audit-setup

audit-setup is a skill for Claude Code from a2ngerer/claude_onboarding_agent. It costs 74 tokens per session (3,639 once invoked), scanned B, original, MIT.

A read-only audit of a Claude setup, covering package managers, instruction files, permissions, Git practices, and MCP servers. It reports findings by priority without changing files.

In plain words
What is it for?
Use it when you want the detailed findings from the setup check, without the broader verdict or automatic delegation provided by `/checkup`.
Why use it?
It helps reveal setup problems and security or maintenance risks before they cause confusing agent behaviour.

Skill for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Part of the claude-onboarding-agent plugin — 16 skills, 4 agents, 1 hook shipped together

Good fit Use it when you want the detailed findings from the setup check, without the broader verdict or automatic delegation provided by /checkup.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/a2ngerer/claude_onboarding_agent/audit-setup
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 a2ngerer/claude_onboarding_agent --skill audit-setup
Clone the repo
git clone --depth 1 https://github.com/a2ngerer/claude_onboarding_agent

Made for: Claude Code.

Or install claude-onboarding-agent, the plugin that ships this one along with the rest of its 16 skills, 4 agents, 1 hook.

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-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/a2ngerer/claude_onboarding_agent/audit-setup.svg)](https://agentmods.dev/skills/a2ngerer/claude_onboarding_agent/audit-setup)
Your own site
<a href="https://agentmods.dev/skills/a2ngerer/claude_onboarding_agent/audit-setup"><img src="https://agentmods.dev/badge/skills/a2ngerer/claude_onboarding_agent/audit-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,639 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00074 $0.03639
Opus 5 $0.00037 $0.01819
Sonnet 5 $0.00015 $0.00728
Haiku 4.5 $0.00007 $0.00364

Measured 8d ago against content hash d1d807387dc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

audit-setup scanned grade B with 2 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 8d 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.

Downloads and executes remote codemediumSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

How to apply (Go): `curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(go env GOPATH)/bin && golangci-lint run`

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

How to apply (Go): `curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(go env GOPATH)/bin && golangci-lint run`
skills/audit-setup/SKILL.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Setup — Claude Setup Audit

Power-user / internal tool. Normal users run /checkup, which invokes this skill as its first stage. Running /audit-setup directly still works and produces the same report — use it when you want the raw findings without the /checkup verdict and delegation.

Audit the current Claude setup and print a prioritized, actionable list of improvement suggestions.

Language: Detect language from the user's first message and respond in it throughout. All file content and finding text stays in English.

Entry: Run all four passes silently first. Collect every finding in context. Print once at the end, sorted HIGH → MEDIUM → LOW. Do not print pass-by-pass intermediate output.


Pass 1 — Claude Config

Read these files if they exist: CLAUDE.md, AGENTS.md, .claude/settings.json. Skip any check whose required file is absent.

Check 1.1 — Secrets in CLAUDE.md [HIGH] Condition: CLAUDE.md contains patterns that look like secrets — API keys (strings matching sk-, ghp_, AIza, xox), passwords (lines containing password = or password:), or bearer tokens. Finding title: "Potential secret or personal data in CLAUDE.md" Why: CLAUDE.md is often committed to version control. Secrets in it can be leaked publicly. How to apply: Move secrets to .env or a secrets manager. Remove personal data from CLAUDE.md.

Check 1.2 — Overly broad permissions [HIGH] Condition: .claude/settings.json exists and its permissions.allow array contains the string "*" or "Bash(*)". Finding title: "Overly broad tool permissions in settings.json" Why: A wildcard allow entry lets any tool run without confirmation — including destructive ones. How to apply: Replace "*" with an explicit allowedTools list. Run /fewer-permission-prompts to generate one.

Check 1.3 — CLAUDE.md length [MEDIUM] Condition: CLAUDE.md exists and has more than 40 lines. Finding title: "CLAUDE.md is [N] lines — aim for under 40" Why: Long CLAUDE.md files dilute signal. Claude reads the whole file every turn; every extra line competes with the instructions that matter. How to apply: Trim to pointers and principles. Move detail into referenced files or inline comments in the codebase.

Read the full file on GitHub · 233 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. 8d ago First seen · 233 lines · 74 tokens per session scan B d1d807387dc4

Subscribe to this mod's changes

audit-setup is a skill published in the GitHub repository a2ngerer/claude_onboarding_agent (5 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 3,639 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (downloads and executes remote code, makes network calls). 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens