Borrowing it
Nothing to install: this file belongs to 3aKHP/prts-mcp. 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/3aKHP/prts-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/3aKHP/prts-mcpWrote 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/3akhp/prts-mcp/claude-md)<a href="https://agentmods.dev/instructions/3akhp/prts-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/3akhp/prts-mcp/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 | $0.06288 | $0.06288 |
| Opus 5 | $0.03144 | $0.03144 |
| Sonnet 5 | $0.01258 | $0.01258 |
| Haiku 4.5 | $0.00629 | $0.00629 |
Grade A, and why
prts-mcp 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 2d 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 — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — AI 协作者说明
PRTS-MCP 是面向明日方舟同人创作的 MCP Server,包含 Python 和 TypeScript 两套独立实现;两端均支持 stdio 与 Streamable HTTP。本文件记录每次会话必读的工作流。
相关文档
| 想看... | 去哪里 |
|---|---|
| 项目现状、版本状态、仓库结构 | STATUS.md |
| 代码规范、反模式、已知陷阱 | docs/dev/STYLE.md |
| 全量 E2E 真机测试流程(高风险改动后必跑) | docs/dev/E2E.md |
| 路线图与未来规划 | ROADMAP.md |
| 1.x → 2.0 迁移(破坏性变更) | docs/migration-1.x-to-2.0.md |
| 1.7 LTS 维护规则 | docs/dev/LTS.md |
| 外部贡献者指南 | CONTRIBUTING.md |
| Python 实现 | python/ |
| TypeScript 实现 | ts/ |
动手写代码前先读 docs/dev/STYLE.md;不确定项目欠什么时查 STATUS.md。
本机运行时环境(WSL2)
本仓库在当前 WSL2 主机上的已验证入口:
- Shell:交互使用当前 POSIX shell;仓库的 Linux 脚本以 Bash 为执行环境
- Python:由
uv管理python/项目环境,初始化运行uv sync --directory python --locked - Python 命令统一经
uv run --directory python ...执行,不直接调用python/.venv,也不依赖 ambientpython - TypeScript:Node.js 要求 >=22,首选
ts/package.json中的 Volta 版本;默认生产运行时为 Bun >=1.3.14 - WSL 下直接使用
npm/npx
快速检查:
./scripts/check-runtime.sh
完整验证:
./scripts/check-runtime.sh --full
python/uv.lock 是可复现环境的来源。uv 仍会在项目内维护隔离环境,但协作者不直接管理其路径。
分支模型
1.7.0 LTS 发布后三条长期分支:
| 分支 | 用途 | 版本号后缀 |
|---|---|---|
main |
最新稳定发布。当前为 2.7.3 | (无) |
lts/1.7 |
1.7.x 长期维护线,从 1.7.0 发布提交创建(EOL 2027-07-02) | (无) |
develop |
开发集成线。所有非 LTS 改动 PR 到这里 | .dev0(当前目标为 2.8.0.dev0) |
合并方向:
feat/refactor/perf/docs/* ───────→ develop
release/* ───────────────────────→ main + develop
fix/docs/*(1.7 LTS)────────────→ lts/1.7 ──→ develop(适用时 cherry-pick)
fix/*(最新稳定 hotfix)────────→ main ──→ develop(forward merge / cherry-pick)
不允许反向合并。允许的同步方向只有:release/* → main、release/* → develop、main → develop(hotfix forward merge)和 lts/1.7 → develop(适用时 cherry-pick / reimplement)。
启动准则
四条硬规则:
- 需明确指令才 Commit。对话里讨论到"要提交"不算指令,必须出现"请提交 / 请 commit / 请开 PR"这类明确祈使句
- 不在长期分支直接工作。所有非 LTS feat / refactor / perf / 非紧急 fix / docs / chore 都 PR 到
develop;1.7.x 兼容性、安全性、数据同步和关键缺陷修复 PR 到lts/1.7;最新稳定 hotfix 才 PR 到main - 不主动 push。即使刚 commit 完,也等用户说"请推"
- 不提交敏感物与本地产物。不提交 secrets、token、凭据、密钥,也不提交本地运行时产物(
.venv、node_modules、会话/缓存状态);安全漏洞细节按SECURITY.md私下处理,不在公开 commit / PR / issue 中复现
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.
- 2d ago Changed · +11 tokens per session 5898dde9dbbc
- 8d ago First seen · 333 lines · 6,277 tokens per session scan A 16b11da0ce9d
prts-mcp CLAUDE.md is an instructions file published in the GitHub repository 3aKHP/prts-mcp (8 stars, last pushed 2d ago), licensed MIT. It adds 6,288 tokens to every session, about $0.0314 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
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).
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.
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 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).
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.