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/repo-scanner.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/repo-scanner)<a href="https://agentmods.dev/agents/a2ngerer/claude_onboarding_agent/repo-scanner"><img src="https://agentmods.dev/badge/agents/a2ngerer/claude_onboarding_agent/repo-scanner/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/repo-scanner"><img src="https://agentmods.dev/badge/agents/a2ngerer/claude_onboarding_agent/repo-scanner.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 | $0.00035 | $0.01397 |
| Opus 5 | $0.00017 | $0.00698 |
| Sonnet 5 | $0.00007 | $0.00279 |
| Haiku 4.5 | $0.00003 | $0.00140 |
Grade A, and why
repo-scanner 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Scanner
Role
Scan the user project rooted at the current working directory and return a single structured report summarizing what Claude should treat the project as. This subagent is read-only: it infers signals, it does not modify files, and it does not dispatch other subagents.
Inputs
The caller provides, in the prompt: field:
- Either an explicit instruction ("scan the current directory") or nothing. The subagent always scans the current working directory — there is no target path argument.
- Optionally: a hint about which signals are most relevant. Hints are advisory; the scanner always returns every field in the output contract.
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 "repo-scan". The object MUST validate against .claude/agents/schemas/repo-scan.schema.json.
Example of the exact reply shape (valid payload, not a placeholder):
{
"ok": true,
"kind": "repo-scan",
"data": {
"inferred_use_case": "web-development",
"signals": [
"package.json",
"next.config.ts",
"package.json:next",
"app/page.tsx"
],
"graphify_candidate": false,
"existing_claude_md": true,
"existing_agents_md": false,
"repo_size_bucket": "small"
}
}
Field definitions (inside data):
inferred_use_case— one of:coding,web-development,data-science,knowledge-base,office,research,academic-writing,content-voice,devops,design,graphify,unknown. Useunknownwhen no signal is strong enough to commit to a single use case.signals— array of strings identifying the detected evidence (file names, directory names, ormanifest:dependencypairs). At least the strongest three signals; at most ten.graphify_candidate—trueif the repo has either > 1000 source files across multiple languages OR > 100 PDFs/Markdown notes underdocs//raw//notes/. Otherwisefalse.existing_claude_md—trueif./CLAUDE.mdexists.existing_agents_md—trueif./AGENTS.mdexists.repo_size_bucket— one of:tiny(< 20 non-hidden files),small(20–200),medium(200–2000),large(> 2000). Count viafind . -not -path './.*' -type f | wc -lor equivalent.
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 · 81 lines · 35 tokens per session scan A 0f4668821a34
repo-scanner is an agent published in the GitHub repository a2ngerer/claude_onboarding_agent (5 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,397 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.