repo-analyzer
par don-gbot
Coding Agents & IDEsRésumé
GitHub repository trust scoring and due diligence.
Description
Ce que fait ce skill
Analyzes GitHub repositories across 14 scoring categories and produces a trust score out of 100. Covers commit health, dependency audits, AI-generated code detection, crypto rug patterns, and agent safety checks. Also extracts and analyzes GitHub links found inside X/Twitter URLs.
Running 14 scoring categories in a single zero-dependency script replaces manually checking stars, CI config, commit history, and secrets across separate tools.
Quand l'utiliser
- Checking if a new DeFi project's repo is legitimate before investing
- Auditing a dependency for malicious packages or install hooks
- Batch scanning multiple repos from a crypto project shortlist
- Extracting and scoring GitHub repos linked in a tweet
- Verifying contributor diversity and bus factor on an open-source tool
Exemple de workflow
User asks: analyze this tweet https://x.com/someuser/status/123 and tell me if the project is legit
- 1
Extracts the GitHub URL embedded in the tweet
- 2
Runs node scripts/analyze.js with the extracted repo and GITHUB_TOKEN loaded
- 3
Scores the repo across 14 categories including crypto safety and agent safety
- 4
Checks for rug patterns, hardcoded secrets, and suspicious dependency hooks
- 5
Returns the grade, score, and notable flags in a concise summary
ProjectName: 62/100 [C] — 3 contributors, no GPG sigs, mint function detected, 1 hardcoded API key found in src/config.js. Agent safety: CAUTION.
Prérequis
- GitHub Personal Access Token (GITHUB_TOKEN environment variable) for full scoring accuracy
Installation
clawhub install don-gbot/repo-analyzerExécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.