Agent skill

gitinjest

Analyze GitHub repositories by converting to LLM-readable text. TRIGGER when user pastes github.com URL, asks "how does [library] work", or references external codebases. Supports public/private repos and subdirectories.

View SKILL.md on GitHub Repository
Stars 5
Forks 3

Install this agent skill to your Project

npx add-skill https://github.com/iamhenry/ai-project-starter-kit/tree/main/.opencode/skills/gitinjest

SKILL.md

Gitingest

TRIGGER CONDITIONS

USE when user message contains:

  • github.com/ URL
  • "look at this repo" or "analyze this codebase"
  • Questions about third-party library internals

SKIP when:

  • URL is user's own project
  • User just wants to clone/fork

Convert GitHub repos into text format using the CLI. By default, gitingest writes to digest.txt; use -o - to stream to stdout.

STREAMING ONLY (HARD DEFAULT)

ALWAYS stream to stdout with -o -. DO NOT:

  • Clone repos locally
  • Write output files (-o file.txt)
  • Redirect to disk (> out.txt)
  • Create temp files

Only write to disk if user EXPLICITLY requests it.

bash
# CORRECT: streams to stdout (recommended default)
gitingest https://github.com/user/repo -o -
gitingest https://github.com/user/repo -i "*.ts" -o -

# WRONG - writes to disk (avoid unless user asks)
gitingest https://github.com/user/repo -o output.txt
gitingest https://github.com/user/repo > dump.txt

Gitingest CLI Commands for External Codebase Analysis

Key lesson: Always search broadly first (-i ".ts" for TypeScript, -i ".py" for Python, etc.) before narrowing down. The commands are powerful, but your search scope determines what you find.

Installation

bash
pipx install gitingest

Linux Notes

  • If pip install --user fails with PEP 668 error, use pipx install gitingest instead.
  • If gitingest: command not found after pipx install, ensure ~/.local/bin is on PATH. Run pipx ensurepath, restart your shell, then verify command -v gitingest.
  • Verify: gitingest --help or pipx list | grep gitingest

Default Usage (Streaming to stdout)

bash
# Stream output directly (no file created)
gitingest https://github.com/username/repo -o -

# Capture in variable for processing
output=$(gitingest https://github.com/username/repo -o -)

Private Repositories

bash
# Set token as environment variable
export GITHUB_TOKEN=github_pat_...
gitingest https://github.com/username/private-repo -o -

# Or pass directly
gitingest https://github.com/username/private-repo --token github_pat_... -o -

Subdirectories

bash
# Analyze only specific part of repo
gitingest https://github.com/user/repo/tree/main/src -o -

Basic Usage

  • gitingest https://github.com/user/repo -o - - Get full repo overview (stdout)
  • gitingest https://github.com/user/repo --include-submodules -o - - Include submodules

File/Content Search

  • gitingest https://github.com/user/repo -i "pattern" -o - - Search files containing pattern
  • gitingest https://github.com/user/repo -i "*filename*" -o - - Find files by name/glob
  • gitingest https://github.com/user/repo -i "path/to/file" -o - - Get specific file content

Filtering

  • gitingest https://github.com/user/repo -e "pattern" -o - - Exclude files matching pattern
  • gitingest https://github.com/user/repo -i "*.ts" -e "node_modules/*" -o - - Include TS files, exclude node_modules

Key Options

  • -o - or --output -: Stream to stdout (no temp file)
  • --token or -t: GitHub token for private repos
  • --include-submodules: Include git submodules
  • --include-gitignored: Include files normally ignored by .gitignore

Output Structure

The CLI returns formatted text with:

  • Summary: File count, size, token count
  • Tree: Directory visualization
  • Content: All code combined and formatted

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

iamhenry/ai-project-starter-kit

verification-gate

Reusable verification gate for completed work before commit or merge. Use when implementation is done and Claude must prove the task works, verify the main user flow, choose between browser-flow, browser-static, or non-browser validation, and return a PASS/FAIL/BLOCKED verdict with evidence. When browser verification is needed, rely on the agent-browser skill for browser actions, screenshots, and recordings.

5 3
Explore
iamhenry/ai-project-starter-kit

osgrep

Semantic code search using natural language queries. Use when users ask "where is X implemented", "how does Y work", "find the logic for Z", or need to locate code by concept rather than exact text. Returns file paths with line numbers and code snippets.

5 3
Explore
iamhenry/ai-project-starter-kit

napkin

Maintain a per-repo napkin file that tracks mistakes, corrections, and what works. Activates EVERY session, unconditionally. Read the napkin before doing anything. Write to it continuously as you work — not just at session boundaries. Log your own mistakes, not just user corrections. The napkin lives in the repo at `.opencode/napkin.md`.

5 3
Explore
iamhenry/ai-project-starter-kit

dogfood

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

5 3
Explore
iamhenry/ai-project-starter-kit

tmux

Manage concurrent background processes using tmux. Use when spawning dev servers, running long-running tasks, monitoring multiple processes, or capturing output from background commands without blocking the main session.

5 3
Explore
iamhenry/ai-project-starter-kit

viral-research

Viral content research and DNA extraction for Instagram Reels. Use this skill whenever you need to research what's performing in a niche on Instagram, find viral faceless Reels, download and analyze them frame-by-frame, identify patterns, and produce a structured research brief. Trigger whenever the user mentions viral content research, Instagram research, Reel analysis, content DNA, swipe file building, niche research, competitor analysis for social content, or wants to understand why certain content performs. Also trigger when the user wants to find content formats to adapt, study what's working in a niche, or build a research-backed content strategy. This skill is research-only — it does not generate or publish content.

5 3
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results