Sourcery MCP
Let your coding agent request Sourcery reviews and fix the comments and security findings itself
Spec Kit
GitHub's open source toolkit for spec driven development with coding agents
About
A repeatable spec, plan, tasks, implement loop for any coding agent
Install the CLI with uv tool install specify-cli (Python 3.11+ and uv required), then run specify init my-project --integration copilot, swapping in your agent. The init step drops the slash commands and templates into your repo. Extensions install with specify extension add, for example specify extension add bug for a bug fix process or specify extension add assess for idea assessment. Things to know: it shines on new features and greenfield projects where a written spec pays off; for tiny fixes the full loop is overkill.
Features
- Spec, plan, tasks and implement slash commands
- Project constitution with your team's principles
- Bug fix and idea assessment extensions
- Presets, workflows and shareable catalogs
- Works with Copilot, Claude Code, Gemini CLI, Cursor, Codex and more
- MIT licensed, maintained by GitHub
Install
Related skills
All skillsRelated articles
All articlesGrok Bot vs Claude Code and Codex: What Each One Is For
How Grok Bot, a persistent personal agent, differs from coding agents like Claude Code and Codex, and when it makes sense to use each one or both together.
7 Tools to Cut Your Coding Agent's Token Bill (2026)
Seven tools that cut Claude Code, Codex and Cursor token usage by compressing shell output, searching code and fetching current docs, with honest caveats.
Best Memory Tools for Claude Code (2026)
Five tools that give Claude Code memory across sessions, agents and machines, with install commands, honest caveats and when CLAUDE.md is enough.
