agentleFS
vibe-cokitvibe-cokit/claude-code/skills/repomix/SKILL.md

repomix

Skill1 starsChanged 4 months agoApache-2.0View on GitHub

Pack a whole repo (local or remote) into one AI-friendly XML/Markdown/JSON file with token counts. Triggers on: "pack this codebase", feeding a large repo to an LLM, auditing an unfamiliar third-party library, building context for a security review.

  • Reads credentials
  • Installs packages

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use Problem-Solving Techniques, markdown-novel-viewer and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • truongtv22Skill

    Problem-Solving Techniques

    Apply systematic problem-solving techniques for complexity spirals (simplification cascades), innovation blocks (collision-zone thinking), recurring patterns (meta-pattern recognition), assumption constraints (inversion exercise), scale uncertainty (scale game), and dispatch when stuck. Techniques derived from Microsoft Amplifier project patterns adapted for immediate application.

    Also in 5 projects that use this

  • OpenAnalystIncSkill

    markdown-novel-viewer

    Also in 3 projects that use this

  • truongtv22Skill

    mobile-development

    Build modern mobile applications with React Native, Flutter, Swift/SwiftUI, and Kotlin/Jetpack Compose. Covers mobile-first design principles, performance optimization (battery, memory, network), offline-first architecture, platform-specific guidelines (iOS HIG, Material Design), testing strategies, security best practices, accessibility, app store deployment, and mobile development mindset. Use when building mobile apps, implementing mobile UX patterns, optimizing for mobile constraints, or making native vs cross-platform decisions.

    Also in 5 projects that use this

The file

Files
SKILL.md

Repomix

Packs repositories into single AI-friendly files, git-aware and token-counted.

Install & basic use

repomix --version                 # check
npm install -g repomix            # or: brew install repomix

repomix                           # pack cwd → repomix-output.xml
repomix --style markdown          # or json, plain
npx repomix --remote owner/repo   # remote, no clone
repomix --include "src/**/*.ts" --remove-comments -o output.md

Core options

PurposeFlag
Include patterns--include "src/**/*.ts,*.md"
Extra ignores-i "tests/**,*.test.js"
Ignore .gitignore--no-gitignore
Output format / path--style xml|markdown|json|plain, -o out.md
Strip comments--remove-comments
Clipboard--copy
Config-c custom-config.json, --init
Token map--token-count-tree [minTokens]
Skip secret scan--no-security-check

Remote forms: owner/repo, full URL, or …/commit/hash.

Workflow

  1. Assess — local or remote? which output format? any sensitive-data concern?
  2. Filter — set --include, add ignores, decide on comment removal.
  3. Pack — run repomix, watch token counts, let the security check run.
  4. Validate — review the output, confirm no secrets leaked, check it fits the target context window.
  5. Deliver — hand over the file plus a token-count summary and any warnings.

Security

Secretlint scans for API keys, passwords, credentials, private keys, AWS secrets. Always review output before sharing; keep sensitive paths in .repomixignore; never pack .env. Only disable the check on codebases you trust.

References

  • references/configuration.md — config file, glob patterns and precedence, output formats, advanced/perf options
  • references/usage-patterns.md — AI-analysis, security-audit, documentation and library-evaluation recipes; CI/CD + git-hook + IDE integration; language-specific patterns; token budgeting; troubleshooting

Docs: https://repomix.com/guide/ — repo: https://github.com/yamadashy/repomix (MCP server available).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.