agentmods.dev

claude-code-wsl2-setup CLAUDE.md

claude-code-wsl2-setup CLAUDE.md is an instructions file for Claude Code from congmnguyen/claude-code-wsl2-setup. It costs 686 tokens per session, scanned B, original, MIT.

Repository instructions for documenting and maintaining a Claude Code setup on Windows Subsystem for Linux 2, the Windows feature that runs a Linux environment. They describe the live configuration, project files, and setup constraints.

In plain words
What is it for?
Use them when changing, verifying, or documenting this WSL2 Claude Code setup, including its skills, agents, hooks, scripts, and configuration.
Why use it?
They clarify which files are authoritative and which setup changes are unsafe or out of scope. They also prevent documentation from drifting away from the active machine.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

not rated 50 +1 5d ago B scan 686 tokens original MIT
View the source file congmnguyen/claude-code-wsl2-setup
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/congmnguyen/claude-code-wsl2-setup/claude-md
Clone the repo
git clone --depth 1 https://github.com/congmnguyen/claude-code-wsl2-setup

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 claude-code-wsl2-setup CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/congmnguyen/claude-code-wsl2-setup/claude-md.svg)](https://agentmods.dev/instructions/congmnguyen/claude-code-wsl2-setup/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/congmnguyen/claude-code-wsl2-setup/claude-md"><img src="https://agentmods.dev/badge/instructions/congmnguyen/claude-code-wsl2-setup/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 686 This file is loaded in full into every session.
When invoked 686 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
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 $0.00686 $0.00686
Opus 5 $0.00343 $0.00343
Sonnet 5 $0.00137 $0.00137
Haiku 4.5 $0.00069 $0.00069

Measured 6d ago against content hash 0713bbf39b57, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

claude-code-wsl2-setup 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 6d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- In `~/.claude/settings.json`, merge settings instead of replacing the file. Use `attribution`, not deprecated or invented attribution keys. See `settings.md`.
CLAUDE.md · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Purpose

  • This repository documents the active Claude Code setup on this WSL2 machine. It has no build system, test suite, or package manager; deliverables are Markdown docs, shell scripts, and config snippets.
  • Treat the live files under ~/.claude/ as runtime truth and this repository as their documented, version-controlled counterpart. When changing an active setup component, inspect both and keep them synchronized.
  • Root *.md files document setup components; agents/, skills/, and hooks/ contain installable artifacts. Do not promote optional or legacy components in README.md unless the live machine uses them.
  • Codex skills and setup live in the separate congmnguyen/codex-wsl2-setup repository. Do not restore a Codex backup tree here.

Non-obvious constraints

  • Run screenshot paste only through the systemd user service; do not add shell or Claude hooks that can race or stop the supervised wsl-screenshot-cli process. See image-paste.md.
  • There are no PreToolUse or PostToolUse hooks in this setup, and none should be added. Every one tried here matched on patterns, and a pattern that is wrong in either direction is worse than nothing: a truncating hook destroyed the middle of failing test output, a credential-blocking hook rejected ordinary source files named token_manager.py, and a Ruff autofix hook silently deleted imports out of files Claude had just written. Prefer exact-match permissions.deny rules, which cannot misfire. See "Pruned notes" in README.md.
  • Notification hooks are fine and still in use — they react to events instead of judging tool input, so they have nothing to get wrong. See claude-notify.md.
  • Browser automation is no longer documented here; playwright-cli.md and the Playwright section of mcp-setup.md were removed. mcp-setup.md now covers only the project-scoped Figma Desktop MCP. Recover the old pages from git history rather than rewriting them.
  • ~/.claude/keybindings.json must be an object containing a bindings array; a bare array silently fails.
  • In ~/.claude/settings.json, merge settings instead of replacing the file. Use attribution, not deprecated or invented attribution keys. See settings.md.
  • Normalize assets/preview-*.png to a 1220x788 #0d1117 canvas and render previews at width 720 in README.md.

Read the full file on GitHub · 32 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. 6d ago First seen · 32 lines · 686 tokens per session scan B 0713bbf39b57

Subscribe to this mod's changes

claude-code-wsl2-setup CLAUDE.md is an instructions file published in the GitHub repository congmnguyen/claude-code-wsl2-setup (50 stars, last pushed 5d ago), licensed MIT. It adds 686 tokens to every session, about $0.0034 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

anthropicclaudeclaude-codedeveloper-toolswindows-terminalwsl2
Related

Other instructions, from other repositories

personal-os-setup CLAUDE.md

Claude Code instructions for AmineDjeghri/personal-os-setup, covering claude.md, what this is, safety: always confirm before system-mutating actions, commands and architecture.

AmineDjeghri/personal-os-setup · 2,938 tokens

podman-mcp CLAUDE.md

Claude Code instructions for sandraschi/podman-mcp, covering podman-mcp — claude / agent context, do, don't and commands.

sandraschi/podman-mcp · 156 tokens

podman-mcp AGENTS.md

AGENTS.md instructions for sandraschi/podman-mcp, covering podman-mcp — agents.md, quick reference, tool pattern, key files and add a tool.

sandraschi/podman-mcp · 771 tokens

wigi-llm AGENTS.md

Instructions for Platano78/wigi-llm, covering wigi-llm — agents.md (router / the map), what this is, areas (route by task — load inputs, skip the rest), verbs and naming conventions (locate, don't grep).

Platano78/wigi-llm · 839 tokens

wigi-llm CLAUDE.md

Instructions for Platano78/wigi-llm, covering wigi-llm, what this is, key files, architecture and rules.

Platano78/wigi-llm · 747 tokens

claude-code-notifire CLAUDE.md

Claude Code instructions for faustoFF/claude-code-notifire, covering claude.md, language, what this is, commands and architecture.

faustoFF/claude-code-notifire · 931 tokens