repo-scout

repo-scout is a skill for Claude Code from big-emotion/agent-atelier. It costs 45 tokens per session (1,261 once invoked), scanned C, original, MIT.

A workflow for investigating a GitHub repository and explaining what it does, what can be reused, and how to use its useful parts. It reads key project files after cloning the repository.

In plain words
What is it for?
Use it when someone shares a GitHub repository and you want a breakdown of its purpose, reusable code or instructions, and concrete setup guidance.
Why use it?
It saves time when you need to understand an unfamiliar repository before adopting or adapting it. It also focuses the review on reusable components and practical instructions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Part of the prompt-utils plugin — 3 skills, 1 command shipped together

Good fit Use it when someone shares a GitHub repository and you want a breakdown of its purpose, reusable code or instructions, and concrete setup guidance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/big-emotion/agent-atelier/repo-scout
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 big-emotion/agent-atelier --skill repo-scout
Clone the repo
git clone --depth 1 https://github.com/big-emotion/agent-atelier

Made for: Claude Code.

Or install prompt-utils, the plugin that ships this one along with the rest of its 3 skills, 1 command.

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-scout

README.md
[![agentmods](https://agentmods.dev/badge/skills/big-emotion/agent-atelier/repo-scout/github.svg)](https://agentmods.dev/skills/big-emotion/agent-atelier/repo-scout)
Your own site
<a href="https://agentmods.dev/skills/big-emotion/agent-atelier/repo-scout"><img src="https://agentmods.dev/badge/skills/big-emotion/agent-atelier/repo-scout/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-scout

Your own site · 80×15
<a href="https://agentmods.dev/skills/big-emotion/agent-atelier/repo-scout"><img src="https://agentmods.dev/badge/skills/big-emotion/agent-atelier/repo-scout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,261 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00045 $0.01261
Opus 5 $0.00023 $0.00630
Sonnet 5 $0.00009 $0.00252
Haiku 4.5 $0.00005 $0.00126

Measured 11d ago against content hash bcdeef5be1df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

repo-scout scanned grade C with 2 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 11d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

Delete the cloned repo: `rm -rf /tmp/repo-scout-{repo}`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

If it's a collection of files: exact cp/curl commands.]
plugins/prompt-utils/skills/repo-scout/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repo Scout

Quickly understand a GitHub repo, extract what's valuable — both for .claude/ and for your own projects — and get concrete usage instructions.

When to Activate

  • User shares a GitHub repo URL and wants to understand it
  • User says "scout this repo", "what does this repo do", "analyze this repo"
  • User wants to know what's reusable in a repo
  • User asks "what can I steal from this repo"

Input

The skill takes one argument: a GitHub repo URL (e.g., https://github.com/owner/repo). The URL may include extra path segments or query params (e.g. ?tab=readme-ov-file) — strip them and extract owner/repo.

If no URL is provided, ask for one.

Workflow

Step 1: Clone and Explore

  1. Extract owner/repo from the URL
  2. Clone into /tmp/repo-scout-{repo} using gh repo clone {owner/repo} /tmp/repo-scout-{repo} -- --depth 1
  3. If the clone fails (auth, not found), inform the user and stop

Step 2: Read Key Files

Read these files in parallel (skip any that don't exist):

  • README.md (or readme.md, README)
  • CLAUDE.md
  • SKILL.md
  • package.json / pyproject.toml / Cargo.toml / go.mod (for metadata + dependencies)
  • LICENSE

Then do a structural deep scan:

  • ls the root directory
  • Glob for **/*.md to find other documentation
  • Glob for skill/agent definitions: **/SKILL.md, **/skills/**, **/agents/**, **/.claude/**
  • Glob for reusable code: **/components/**, **/utils/**, **/lib/**, **/services/**, **/hooks/**, **/helpers/**, **/middleware/**, **/prompts/**, **/templates/**
  • Read key source files that look reusable (utilities, services, core logic) — skim 5-10 files max to understand quality and patterns

Step 3: Analyze and Respond

Produce a structured response with exactly these sections:

## What it does
[2-3 sentence plain-language summary. No marketing fluff. What problem does it solve, for whom.]

## 3 things you need to know
1. **[Thing]** — [concise explanation. Focus on what matters for someone evaluating this repo]
2. **[Thing]** — [architecture, key pattern, or important limitation]
3. **[Thing]** — [maturity, quality, or gotcha worth knowing]

## Reusable parts — what to steal

### For `~/.claude/` (skills, agents, configs)
[List specific files/directories worth copying into .claude/, with exact cp commands.
Focus on: skills, agents, CLAUDE.md snippets, prompts, configurations.
If nothing is worth copying, say "Nothing `.claude/`-specific here." and move on.]

### For your projects (components, utils, patterns)
[List reusable code: components, utilities, services, patterns, middleware, configs.
For each item:]
- **`path/to/file.ts`** — [what it does] — **Why:** [why it's worth reusing over writing your own]

[If the repo has nothing worth extracting, say so honestly. Don't invent value.]

## Use it right now
[One concrete, copy-paste example of using this repo/tool/skill TODAY.
Include the actual command or code. No "you could" — show "do this".
If it's a library: install + minimal usage.
If it's a tool: run command.
If it's a collection of files: exact cp/curl commands.]

## Quick stats
- **Language:** [primary language]
- **License:** [license type — flag if restrictive]
- **Last commit:** [date, from git log --format="%ai" -1]
- **Stars:** [from gh repo view --json stargazerCount]
- **Health:** [Active / Maintained / Stale / Abandoned — based on commit frequency and issue activity]

Read the full file on GitHub · 116 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. 11d ago First seen · 116 lines · 45 tokens per session scan C bcdeef5be1df

Subscribe to this mod's changes

repo-scout is a skill published in the GitHub repository big-emotion/agent-atelier (2 stars, last pushed 4d ago), licensed MIT. It adds 45 tokens to every session and 1,261 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

setup-pipeline

Sets up a Power Platform Pipeline for automated Power Pages deployments. Power Platform Pipelines is Microsoft's native CI/CD tool built into the Power Platform — no external infrastructure required. Use when asked to: "set up ci/cd", "create pipeline", "setup pipeline", "set up power platform pipelines", "create…

microsoft/power-platform-skills · 118 tokens

configure-env-variables

Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…

microsoft/power-platform-skills · 119 tokens

add-azuredevops

Adds Azure DevOps connector to a Power Apps code app. Use when querying work items, creating bugs, managing pipelines, or making ADO API calls.

microsoft/power-platform-skills · 37 tokens

pr-watch

Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.

SethGammon/Citadel · 46 tokens

azure-devops

Manage Azure DevOps projects, work items, repos, PRs, pipelines, wikis, test plans, security alerts, variable groups, environments/approvals, branch policies, and attachments. Use when user asks to: manage sprints, create/update work items, list repos, create PRs, run pipelines, search code, manage wiki pages, check…

sanjay3290/ai-skills · 105 tokens

push-ci

Push to remote and monitor CI. Validates branch safety, executes git push WITH explicit user approval, then monitors CI run status via gh CLI. Use when: user says 'push', 'push and watch CI', 'ship it', 'push-ci'. Not for: committing (use /smart-commit), creating PRs (use /create-pr), merging (use /merge-prep).

sd0xdev/sd0x-harness · 82 tokens