CLAUDE.md / AGENTS.md Starter Template

This is the generic version of the instruction file I actually run, with my paths, org, and integrations stripped out and replaced with placeholders. It's the file the agent loads into every conversation in a project, so what goes in it is a budget decision as much as a style one.

Two files, same rules:

• AGENTS.md — platform-neutral. Works in the Codex CLI (~/.codex/AGENTS.md globally, AGENTS.md at a repo root) and in Claude Code if you symlink CLAUDE.md to it. Adds a cross-model delegation section and an appendix mapping every concept across both platforms: what Claude Code calls a hook, what Codex calls an approval policy, where each one keeps skills, agents, rules, and MCP servers.
• CLAUDE.md — the same rules in Claude Code's vocabulary, with hook events and subagent routing named directly.

Pick one. They overlap by design, and you don't need to maintain both.

What's in it

Ten sections, any of which you can delete:

• Profile and communication — who you are, and the tone rules for work versus messages written on your behalf, including a banned-words list.
• Verification — observe the result before claiming it, and label every finding observed or reported.
• Delegation and parallelism — route subagents by how much judgment the task needs, plus the model-inheritance trap that quietly runs cheap work on your most expensive model.
• Cross-model delegation — why a second model family buys a separate quota pool and a reviewer with different blind spots, and why the call belongs in a wrapper script that owns every flag.
• Adversarial review — how to get a critique from a reviewer that would otherwise agree with you, and the reframing that gives the review loop a stopping point.
• Session handoff — an append-only decision log written before the work happens.
• Safety — confirm before outward-facing actions, the destructive-command list, and secrets handling.
• Context budget — the read-and-reread discipline, with a note on enforcing it through a hook so it doesn't depend on the model remembering.
• Preferences — the placeholders for your own tooling.
• Maintaining this file — a schedule for deleting rules a newer model no longer needs.

Three rules to take even if you skip the file

Put the rule in the file and the mechanism in a skill. If the instruction file explains how a tool works, move that explanation somewhere loaded on demand, because everything in this file competes with the task for attention on every turn.

Label every result observed or reported. A subagent saying "tests pass" and you having watched eight tests pass are different facts, and collapsing them is how a wrong assumption survives three sessions. Making the model say which one it has costs a word.

Delete rules on a schedule. Instructions written to steer an older model can hurt a newer one, because capable models need less direction and a stale guardrail reads as a constraint to satisfy. Open a fresh session, hand it your config, and ask what's unnecessary. Expect to cut a quarter of it. When a session flails on something simple, suspect the config before the model.

How it fits

The reasoning behind each section, with the specifics I run rather than the placeholders, is in the Claude Code Playbook. The packaged agents and skills are at /skills. Three public repos build on the same rules: maven-template is a full working repository, organization-ai-skills is 30 skills in the open SKILL.md format that install unchanged on Claude Code and Codex, and cross-model-agent-delegation is the wrapper pair for the delegation section.