Guardrails, task board and spec-driven agent roles for Claude Code, enforced by hooks instead of prompts.
✳︎ ratchet
└─ Make every conversation easier
Browse source-linked experiments outside the main categories.
90 projectsGuardrails, task board and spec-driven agent roles for Claude Code, enforced by hooks instead of prompts.
Keeps review findings (H1, M3, L2...) per repo across sessions and ticks them off when their PR merges
Vimium-style hints over the Claude desktop app: /hintvim or Ctrl+;. Needs the hintvim app on macOS.

BazaarLink is an OpenAI-compatible AI API gateway: one key for 140+ AI models, pay as you go, with budget limits.
bazaarlink.aiVisit sponsor ↗A colored card with a link under each MR/PR created, merged, approved or reviewed
Buddy: context, session summaries and resume, project diagnostics, STH skills and fika breaks
Unified workbench: a status band for subagents and mmrun reviews, plus a seven-page pane (Overview / Agents / Reviews / GPU / Timeline / Usage / Progress; Reviews, GPU and Progress show once they have data); the Progress page lists the per-project progress board, recorded after each typed turn that changed files or made a commit

Claude Code adds mods functionality, allowing customization of behavior and interface with a few lines of TypeScript, installed as plugins via /plugin, built on hooks; Anthropic says /diff and AGENTS.md support are built with mods.

Claude Mods are Plugins for Claude Code https://youtu.be/EiThSVZ8pME?is=ZSnNOC6
Track what your AI coding tools cost
syrtis.nyanako.comVisit sponsor ↗charts is a Claude Code mod that replaces vega-lite, mermaid and dot blocks with real images: PNG in the terminal (kitty protocol) and SVG in the desktop app, with render caching.
Top 3 by votes, then GitHub stars
No. Votes and stars measure popularity. Review the source and permission scan before installing.