Borrowing it
Nothing to install: this file belongs to shiyi-0x7f/zlib-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/shiyi-0x7f/zlib-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/shiyi-0x7f/zlib-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/shiyi-0x7f/zlib-mcp/claude-md)<a href="https://agentmods.dev/instructions/shiyi-0x7f/zlib-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shiyi-0x7f/zlib-mcp/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/shiyi-0x7f/zlib-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shiyi-0x7f/zlib-mcp/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 | $0.00702 | $0.00702 |
| Opus 5 | $0.00351 | $0.00351 |
| Sonnet 5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
zlib-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 9d 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 — zlib-mcp
全局约定见
D:\ClaudeData\.claude\CLAUDE.md，本文件只写本项目特有的硬约束。
项目性质
分发给他人使用的 stdio MCP server，npm 包名 zlib-mcp，通过 npx zlib-mcp 运行。零服务端、零鉴权，每个使用者用自己的 z-library 账号。
需求 / 架构 / 上游契约来源等内部文档在本机 dev_docs/（不入库，见 .gitignore）。
铁律
- stdout 是 MCP 协议通道。任何
console.log/process.stdout.write都会破坏帧。日志一律走src/logger.ts（stderr），由 eslint 的no-console强制（仅src/logger.ts豁免）。 - password 与完整 remix_key 不进返回值、日志、错误消息。
remix_key必须出现时用maskKey()脱敏。password 也永不落盘。 - 搜索结果必须过
src/shaping.ts的白名单裁剪，不透传上游原始 JSON。上游多返回的字段一律丢弃 —— 宁可少字段，不可灌爆上下文。 - 文件名与落盘路径必须过
src/safe-path.ts的三道防线。上游Content-Disposition、用户入参、URL 末段都不可信。 - 不在启动时登录。凭证懒解析，失败表现为可操作的工具错误，不是进程崩溃。
- 不注册未授权的能力。
zlib_download只在配了ZLIB_DOWNLOAD_DIR时才注册。 - 测试不打真实上游。
ZlibraryClient与streamToDisk都接受fetchImpl注入。 - 中文查询必须是 UTF-8 百分号编码，且
Content-Type显式带charset=UTF-8。请求体一律用URLSearchParams构造（它本身就按 UTF-8 编码），禁手拼 query string；charset 不声明时上游可能按 latin-1 / GBK 还原，中文书名直接搜不到。有测试锁死。
命令
pnpm check # 门禁：format:check → lint → typecheck → test（CI 跑同一条）
pnpm build # tsc -p tsconfig.build.json → dist/
pnpm test # vitest run
发布
v* tag 触发 .github/workflows/release.yml。tag 必须与 package.json 的 version 一致，否则 workflow 直接失败。上游域名默认值变更算 patch，工具入参不兼容变更算 major。
边界
本项目零服务端依赖：不 import 任何自有项目、不调任何自有服务、不碰任何共享账号池。上游只有 z-library 本身。
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.
- 9d ago First seen · 37 lines · 702 tokens per session scan A b2e65326e0f7
zlib-mcp CLAUDE.md is an instructions file published in the GitHub repository shiyi-0x7f/zlib-mcp (5 stars, last pushed 21d ago), licensed MIT. It adds 702 tokens to every session, about $0.0035 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
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).
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.
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.