wassden-mcp: Instructions file for Claude Code

CLAUDE.md

wassden-mcp CLAUDE.md is an instructions file for Claude Code from tokusumi/wassden-mcp. It costs 2,811 tokens per session, scanned B, original, MIT.

A set of Claude Code instructions for the wassden-mcp project, including commands for formatting, linting, type checking, testing, and command-line verification. Claude Code is a coding assistant that follows project instructions while editing code.

In plain words
What is it for?
Maintaining the wassden-mcp Python project with Ruff formatting and linting, mypy type checks, pytest tests, coverage checks, and development or CI verification.
Why use it?
It prevents unfinished changes from being treated as complete when checks fail. The project uses one command to run its required checks and separate commands for development and CI.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is tokusumi/wassden-mcp's own configuration. It tells Claude Code how to work on wassden-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything wassden-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tokusumi/wassden-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.

Copy the file
curl -O https://raw.githubusercontent.com/tokusumi/wassden-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/tokusumi/wassden-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for wassden-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tokusumi/wassden-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/tokusumi/wassden-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tokusumi/wassden-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tokusumi/wassden-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.

agentmods 80×15 button for wassden-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tokusumi/wassden-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tokusumi/wassden-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,811 This file is loaded in full into every session.
When invoked 2,811 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02811 $0.02811
Opus 5 $0.01406 $0.01406
Sonnet 5 $0.00562 $0.00562
Haiku 4.5 $0.00281 $0.00281

Measured 10d ago against content hash b2df8ff2e9d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

wassden-mcp CLAUDE.md scanned grade B 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 10d 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- All code must pass linting without warnings (ruff with extensive rule set)
CLAUDE.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Instructions

Linter and Test Policy

  • NEVER ignore linter errors - All linting issues must be fixed
  • NEVER ignore test failures - All tests must pass
  • NEVER disable or skip linter rules without explicit user approval
  • NEVER disable or skip tests without explicit user approval
  • Always run make check after code changes
  • If linter/test commands fail, the task is NOT complete

Commands

Development Commands

  • All checks: make check - Runs format, lint, typecheck, test, and CLI verification for dev mode
  • CI dev mode: make ci - Runs all checks for dev mode in CI (format --check, with dev dependencies)
  • CI core mode: make ci-core - Runs checks for core functionality only (no dev dependencies)
  • Format code: make format - Format code with ruff
  • Lint code: make lint - Lint code with ruff check
  • Type check: make typecheck - Type check with mypy
  • Run all tests: make test - Run all tests with coverage using pytest
  • Run core tests: make test-core - Run core tests only (excludes dev-marked tests)
  • Run dev tests: make test-dev - Run dev tests only (requires dev dependencies)
  • Run AST tests: make test-ast - Run AST validation tests only (172 tests)
  • Validate examples: make validate-examples - Run integration tests for spec examples in both Japanese and English
  • Help: make help - Show all available make commands

CLI Testing Commands

  • Local CLI: uv run wassden --help - Show available CLI commands
  • Test functionality: uv run wassden prompt-requirements --userInput "test" - Test CLI functionality
  • Start MCP server: uv run wassden start-mcp-server --transport stdio - Start MCP server locally

Multi-Language Support Commands

  • Japanese mode: Add --language ja to any command for Japanese output
  • English mode: Add --language en to any command for English output
  • Auto-detection: Omit --language to let the system automatically detect language
  • Examples:
    • uv run wassden prompt-requirements --userInput "test" --language en - Force English
    • uv run wassden prompt-requirements --userInput "テストプロジェクト" - Auto-detects Japanese
    • uv run wassden validate-requirements --requirementsPath specs/requirements.md - Detects from file content
  • MCP Server: All MCP tools automatically detect language from content without parameters
  • Default Fallback: Defaults to Japanese (ja) when detection is uncertain

Read the full file on GitHub · 216 lines

Changes

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.

  1. 10d ago First seen · 216 lines · 2,811 tokens per session scan B b2df8ff2e9d5

Subscribe to this mod's changes

wassden-mcp CLAUDE.md is an instructions file published in the GitHub repository tokusumi/wassden-mcp (1 stars, last pushed 9mo ago), licensed MIT. It adds 2,811 tokens to every session, about $0.0141 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.