Borrowing it
Nothing to install: this file belongs to YOLKINS/weeek-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/YOLKINS/weeek-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/YOLKINS/weeek-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/yolkins/weeek-mcp/claude-md)<a href="https://agentmods.dev/instructions/yolkins/weeek-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/yolkins/weeek-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/yolkins/weeek-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/yolkins/weeek-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 | $0.03049 | $0.03049 |
| Opus 5 | $0.01524 | $0.01524 |
| Sonnet 5 | $0.00610 | $0.00610 |
| Haiku 4.5 | $0.00305 | $0.00305 |
Grade C, and why
weeek-mcp CLAUDE.md scanned grade C 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 8d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Do not use destructive shortcuts.** No `rm -rf` of unfamiliar files; no How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — guide for AI coding agents working on weeek-mcp
This file is the entry point for AI agents (Claude Code, Cursor, etc.)
operating on this repository. Humans should read README.md
first; this is the agent-facing contract on top of it.
What this is
A local read-only-by-default MCP server for Weeek,
talking to AI clients over stdio via @modelcontextprotocol/sdk.
The surface is 10 / 15, and both counts are pinned literally. Ten
read tools — ping, weeek_get_me, weeek_list_projects,
weeek_get_project, weeek_list_tasks, weeek_get_task,
weeek_list_members, weeek_list_tags, weeek_list_boards,
weeek_list_board_columns — are what a default install exposes. Five
write tools — weeek_complete_task, weeek_move_task,
weeek_create_task, weeek_update_task, weeek_set_task_mr_link —
carry readOnly: false in the registry and appear only under
READ_ONLY=false, taking tools/list to 15.
The write set is closed. A sixth write tool is a new increment with
its own scope call, not an addition to this one. Adding or removing any
tool means changing a literal count in tests/tools/registry.test.ts
and tests/invariants/tools-list-wire.test.ts (and
tests/helpers/toolNames.ts, the single copy of the names) — in the
same PR. That is deliberate: a structural assertion cannot tell "we
shipped the tools we planned" from "we shipped fewer and the helper list
agrees".
Tech stack pinning
Pinned for a reason. Do not bump any of these without writing the rationale into the bump commit / PR first.
@modelcontextprotocol/sdk—^1.29. Do not jump to a v2 alpha without a dedicated RFC; we depend on the 1.xMcpServer/StdioServerTransportsurface and the 1.xtools/listregistration shape.zod—^3.23.8. Do not upgrade to v4: the SDK turns our zod schemas into every tool'sinputSchemaandoutputSchema, so a zod major is atools/listwire change, not an implementation detail. Re-open when the SDK line itself moves.typescript—^6.0.3. Do not jump to TS 7:typescript-eslint^8.65declarestypescript: >=4.8.4 <6.1.0, so TS 7 takes the linter — and therefore INVARIANT-1's enforcement — out with it.vitest—^4.1. Every coverage floor invitest.config.tsmust stay put: a floor that moves is a decision, never a migration artefact. (v4's v8 provider remaps through the AST, so coverage numbers are not comparable across the v3→v4 boundary.)eslint—^10.7withtypescript-eslint^8.65.no-consolehere is what enforces INVARIANT-1 — verify the rule still fires after any linter bump.@types/node—^25.9. Tracks the newest Node release line, not our floor: the compiler sees APIs Node 20 does not have, so the CI matrix, not the type checker, is what defendsengines.node.- Node —
>=20. CI matrix runs Node 20 + 22.
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.
- 8d ago First seen · 215 lines · 3,049 tokens per session scan C 7c5de50b4594
weeek-mcp CLAUDE.md is an instructions file published in the GitHub repository YOLKINS/weeek-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 3,049 tokens to every session, about $0.0152 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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).
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.