Borrowing it
Nothing to install: this file belongs to Trum-ok/tutu-mcp-hackathon. 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/Trum-ok/tutu-mcp-hackathon/master/CLAUDE.mdgit clone --depth 1 https://github.com/Trum-ok/tutu-mcp-hackathonWrote 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/trum-ok/tutu-mcp-hackathon/claude-md)<a href="https://agentmods.dev/instructions/trum-ok/tutu-mcp-hackathon/claude-md"><img src="https://agentmods.dev/badge/instructions/trum-ok/tutu-mcp-hackathon/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/trum-ok/tutu-mcp-hackathon/claude-md"><img src="https://agentmods.dev/badge/instructions/trum-ok/tutu-mcp-hackathon/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 | $0.00510 | $0.00510 |
| Opus 5.5 | $0.00204 | $0.00204 |
| Sonnet 5.5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
tutu-mcp-hackathon 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
CLAUDE.md
Документация и комментарии
- Пишутся на русском.
- Код объясняет себя сам — не оставляй пояснительных комментариев после изменений.
- Не используй эмодзи, если не просят.
- Не фиксируй в доке то, что есть в источнике истины (версии —
pyproject.toml, история — git).
Запрет живого режима
Живой режим тратит общий лимит хакатона, поэтому он закрыт не на словах, а на уровне харнесса —
.claude/settings.json: deny-правила плюс хук PreToolUse на Bash, который вызывает
block-live-commands.py. Запрет действует и на
подагентов.
Блокируются: make run-live, make evals, make evals-record, make fixtures,
tutu.py record, tutu.py evals с --live или --record-missing, любая команда,
начинающаяся с TUTU_PROXY_MODE=live.
Остаются разрешёнными: make evals-dry, make demo-traces, make run-mock, make viewer,
make test, make lint — всё, что работает на фикстурах.
Хук смотрит только на исполняемую часть команды: тела heredoc'ов и содержимое кавычек
вырезаются, поэтому писать документацию с упоминанием этих команд можно.
Проверить поведение: python3 .claude/hooks/test_block_live.py.
Живой прогон запускает человек вручную в отдельном терминале. Подагенты оценивают живые пути по чтению кода и обязаны помечать это в отчёте.
Git-конвенции
- Коммиты:
<тип>: <описание на русском>, тип из [feat, fix, refactor, chore, docs, style, perf] (можно расширять). - Ветки:
<тип>/<краткое-описание>(english, kebab-case), тип из [feature/, fix/, refactor/, chore/]. Персональныеdev-<Имя>допустимы. - commit и push: не коммить и не пуш ничего без моего согласия.
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 · 37 lines · 510 tokens per session scan A 25b584ecb5f9
tutu-mcp-hackathon CLAUDE.md is an instructions file published in the GitHub repository Trum-ok/tutu-mcp-hackathon (0 stars, last pushed 29d ago), licensed MIT. It adds 510 tokens to every session, about $0.0020 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.