wcgw: Instructions file for Claude Code

CLAUDE.md

wcgw CLAUDE.md is an instructions file for Claude Code from rusiaaman/wcgw. It costs 451 tokens per session, scanned A, original, Apache-2.0.

Project-specific coding instructions for contributing to the wcgw Python repository. They cover strict mypy type checking, the uv package manager, testing commands, and rules for keeping code simple and explicit.

In plain words
What is it for?
Use them when editing wcgw or wcgw_cli, adding dependencies, running tests, checking types, or deciding how to represent states, errors, and contracts.
Why use it?
They make the repository's expectations clear before a developer changes code, reducing type errors and hidden assumptions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is rusiaaman/wcgw's own configuration. It tells Claude Code how to work on wcgw 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 wcgw configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rusiaaman/wcgw. 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/rusiaaman/wcgw/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/rusiaaman/wcgw

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 wcgw CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rusiaaman/wcgw/claude-md"><img src="https://agentmods.dev/badge/instructions/rusiaaman/wcgw/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 451 This file is loaded in full into every session.
When invoked 451 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00451 $0.00451
Opus 5 $0.00226 $0.00226
Sonnet 5 $0.00090 $0.00090
Haiku 4.5 $0.00045 $0.00045

Measured 9d ago against content hash e6177918ce82, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

wcgw 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.

CLAUDE.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Alignment instructions to contribute to this repository

Hard rules

  • Make sure mypy --strict passes for these two folders uv run mypy --strict src/wcgw src/wcgw_cli.
  • Use list directly for typing like list[str] no need to import List. Same thing for tuple, set, etc.
  • No optional parameters in a function with default values. All parameters must be passed by a caller.
  • This library uses uv as package manager. To add a package uv add numpy. To run pytest uv run pytest and so on.

Coding mantras

Reduce states and dependencies between the states

  • Don't introduce any state unless really necessary.
  • If anything can be derived, avoid storing it or passing it.
Python Exception guideline 1
  • Exception thrown inside functions are their hidden extra state which should be avoided.
  • Parse don't validate: avoid throwing validation errors by letting the types avoid bad values to be passed in the first place.

Put burden on type checker not the code reader

  • No hidden contracts and assumptions.
  • Don't assume any relationship between two states unless it's encoded in the type of the state.
  • Any contract should be enforced by the way types are constructed.
  • If it's just not possible due to complexity to type in such a way to avoid hidden contract, add in docstring details.
Python Exception guideline 2
  • When you can't avoid it, instead of enforcing the hidden contract as hard failure during runtime, try to return some sensible value instead. Example In PIL adding boxes outside image bounds don't do anything, but they don't fail either, making it a cleaner experience to deal with edge cases.

  • A functions signature (along with types) should be enough to understand its purpose.

  • This can be achieved by typing the parameters to only take narrow types

Functions should be as pure as possible

  • Avoid mutating mutable input parameters, instead return newly derived values in the output and leave upto the caller to update the state if required.
  • It should be clear from function signature what the function computes, this should also enforce the previous point of not updating mutable input parameters.

Read the full file on GitHub · 42 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. 9d ago First seen · 42 lines · 451 tokens per session scan A e6177918ce82

Subscribe to this mod's changes

wcgw CLAUDE.md is an instructions file published in the GitHub repository rusiaaman/wcgw (674 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 451 tokens to every session, about $0.0023 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 2026-08-30.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens