Borrowing it
Nothing to install: this file belongs to cryptoyoginya/harness-health-engineering. 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/cryptoyoginya/harness-health-engineering/main/CLAUDE.mdgit clone --depth 1 https://github.com/cryptoyoginya/harness-health-engineeringWrote 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/cryptoyoginya/harness-health-engineering/claude-md)<a href="https://agentmods.dev/instructions/cryptoyoginya/harness-health-engineering/claude-md"><img src="https://agentmods.dev/badge/instructions/cryptoyoginya/harness-health-engineering/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/cryptoyoginya/harness-health-engineering/claude-md"><img src="https://agentmods.dev/badge/instructions/cryptoyoginya/harness-health-engineering/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 | $0.01563 | $0.01563 |
| Opus 5.5 | $0.00625 | $0.00625 |
| Sonnet 5.5 | $0.00313 | $0.00313 |
| Haiku 4.5 | $0.00156 | $0.00156 |
Grade B, and why
harness-health-engineering CLAUDE.md scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| **Permissions + Hooks** | [`.claude/settings.json`](./.claude/settings.json) | что разрешено авто, какие хуки проверяют записи | How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Правила проекта — health-harness
Этот файл загружается Claude Code как operational rules: язык, дисциплина, привычки, домен-правила. AGENTS.md описывает как работать с KB о здоровье. CLAUDE.md — как работать в этом конкретном репо.
Язык
Все артефакты (логи, документы, коммиты) — на русском. На латинице в любом случае: ID/ключи/имена файлов/переменных; имена собственные (Whoop, Blueprint, HRV, REM, SpO2); аббревиатуры; цифры и единицы (₽, %, мс, ч, мин.).
Дисциплина веток
- Работаем в feature-ветке, мерджим в
mainчерез ff-merge. Без force-push. - После пуша в
main— короткое резюме: что сделано + как проверить. - Перед мержем значимых правок —
pnpm kb:doctor(EXIT 0).
Артефакты — сразу в git
.context/ — gitignored зона для черновиков. Любой значимый артефакт (документ с frontmatter
type:/version:) — сразу в коммитимую зону: synthesis → /04_synthesis/, решения и эксперименты →
/05_decisions/, финальное для людей → /06_outputs/.
Слои оснастки (AI harness)
| Слой | Где живёт | Роль |
|---|---|---|
| System prompt | AGENTS.md |
reading order, метки, медицинская граница, ingest |
| Operational rules | CLAUDE.md (этот файл) |
язык, ветки, домен-правила здоровья |
| Permissions + Hooks | .claude/settings.json |
что разрешено авто, какие хуки проверяют записи |
| Working memory | .remember/core.md |
semantic invariant (коммитится) |
| Skills | skills/ |
плейбуки: red-recovery, sleep-debt, mood-dip, injury, getting-back, weekly-synthesis, coach |
| Whoop ingest | scripts/whoop/ |
auth.mjs (OAuth разово), sync.mjs (утро: физиология → daily-лог) |
| Semantic search | scripts/semantic/ |
on-device hybrid RAG: search.mjs, think.mjs, backlinks.mjs |
| MCP-сервер KB | scripts/semantic/mcp-server.mjs |
kb_search, kb_think, kb_backlinks. Конфиг: .mcp.json |
| KB-doctor | scripts/kb-doctor.mjs |
health-check KB: frontmatter, broken related:, orphans |
| Dream cycle | scripts/dream-cycle.mjs |
еженедельный LLM-аудит KB |
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 · 84 lines · 1,563 tokens per session scan B 7734b7ea4257
harness-health-engineering CLAUDE.md is an instructions file published in the GitHub repository cryptoyoginya/harness-health-engineering (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,563 tokens to every session, about $0.0063 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
harness-health-engineering CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| harness-health-engineering CLAUDE.mdcryptoyoginya/harness-health-engineering | Instructions file | 0 | 4mo ago | MIT | B | 1,563 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |