IDEA.Md
Description
IDEA.md — A standard file for portable idea intent in agentic software work. Share the idea, not the code. Your agent builds the rest. Inspired by Karpathy's idea file concept. Vendor-neutral, works with Claude Code, Codex, Gemini CLI, Copilot, and any LLM agent.
Installation
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open the source below and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
README
IDEA.md — A Standard for Portable Idea Intent in Agentic Software
**IDEA.md** is a vendor-neutral file standard for expressing *what to build and why* before any code is written. It is the upstream intent document for AI coding agents — designed to sit above `AGENTS.md`, `CLAUDE.md`, `GEMINI.md`, and Copilot instruction files in the project hierarchy. Where those files tell agents how to behave in a repo, `IDEA.md` tells them what the idea actually is.
Inspired by Andrej Karpathy's [idea file concept](https://x.com/karpathy/status/2040470801506541998): in an era where AI agents can build anything from a prompt, the scarce resource is knowing what to build. Share the idea, not the code. The other person's agent customizes and builds it for their specific needs.
Why IDEA.md Exists
AI coding agents like Claude Code, OpenAI Codex, Gemini CLI, and GitHub Copilot already have instruction files for agent behavior. But there is no broadly adopted, vendor-neutral file for the idea itself — the product thesis, problem framing, solution shape, and boundaries.
`IDEA.md` fills that gap. It is the source-of-truth file for product intent in any agentic software project.
How It Works
Every project gets one root-level `IDEA.md`. It has five required sections:
| Section | Purpose |
|---|---|
| Thesis | One or two sentences capturing the core idea |
| Problem | What's broken today and for whom |
| How It Works | The pattern and key insight — not the implementation |
| What It Does Not Do | Boundaries that prevent scope creep and overbuilding |
| Where To Start | A nudge for agents to begin collaborating with the user |
Optional sections (add when they earn their place): Why Now, Who Benefits, Constraints, Risks, Open Questions, Success Criteria, Context and References.
The file is intentionally abstract. It describes ideas, not implementations. The agent and the user figure out the specifics together.
Quick Start
- Copy [`ID
Related Skills
Auto Update
Pull the latest ECC repo changes and reinstall the current managed targets.
Development Ecc Guide
Navigate ECC's current agents, skills, commands, hooks, install profiles, and docs from the live repository su
Development Epic Claim
Claim an epic issue, stamp coordination state, and sync local ownership.
Development Epic Publish
Publish a validated epic update back to the issue and local cache.
Development Epic Review
Mark epic review requested, approved, or changes requested.
Development Epic Unblock
Sweep blocked epic issues and reopen anything whose dependencies are closed.
Development Related Agents
Django Build Resolver
Django/Python build, migration, and dependency error resolution specialist. Fixes pip/Poetry errors, migration
Openai Codex CLI
(55.8k ⭐) - Lightweight coding agent that runs in your terminal.
src/agents/ — 11 Agent Definitions
**Generated:** 2026-04-11