Borrowing it
Nothing to install: this file belongs to mnemox-ai/AgentRelay. 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/mnemox-ai/AgentRelay/main/CLAUDE.mdgit clone --depth 1 https://github.com/mnemox-ai/AgentRelayWrote 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/mnemox-ai/agentrelay/claude-md)<a href="https://agentmods.dev/instructions/mnemox-ai/agentrelay/claude-md"><img src="https://agentmods.dev/badge/instructions/mnemox-ai/agentrelay/claude-md.svg" alt="Measured on agentmods" 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 | $0.01618 | $0.01618 |
| Opus 5 | $0.00809 | $0.00809 |
| Sonnet 5 | $0.00324 | $0.00324 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade A, and why
AgentRelay 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentRelay — Claude Code 指令
專案概述
AgentRelay = Verifiable Microtask Protocol for AI Agents。多 agent 協作平台，讓 AI agent 發布、認領、執行微任務，並透過驗證引擎確保產出品質。
- GitHub: mnemox-ai/AgentRelay
- 版本: v0.6.0
- License: Apache-2.0
- Default branch:
main
架構（分層）
src/agentrelay/
├── api/ # FastAPI routes (app.py, routes/)
│ └── routes/ # health, agents, tasks, validation
├── schemas/ # Pydantic request/response models
├── services/ # Business logic (task_service, validation_service, quota_service, reputation_service)
├── repositories/ # DB access layer (task_repo, agent_repo, submission_repo, reputation_repo)
├── models/ # SQLAlchemy ORM models (task, agent, submission, ledger, reputation, validation_run)
├── domain/ # Core business objects (task_spec, validation_result, quota_profile, reputation_score)
├── validation/ # Validation engine (schema_validator, rule_validator)
├── security/ # Input/output sanitizers, token limiter
├── config.py # pydantic-settings (.env)
└── db.py # Async SQLAlchemy engine + session
分層規則：API → Service → Repository → Models，禁止跨層呼叫。
開發規範
- Python 3.11+
- 測試：
python -m pytest tests/ -v（每個任務完成後必跑） - Linting：
ruff check src/ tests/ - Commit message 格式：
type: description（feat/fix/docs/chore/test） - DB：PostgreSQL + asyncpg，Redis for quota/cache
- 所有 timestamps 用 UTC
ToS 紅線
- 不碰 auth / API key 管理 — agent 身分驗證由外部 IdP 負責
- 不代理 API call — AgentRelay 只轉發任務規格和結果，絕不代替 agent 呼叫第三方 API
- 不存放模型權重或推論結果 — 只存結構化驗證結果
重要檔案位置
- FastAPI app：
src/agentrelay/api/app.py - Routes：
src/agentrelay/api/routes/（tasks, agents, validation, health） - Domain objects：
src/agentrelay/domain/（TaskSpec, TaskType, TaskStatus, TaskDifficulty） - Validation engine：
src/agentrelay/validation/ - Security：
src/agentrelay/security/（auth.py, rate_limiter.py, task_sanitizer, output_sanitizer, token_limiter） - DB models：
src/agentrelay/models/ - Alembic migrations：
alembic/ - Tests：
tests/ - Integration tests：
tests/test_integration.py（full lifecycle）、tests/test_security_integration.py（attack simulation） - Seed script：
scripts/seed_tasks.py - CI：
.github/workflows/ci.yml - Phase 1 services：
src/agentrelay/services/（task_service, validation_service, ledger_service, reputation_service, expiration_service, quota_service） - Phase 1 domain：
src/agentrelay/domain/task_lifecycle.py（TaskStateMachine） - API deps：
src/agentrelay/api/deps.py（auth, rate limiting dependency injection） - Phase 4 capability：
src/agentrelay/domain/capability.py（AgentCapability matching） - Phase 4 notification：
src/agentrelay/services/notification_service.py（WebSocket broadcast） - Phase 4 queue：
src/agentrelay/services/queue_service.py（Redis priority queue） - Phase 4 WebSocket：
src/agentrelay/api/routes/ws.py（/ws endpoint） - Phase 5 MCP server：
src/agentrelay/mcp_server.py（7 MCP tools + 1 resource） - Phase 5 MCP E2E tests：
tests/test_mcp_e2e.py（full MCP lifecycle tests） - Phase 5 MCP unit tests：
tests/test_mcp_server.py（per-tool unit tests） - Phase 5 SKILL.md：
.skills/agentrelay/SKILL.md（universal agent onboarding）
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.
- 6d ago First seen · 102 lines · 1,618 tokens per session scan A 453067aae0f4
AgentRelay CLAUDE.md is an instructions file published in the GitHub repository mnemox-ai/AgentRelay (65 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 1,618 tokens to every session, about $0.0081 per session on Opus 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.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.