GitHub radar
Make your AI coding agent plan, test, and review itself first
This add-on changes how your AI agent works: it plans and writes tests before touching code, then checks its own result. Expect fewer mistakes and less back-and-forth.
ECC is an add-on for your AI agent: 68 specialized helpers and 293 ready-made workflows (skills). The agent plans and tests a task first, then writes the code.
When it helps
Useful if you already code with an AI agent and want fewer bugs and rewrites. Skip it if you don't use an agent for coding.
Pros
- Agent writes its own tests and reviews the code
- Fewer fixes and errors needed after each task
- Successful solutions turn into reusable workflows later
- Scans agent configs and files for hidden threats
Cons
- Full support is for Claude Code; other agents get less
- 293 skills and 68 agents can overwhelm a beginner
- Private repos and some features require a paid plan
How to set it up — step by step
- 1Open your AI agent (Claude Code or Codex) inside your project folder.
- 2Send the agent the text from the block below — it installs ECC and asks you for keys if needed.
- 3In Claude Code, run /plugin list to confirm ecc@ecc is enabled.
- 4Ask the agent to handle a small task and watch it plan and test first.
- 5Check the result — if it works, the agent saves the approach to reuse later.
Text for your agent
Copy this and send it to your agent — Claude Code, Codex, any of them:
Install ECC from https://github.com/affaan-m/ECC — follow the README, run /plugin install ecc@ecc in Claude Code or npx ecc-universal setup in the terminal, and ask me if you need any permissions or keys.
▌ More finds