Coding agents in the review loop
Every coding agent and assistant CodePanel works with, how each one connects, and the instruction files they read.
Coding agents
They write the code, open the pull request, and answer the panel's findings: fixed, disputed with evidence, and rated.
| Agent | Maker | Connects through | Rules files |
|---|---|---|---|
| Claude Code | Anthropic | Plugin (setup) | CLAUDE.md, .claude/rules/*.md, AGENTS.md (by default only when there is no CLAUDE.md) |
| Codex | OpenAI | MCP, Skills (setup) | AGENTS.md, AGENTS.override.md |
| Cursor | Anysphere | MCP, Skills (setup) | .cursor/rules/*.mdc, AGENTS.md, CLAUDE.md |
| Copilot in VS Code | GitHub | MCP, Setup prompt (setup) | AGENTS.md, .github/copilot-instructions.md, .github/instructions/**/*.instructions.md, CLAUDE.md (in the Local harness) |
| Gemini CLI | MCP, Skills (setup) | GEMINI.md, AGENTS.md (when listed in context.fileName) |
|
| OpenCode | Anomaly | MCP, Skills (setup) | AGENTS.md, CLAUDE.md (only when there is no AGENTS.md) |
| GitHub Copilot CLI | GitHub | MCP, Skills (setup) | AGENTS.md, .github/copilot-instructions.md, .github/instructions/**/*.instructions.md, CLAUDE.md, GEMINI.md |
Assistants
They read reviews and rate findings in chat. The fixes come from a coding agent.
| Agent | Maker | Connects through | Rules files |
|---|---|---|---|
| Claude | Anthropic | Connector (setup) | None |
| ChatGPT | OpenAI | Connector (setup) | None |
Instruction files
What each agent reads before it works, and what to put there for review.
- AGENTS.md for an agent-to-agent review loop: What to put in AGENTS.md so a coding agent answers AI code review on its own: how each agent loads the file, the review section, and one file for every agent.
- CLAUDE.md for an agent-to-agent review loop: What to put in CLAUDE.md so Claude Code sees AI code review through to merge: what loads when, where the loop goes, the size target, and sharing with AGENTS.md.
- copilot-instructions.md for an agent-to-agent review loop: How GitHub Copilot CLI and Copilot in VS Code combine copilot-instructions.md with AGENTS.md, CLAUDE.md and GEMINI.md, and where the review loop belongs.
- Cursor rules for an agent-to-agent review loop: Cursor rules for AI code review: which .mdc rule type to use, scoping a rule with globs like a .codepanel/rules.md section, and when to use AGENTS.md.
- GEMINI.md for an agent-to-agent review loop: What Gemini CLI loads from GEMINI.md, why it skips AGENTS.md by default, and three ways to give it the same review instructions as every other agent.