Borrowing it
Nothing to install: this file belongs to congmnguyen/claude-code-wsl2-setup. 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/congmnguyen/claude-code-wsl2-setup/main/AGENTS.mdgit clone --depth 1 https://github.com/congmnguyen/claude-code-wsl2-setupWrote 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/congmnguyen/claude-code-wsl2-setup/agents-md)<a href="https://agentmods.dev/instructions/congmnguyen/claude-code-wsl2-setup/agents-md"><img src="https://agentmods.dev/badge/instructions/congmnguyen/claude-code-wsl2-setup/agents-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/congmnguyen/claude-code-wsl2-setup/agents-md"><img src="https://agentmods.dev/badge/instructions/congmnguyen/claude-code-wsl2-setup/agents-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 | $0.00987 | $0.00987 |
| Opus 5.5 | $0.00395 | $0.00395 |
| Sonnet 5.5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade B, and why
claude-code-wsl2-setup AGENTS.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 5d 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`. This is a copy
100% identical to superpowers AGENTS.md — 140 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository instructions
Purpose
- This repository preserves the maintainer's previous Claude Code setup for WSL2 + Windows Terminal. The maintainer now uses Ubuntu + Ghostty and no longer tests WSL2 daily. It has no build system or package manager; lightweight checks live in
tests/andscripts/; deliverables are Markdown docs, shell scripts, and config snippets. - The current machine's
~/.claude/is not the source of truth for the preserved WSL2 setup. Do not synchronize it with this repository or install WSL2 components on Ubuntu as part of documentation maintenance. - Root
*.mdfiles document setup components. Keep optional components clearly labeled. Agents, skills, and copies of official plugins were removed; do not add them back. Do not present the repository as a tested Ubuntu setup. - The separate
codex-wsl2-setuprepository no longer exists. The Codex notification and terminal-title notes stay here because they reuse this repository's scripts; Codex delegation was removed; recover it from git history if needed. 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-cliprocess. The upstream installer offers to add exactly those, so the guide installs a pinned release instead. Seeimage-paste.md. bin/claude-notifypasses text to PowerShell base64-encoded. Never interpolate text into a PowerShell string literal: PowerShell also ends single-quoted strings at‘ ’ ‚ ‛, and Codex replies are untrusted model output.- There are no
PreToolUseorPostToolUsehooks 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 namedtoken_manager.py, and a Ruff autofix hook silently deleted imports out of files Claude had just written. Prefer exact-matchpermissions.denyrules, which cannot misfire. Seepruned-notes.md. Notificationhooks remain part of the documented WSL2 setup. Seeclaude-notify.md.- Browser automation is no longer documented here;
playwright-cli.mdand the Playwright section ofmcp-setup.mdwere removed.mcp-setup.mdnow covers only the project-scoped Figma Desktop MCP. Recover the old pages from git history rather than rewriting them. ~/.claude/keybindings.jsonmust be an object containing abindingsarray; a bare array silently fails.- In
~/.claude/settings.json, merge settings instead of replacing the file. Useattribution, not deprecated or invented attribution keys. Seesettings.md. - Normalize
assets/preview-*.pngto a 1220x788#0d1117canvas and render previews at width 720 inREADME.md.tests/test_docs.pyenforces both. - Keep
scripts/doctor.shread-only: no file edits, service changes, or notifications. Its output goes into public issues, so keep home paths and Windows user names abbreviated.
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.
- 5d ago Changed · +5 tokens per session 3e23ba9e0663
- 13d ago Changed · +3 lines · +217 tokens per session bb4dd5547b3c
- 1mo ago Changed · +31 lines · +759 tokens per session scan A → B 1e75d5e88099
- 1mo ago First seen · 2 lines · 6 tokens per session scan A e9a7ddcee534
claude-code-wsl2-setup AGENTS.md is an instructions file published in the GitHub repository congmnguyen/claude-code-wsl2-setup (55 stars, last pushed 6d ago), licensed MIT. It adds 987 tokens to every session, about $0.0039 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 100% identical to superpowers AGENTS.md, differing in 140 lines, and is treated as a copy.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.