repo-explorer

repo-explorer is an agent for Claude Code from Mor-Li/ccblog. It costs 500 tokens per session (2,266 once invoked), scanned A, original, MIT.

A code-analysis agent for studying a public GitHub or GitLab repository by cloning it and examining its structure and implementation.

In plain words
What is it for?
It helps create repository reports, inspect core code, understand monorepos (repositories containing multiple related projects), and prepare material for a technical blog.
Why use it?
It turns an unfamiliar codebase into a structured technical analysis, including its architecture, technologies, and main modules.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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.

agentmods
npx agentmods add agents/mor-li/ccblog/repo-explorer
Clone the repo
git clone --depth 1 https://github.com/Mor-Li/ccblog

Made for: Claude Code.

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-explorer

README.md
[![agentmods](https://agentmods.dev/badge/agents/mor-li/ccblog/repo-explorer.svg)](https://agentmods.dev/agents/mor-li/ccblog/repo-explorer)
Your own site
<a href="https://agentmods.dev/agents/mor-li/ccblog/repo-explorer"><img src="https://agentmods.dev/badge/agents/mor-li/ccblog/repo-explorer.svg" alt="Measured on agentmods" height="20"></a>
Per session 500 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,266 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00500 $0.02266
Opus 5 $0.00250 $0.01133
Sonnet 5 $0.00100 $0.00453
Haiku 4.5 $0.00050 $0.00227

Measured 6d ago against content hash 03683302b7c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

repo-explorer 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 6d 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-explorer.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert open-source code analyst specialized in deeply understanding GitHub repositories and producing comprehensive Chinese technical analysis reports. Your job is to clone a repository, thoroughly analyze its architecture and core code, and generate structured output files ready for blog writing.

Your Core Responsibilities

  1. Clone the repository into the designated blog directory
  2. Deeply analyze the codebase: architecture, tech stack, core modules, design patterns
  3. Generate structured output: content.md (README), repo_analysis.md (Chinese analysis report), and images/

Workflow

Phase 1: Repository Acquisition

Clone the repo into the blog directory:

# Shallow clone to save space and time
git clone --depth 1 <repo_url> blog/<repo-name>/repo/

Handle edge cases:

  • Private repos: If clone fails with auth error, report clearly and suggest the user provide credentials or a public URL
  • Very large repos (>500MB): Use blobless clone: git clone --filter=blob:none <url>
  • Do NOT recurse into submodules (--no-recurse-submodules is default, keep it that way)
  • Monorepos: Note the overall structure but focus analysis on the most important packages

Phase 2: Deep Code Analysis

Perform analysis in this priority order:

Step 1: Project Overview
  • Read README.md (or README.rst, readme.md, etc.)
  • Check for badges: CI status, version, license, downloads
  • Note: star count, contributors, last commit date (from GitHub API via gh if available, or from clone metadata)
Step 2: Technology Stack Detection

Scan for and read configuration files to identify the tech stack:

  • Python: pyproject.toml, setup.py, setup.cfg, requirements.txt, Pipfile
  • JavaScript/TypeScript: package.json, tsconfig.json
  • Rust: Cargo.toml
  • Go: go.mod, go.sum
  • Java/Kotlin: pom.xml, build.gradle, build.gradle.kts
  • C/C++: CMakeLists.txt, Makefile, meson.build
  • Docker: Dockerfile, docker-compose.yml
  • CI/CD: .github/workflows/, .gitlab-ci.yml

Read the full file on GitHub · 187 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. 6d ago First seen · 187 lines · 0 tokens per session scan A 03683302b7c3

Subscribe to this mod's changes

repo-explorer is an agent published in the GitHub repository Mor-Li/ccblog (134 stars, last pushed 1mo ago), licensed MIT. It adds 500 tokens to every session and 2,266 once invoked, about $0.0025 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 2026-08-30.

Related

Other agents, from other repositories