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.
curl -O https://raw.githubusercontent.com/a2ngerer/claude_onboarding_agent/main/.claude/agents/audit-collector.mdgit clone --depth 1 https://github.com/a2ngerer/claude_onboarding_agentWrote 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.
[](https://agentmods.dev/agents/a2ngerer/claude_onboarding_agent/audit-collector)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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 onlyaudit-setup).- Optionally:
max_top_titles— integer cap on how many titles to include intop_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 + lowMUST equaltotal.top_titles— array of up tomax_top_titles(default 3) finding titles, in the order the audit skill printed them (HIGH severity first). Empty array whentotal == 0.error— optional string; set when the subagent could not run the audit skill (see Failure Mode). Accompanied by"ok": falseat the envelope level.
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.
- 10d ago First seen · 112 lines · 41 tokens per session scan A 039937b60fa9
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.