audit-agent-onboarding

audit-agent-onboarding is a skill for Claude Code from gustavo-meilus/aiboarding. It costs 76 tokens per session (864 once invoked), scanned A, original, MIT.

A read-only checker for agent onboarding files such as AGENTS.md, CLAUDE.md, and rule files. It looks for bloated, duplicated, contradictory, vague, outdated, or unsafe instructions.

In plain words
What is it for?
Use it to audit a repository's agent instructions or view recorded compression statistics with --stats. It reports findings but does not edit files.
Why use it?
It helps find instruction-file problems that can confuse coding agents, waste context, or expose secrets before the files are updated.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Codex.

Part of the aiboarding plugin — 17 skills, 11 commands, 4 hooks shipped together

Good fit Use it to audit a repository's agent instructions or view recorded compression statistics with --stats. It reports findings but does not edit files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gustavo-meilus/aiboarding/audit-agent-onboarding
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 gustavo-meilus/aiboarding --skill audit-agent-onboarding
Clone the repo
git clone --depth 1 https://github.com/gustavo-meilus/aiboarding

Made for: Claude Code.

Or install aiboarding, the plugin that ships this one along with the rest of its 17 skills, 11 commands, 4 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-agent-onboarding

README.md
[![agentmods](https://agentmods.dev/badge/skills/gustavo-meilus/aiboarding/audit-agent-onboarding/github.svg)](https://agentmods.dev/skills/gustavo-meilus/aiboarding/audit-agent-onboarding)
Your own site
<a href="https://agentmods.dev/skills/gustavo-meilus/aiboarding/audit-agent-onboarding"><img src="https://agentmods.dev/badge/skills/gustavo-meilus/aiboarding/audit-agent-onboarding/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for audit-agent-onboarding

Your own site · 80×15
<a href="https://agentmods.dev/skills/gustavo-meilus/aiboarding/audit-agent-onboarding"><img src="https://agentmods.dev/badge/skills/gustavo-meilus/aiboarding/audit-agent-onboarding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 864 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 $0.00076 $0.00864
Opus 5 $0.00038 $0.00432
Sonnet 5 $0.00015 $0.00173
Haiku 4.5 $0.00008 $0.00086

Measured 9d ago against content hash a9f77d14c198, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

audit-agent-onboarding 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 9d 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.

skills/audit-agent-onboarding/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auditing agent onboarding files

Static + cross-reference linter for instruction-file smells. Read-only: this skill never writes files. It produces a findings report; applying fixes is update-agent-onboarding's job (content) or the user's (structure).

Announce at start: "Using audit-agent-onboarding to lint the onboarding files."

Usage: audit-agent-onboarding [--stats]

--stats: compression receipts

Read .aiboarding/state.json:receipts and render a table: file, level, bytes and lines before/after, percent saved, measured-at. Label token figures approximate when the receipt does (they are byte/4 estimates unless a real tokenizer produced them). Since instruction files load every session, per-session savings compound - present "per-session saved × sessions" only as a clearly labeled estimate. For each receipt, render optional high_consequence_regions evidence as location, category, outcome (preserved or rewritten), and explicit opt-in status, without instruction text. Render an empty array as none; when field is absent, render not recorded. Keep existing level, byte, line, date, and token output unchanged. Then stop.

Evidence-aware audit

Run .aiboarding/tools/audit-onboarding-evidence <repo-root> first (fallback: the plugin's templates/tools/audit-onboarding-evidence). Capture its lines and exit status. Exit 0 means no computed FAIL; 1 means computed validation FAIL; 2 is an operational error: stop and report tooling failure, never render it as an audit finding. Do not write onboarding files in either case.

Each finding has independent severity (FAIL, WARN, INFO) and provenance (computed, inferred). Preserve validator provenance and render one report ordered FAIL, WARN, INFO. Never upgrade model judgment to computed.

Category Evidence
Local size budget; Codex project-chain budget; wrapper integrity Computed
Stale commands Mixed: validator only for explicit paths, package scripts, Make/Just targets; infer unresolved context-dependent cases
Duplication; contradictions; vague commands; missing sections; skill leakage; lint leakage; rules extraction candidates; unsafe content Inferred

Read the full file on GitHub · 68 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. 9d ago First seen · 68 lines · 76 tokens per session scan A a9f77d14c198

Subscribe to this mod's changes

audit-agent-onboarding is a skill published in the GitHub repository gustavo-meilus/aiboarding (2 stars, last pushed 12d ago), licensed MIT. It adds 76 tokens to every session and 864 once invoked, about $0.0004 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.