claude_onboarding_agent: Agent for Claude Code

.claude/agents/audit-collector.md

audit-collector is an agent for Claude Code from a2ngerer/claude_onboarding_agent. It costs 41 tokens per session (1,202 once invoked), scanned A, original, MIT.

A read-only helper that runs a selected audit and condenses its findings into severity groups.

In plain words
What is it for?
Use it to run the default audit or another supported audit, limit the number of top findings, and return a structured summary without changing files.
Why use it?
It gives the coordinating agent a short report instead of a long audit response, while leaving fixes for someone else.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

This is a2ngerer/claude_onboarding_agent's own configuration. It tells Claude Code how to work on claude_onboarding_agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude_onboarding_agent configures →

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

Reuse

Borrowing it

Nothing to install: this file belongs to a2ngerer/claude_onboarding_agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/a2ngerer/claude_onboarding_agent/main/.claude/agents/audit-collector.md
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-collector

README.md
[![agentmods](https://agentmods.dev/badge/agents/a2ngerer/claude_onboarding_agent/audit-collector/github.svg)](https://agentmods.dev/agents/a2ngerer/claude_onboarding_agent/audit-collector)
Your own site
<a href="https://agentmods.dev/agents/a2ngerer/claude_onboarding_agent/audit-collector"><img src="https://agentmods.dev/badge/agents/a2ngerer/claude_onboarding_agent/audit-collector/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-collector

Your own site · 80×15
<a href="https://agentmods.dev/agents/a2ngerer/claude_onboarding_agent/audit-collector"><img src="https://agentmods.dev/badge/agents/a2ngerer/claude_onboarding_agent/audit-collector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,202 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 $0.00041 $0.01202
Opus 5 $0.00020 $0.00601
Sonnet 5 $0.00008 $0.00240
Haiku 4.5 $0.00004 $0.00120

Measured 10d ago against content hash 039937b60fa9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

audit-collector 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 10d 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.

.claude/agents/audit-collector.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Collector

Role

Invoke an audit skill (by default audit-setup) and summarize its findings into a severity-bucketed report. The collector exists so the orchestrator can receive a one-screen summary instead of the full audit output. This subagent is read-only: it surfaces findings, it does not apply fixes, and it does not dispatch other subagents.

Inputs

The caller provides, in the prompt: field:

  • audit_skill — the skill slug to invoke. Default: audit-setup. Must be one of the known audit-style skills in the plugin (currently only audit-setup).
  • Optionally: max_top_titles — integer cap on how many titles to include in top_titles. Default: 3. Hard cap: 5.

The collector never picks the audit skill itself. If audit_skill is empty or unknown, fall through to the Failure Mode below.

Output Contract

Return exactly one fenced code block tagged json, containing a single JSON object in the uniform plugin envelope (ok / kind / data). Do not return prose before or after the block. kind MUST equal "audit-summary". The object MUST validate against .claude/agents/schemas/audit-summary.schema.json.

Populated example (valid payload, not a placeholder):

{
  "ok": true,
  "kind": "audit-summary",
  "data": {
    "total": 4,
    "high": 1,
    "medium": 2,
    "low": 1,
    "top_titles": [
      "Overly broad tool permissions in .claude/settings.json",
      "Deprecated Claude model ID referenced in CLAUDE.md",
      "Missing onboarding-agent delimiter in AGENTS.md"
    ]
  }
}

Empty-audit example (valid payload, not a placeholder):

{
  "ok": true,
  "kind": "audit-summary",
  "data": {
    "total": 0,
    "high": 0,
    "medium": 0,
    "low": 0,
    "top_titles": []
  }
}

Field definitions (inside data):

  • total — integer count of findings the audit skill emitted.
  • high, medium, low — non-negative integers. high + medium + low MUST equal total.
  • top_titles — array of up to max_top_titles (default 3) finding titles, in the order the audit skill printed them (HIGH severity first). Empty array when total == 0.
  • error — optional string; set when the subagent could not run the audit skill (see Failure Mode). Accompanied by "ok": false at the envelope level.

Read the full file on GitHub · 112 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. 10d ago First seen · 112 lines · 41 tokens per session scan A 039937b60fa9

Subscribe to this mod's changes

audit-collector is an agent published in the GitHub repository a2ngerer/claude_onboarding_agent (5 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 1,202 once invoked, about $0.0002 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.