claude_onboarding_agent: Agent for Claude Code

.claude/agents/repo-scanner.md

repo-scanner is an agent for Claude Code from a2ngerer/claude_onboarding_agent. It costs 35 tokens per session (1,397 once invoked), scanned A, original, MIT.

A read-only project scanner that examines the current folder and reports its programming language, framework, project size, and likely purpose.

In plain words
What is it for?
Identifying project structure and technology, estimating the size of a codebase, and preparing context for other setup or coding tasks.
Why use it?
It gives the coding agent a quick picture of the project without changing files or requiring you to explain the repository manually.

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/repo-scanner.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 repo-scanner

README.md
[![agentmods](https://agentmods.dev/badge/agents/a2ngerer/claude_onboarding_agent/repo-scanner/github.svg)](https://agentmods.dev/agents/a2ngerer/claude_onboarding_agent/repo-scanner)
Your own site
<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.

agentmods 80×15 button for repo-scanner

Your own site · 80×15
<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>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,397 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 $0.00035 $0.01397
Opus 5 $0.00017 $0.00698
Sonnet 5 $0.00007 $0.00279
Haiku 4.5 $0.00003 $0.00140

Measured 10d ago against content hash 0f4668821a34, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

.claude/agents/repo-scanner.md · 81 lines

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. Use unknown when no signal is strong enough to commit to a single use case.
  • signals — array of strings identifying the detected evidence (file names, directory names, or manifest:dependency pairs). At least the strongest three signals; at most ten.
  • graphify_candidatetrue if the repo has either > 1000 source files across multiple languages OR > 100 PDFs/Markdown notes under docs/ / raw/ / notes/. Otherwise false.
  • existing_claude_mdtrue if ./CLAUDE.md exists.
  • existing_agents_mdtrue if ./AGENTS.md exists.
  • repo_size_bucket — one of: tiny (< 20 non-hidden files), small (20–200), medium (200–2000), large (> 2000). Count via find . -not -path './.*' -type f | wc -l or equivalent.

Read the full file on GitHub · 81 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 · 81 lines · 35 tokens per session scan A 0f4668821a34

Subscribe to this mod's changes

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.