clist: Instructions file for Codex

AGENTS.md

Short operating contract for AI coding agents working in the CLIST repository. It holds only the invariants every agent must see without a click; everything else lives in docs/ and in the skills.

The per-tool files — CLAUDE.md, GEMINI.md, and .github/copilot-instructions.md — are symlinks to this file, so Claude, Gemini, Copilot, Cursor, Codex, and any other agent read the same rules.

What CLIST is: a competitive-programming aggregator — see docs/project-context.md.

Golden rules

• Make small, reviewable changes. No large refactors or architectural changes unless explicitly asked.
• Inspect before editing. Read the relevant files and state a short plan before changing code.
• Match surrounding code — naming, structure, comment density, imports. Prefer existing project patterns over introducing new abstractions or dependencies.
• Do not rename public APIs, model fields, DB columns, env vars, or external contracts without asking.
• Never run destructive or outward-facing commands without explicit approval: no git push, git reset --hard, git clean -fd, no rm -rf, no DROP/DELETE/TRUNCATE, no deploys, no docker ... prune.
• Create or switch branches only when the user explicitly asks. A request to commit changes does not imply creating a separate branch.
• Commit or push only when the user asks.
• Never print or commit secrets — see docs/git-and-safety.md.
• After editing, run the narrowest relevant check first, then broaden — see docs/testing.md, docs/linting-formatting.md, and the run-and-verify skill.
• Be honest about what was and wasn't verified.

Documentation index