wmux: Instructions file for Claude Code

CLAUDE.md

wmux CLAUDE.md is an instructions file for Claude Code from openwong2kim/wmux. It costs 728 tokens per session, scanned A, original, MIT.

Repository-specific instructions for the openwong2kim/wmux project. They define language rules, how different tasks should be routed, and conventions for design, versions, and releases.

In plain words
What is it for?
Use them when working on wmux to choose the right task workflow, write repository artifacts in English, and follow its design and release conventions.
Why use it?
They give coding agents consistent project context so their changes and responses follow the repository owner's decisions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is openwong2kim/wmux's own configuration. It tells Claude Code how to work on wmux 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 wmux configures →

Reuse

Borrowing it

Nothing to install: this file belongs to openwong2kim/wmux. 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/openwong2kim/wmux/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/openwong2kim/wmux

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 wmux CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/openwong2kim/wmux/claude-md.svg)](https://agentmods.dev/instructions/openwong2kim/wmux/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/openwong2kim/wmux/claude-md"><img src="https://agentmods.dev/badge/instructions/openwong2kim/wmux/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 728 This file is loaded in full into every session.
When invoked 728 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 $0.00728 $0.00728
Opus 5 $0.00364 $0.00364
Sonnet 5 $0.00146 $0.00146
Haiku 4.5 $0.00073 $0.00073

Measured 7d ago against content hash ff9b4be84216, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

wmux 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 7d 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 · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Language (owner decision, 2026-07-20)

This is a public open-source repo: all repo artifacts are English, always — commit messages, CHANGELOG entries, PR titles/bodies, code comments, and docs. This OVERRIDES the global ~/.claude/CLAUDE.md Korean-commit/comment convention for this repository. New code comments are written in English; do not mass-rewrite existing Korean comments (respect the "don't improve adjacent code" rule), just stop adding new Korean ones. Chat/reports with the owner may stay Korean.

Skill routing

When the user's request matches an available skill, ALWAYS invoke it using the Skill tool as your FIRST action. Do NOT answer directly, do NOT use other tools first. The skill has specialized workflows that produce better results than ad-hoc answers.

Key routing rules:

  • Product ideas, "is this worth building", brainstorming → invoke office-hours
  • Bugs, errors, "why is this broken", 500 errors → invoke investigate
  • Ship, deploy, push, create PR → invoke ship
  • QA, test the site, find bugs → invoke qa
  • Code review, check my diff → invoke review
  • Update docs after shipping → invoke document-release
  • Weekly retro → invoke retro
  • Design system, brand → invoke design-consultation
  • Visual audit, design polish → invoke design-review
  • Architecture review → invoke plan-eng-review

Design System

Always read DESIGN.md before making any visual or UI decisions. All chrome/layout contracts, color grammar (amber = alive + focus, 5±2 points per screen, no washes), typography, and aesthetic direction are defined there. Do not deviate without explicit user approval. In QA/design-review mode, flag any code that doesn't match DESIGN.md.

Versioning & release (owner decision, 2026-07-05)

  • PRs never bump the version. package.json stays at the last released version on every feature branch. Do NOT let /ship (or any workflow) bump MAJOR/MINOR/PATCH, claim version slots, or prefix PR titles with vX.Y.Z.
  • CHANGELOG: a PR does not edit CHANGELOG.md. It adds one fragment, changelog.d/<pr-number>.md, holding its user-facing entries under plain Keep a Changelog headings. Separate files cannot conflict — editing the one shared insertion point meant every merge left every other open PR dirty. See changelog.d/README.md.
  • Release = explicit user action: run node scripts/collect-changelog.mjs to fold the fragments into CHANGELOG.md, bump package.json version, rename [Unreleased][X.Y.Z] — YYYY-MM-DD, run node scripts/gen-api-reference.mjs (the generated header bakes the version — the CI drift guard enforces this), commit chore(release), then push a v* tag (installer builds hang off the tag).
  • Consequence accepted with this decision: same-version dev builds are not distinguishable by semver, so the stale-daemon auto-replacement triggers only on (a) pre-B′ daemons (missing version field) and (b) release-to- release upgrades and (c) CHANNELS_EPOCH bumps — not on every dev rebuild.

Read the full file on GitHub · 57 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. 7d ago First seen · 57 lines · 728 tokens per session scan A ff9b4be84216

Subscribe to this mod's changes

wmux CLAUDE.md is an instructions file published in the GitHub repository openwong2kim/wmux (366 stars, last pushed yesterday), licensed MIT. It adds 728 tokens to every session, about $0.0036 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