushed 3d ago), licensed MIT. It adds 98 tokens to every session and 2,988 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens