Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/a2c-smcp/theseus-kit/claude-mdgit clone --depth 1 https://github.com/A2C-SMCP/theseus-kitWrote 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/a2c-smcp/theseus-kit/claude-md)<a href="https://agentmods.dev/instructions/a2c-smcp/theseus-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/a2c-smcp/theseus-kit/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 | $0.02827 | $0.02827 |
| Opus 5 | $0.01413 | $0.01413 |
| Sonnet 5 | $0.00565 | $0.00565 |
| Haiku 4.5 | $0.00283 | $0.00283 |
Grade A, and why
theseus-kit 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 4d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
项目概述
theseus-kit 是一个 MCP 服务器，用于安全地检查、编辑、模板化和发布 TFRobot 配置。它通过标准 MCP 协议运行，同时暴露可选的 A2C-SMCP 兼容的 window:// 和 skill:// 资源。
当前状态：0.1.0 项目骨架阶段，配置变更工具尚未实现。详情见 0.1.0 里程碑。
开发命令
需要 Python 3.11+ 和 uv。
uv sync --locked --all-groups # 安装全部依赖
uv run theseus-kit # 启动 MCP 服务器（stdio 传输）
所有质量检查通过 Poe 任务运行：
uv run poe check # 顺序执行 format-check → lint → typecheck
uv run poe ci # CI 完整流程：lock-check → check → test-cov
uv run poe format # ruff 格式化
uv run poe lint # ruff 代码检查
uv run poe typecheck # mypy 严格模式类型检查
uv run poe test # 运行测试（pytest，asyncio 模式 auto）
uv run poe test-cov # 测试覆盖率（需要 ≥80%）
uv run poe build # 构建 wheel + sdist
uv run poe package-check # twine 检查构建产物
任务列表可通过 uv run poe --help 查看。
运行单个测试
uv run pytest tests/test_auth_routing.py -v
uv run pytest tests/test_auth_routing.py::test_exchange_wire_user_pat -v
E2E 测试（需要真实机器人）
THESEUS_E2E=1 \
THESEUS_ROBOT__ROBOT_ID=<rid> \
THESEUS_ROBOT__NAMESPACE=<ns> \
THESEUS_ROBOT__ROBOT_TYPE=tfrobot \
THESEUS_ROBOT__API_BASE_URL=https://api.<clusterDomain> \
THESEUS_ROBOT__MANAGER_BASE_URL=https://<manager-host> \
THESEUS_CREDENTIAL__KIND=user_pat \
THESEUS_CREDENTIAL__PAT=<tfp_...> \
THESEUS_CREDENTIAL__ROBOT_PUBLIC_ID=<orgSlug>:<employeeNo> \
uv run pytest tests/test_e2e_robot.py -v -m e2e
发布前准备
uv run poe ci && uv run poe build && uv run poe package-check
发布流程见 docs/releasing.md：版本号由 bump-my-version 管理，通过 GitHub Release + OIDC Trusted Publishing 发布到 PyPI/TestPyPI。
架构
分层设计
- MCP 表面层（
server.py）— FastMCP 实例，工具/资源声明 - 应用服务层（尚未实现）— 读、编辑、保存模板、发布用例
- TFRobot 客户端（
transport.py、routing.py、tokens.py、credentials.py）— 认证 HTTP 适配器，对接/v1/factory/**和/llms.txt - 资源投影层 —
window://实时快照（resources.py，三个窗口 summary/recent/topology + 订阅能力subscriptions.py）与skill://技能指南（skills/，12 个类别，三层结构）：theseus总纲调度 → 阶段技能persona-interview/persona-optimize/plan-config/apply-config-plan→ 原子技能analyze-config/manage-topology/tune-config/save-template/publish-config/write-tfonto，外加反馈闭环技能enhance。阶段交接物在机器人工作区~/.theseus/workspaces/<slug>/（画像<slug>.md+configs/+plans/）
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.
- 4d ago First seen · 149 lines · 2,827 tokens per session scan A d646e69e4e4d
theseus-kit CLAUDE.md is an instructions file published in the GitHub repository A2C-SMCP/theseus-kit (0 stars, last pushed 18d ago), licensed MIT. It adds 2,827 tokens to every session, about $0.0141 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 2026-08-31.
Other instructions, from other repositories
apm python.instructions.md
Python development guidelines.
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
foundry-local python-cffi-pointer-types.instructions.md
Use when working on the Python SDK's native bindings (cffi), especially when defining new Item subclasses, working with flItemQueue, or extending Request/Session methods that pass native handles.
haggle AGENTS.md
AGENTS.md instructions for NaanyaBiz/haggle, covering agents.md — haggle integration guide, dev loop, install deps (once, or after pyproject.toml changes), run tests and lint + format.
pydantic-ai-gepa AGENTS.md
AGENTS.md instructions for indexedlabs/pydantic-ai-gepa, covering repository guidelines, mighty workflow, project structure & module organization, build, test, and development commands and coding style & naming conventions.
genmedia-izumi-agent GEMINI.md
Gemini CLI instructions for GoogleCloudPlatform/genmedia-izumi-agent.