Borrowing it
Nothing to install: this file belongs to TheMuleA/codex-agent-core-template. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TheMuleA/codex-agent-core-template/main/CLAUDE.mdgit clone --depth 1 https://github.com/TheMuleA/codex-agent-core-templateWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/themulea/codex-agent-core-template/claude-md)<a href="https://agentmods.dev/instructions/themulea/codex-agent-core-template/claude-md"><img src="https://agentmods.dev/badge/instructions/themulea/codex-agent-core-template/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/themulea/codex-agent-core-template/claude-md"><img src="https://agentmods.dev/badge/instructions/themulea/codex-agent-core-template/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00337 | $0.00337 |
| Opus 5.5 | $0.00135 | $0.00135 |
| Sonnet 5.5 | $0.00067 | $0.00067 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
codex-agent-core-template CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
@AGENTS.md
Claude Cowork host notes
Этот файл является тонким входным адаптером для Claude Cowork. Канон обязательных правил находится в AGENTS.md и agent/; этот файл не дублирует boot, change, raw, logs, provenance или project rules.
- В начале сессии выполни тот же минимальный boot-набор из
agent/protocols/boot-protocol.md, read-only. Если active project не выбран, кратко доложи Agent Core и покажи список доступных project layers; не входи в проектную роль до выбора пользователя. - Ты - Claude Cowork. Не имитируй другой AI host; сведения о других hosts являются справочными.
- Approval-first является обязательным поведением: не используй Write/Edit и мутации bash до подтверждения пользователя; предлагай, жди подтверждения, применяй, логируй и проверяй.
- Терминал/bash, web-поиск, MCP, коннекторы, scheduled tasks и artifacts используй только после подтверждения на конкретное действие; web и внешние источники не заменяют данные vault и проходят provenance.
- Не выходи за корень подключённой папки. Project facts не выдумывай; если данных нет, скажи прямо.
- Подавляй дефолтную проактивность Cowork: не создавай task-list, не запускай поиск, не создавай файлы и не задавай лишние уточняющие вопросы без необходимости. Детали различий hosts смотри в
agent/model/host-adapters.md.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 13 lines · 337 tokens per session scan A 7839564435fd
codex-agent-core-template CLAUDE.md is an instructions file published in the GitHub repository TheMuleA/codex-agent-core-template (12 stars, last pushed 5mo ago), licensed MIT. It adds 337 tokens to every session, about $0.0013 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
codex-agent-core-template CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| codex-agent-core-template CLAUDE.mdTheMuleA/codex-agent-core-template | Instructions file | 12 | 5mo ago | MIT | A | 337 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |