O-ALL-WANT: Instructions file for Claude Code

CLAUDE.md

O-ALL-WANT CLAUDE.md is an instructions file for Claude Code from lihowfun/O-ALL-WANT. It costs 1,507 tokens per session, scanned A, original, MIT.

Project instructions for OAW, a command router that directs an AI coding agent to the right workflow and project reference files.

In plain words
What is it for?
They help route operational, wiki, and other project tasks, while keeping behavior rules in CLAUDE.md and project facts in AI_CONTEXT.md.
Why use it?
They prevent the agent from loading every document at startup and define which file is authoritative when instructions overlap.

Instructions file for Claude Code

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

This is lihowfun/O-ALL-WANT's own configuration. It tells Claude Code how to work on O-ALL-WANT 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 O-ALL-WANT configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lihowfun/O-ALL-WANT. 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/lihowfun/O-ALL-WANT/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/lihowfun/O-ALL-WANT

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 O-ALL-WANT CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lihowfun/o-all-want/claude-md/github.svg)](https://agentmods.dev/instructions/lihowfun/o-all-want/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lihowfun/o-all-want/claude-md"><img src="https://agentmods.dev/badge/instructions/lihowfun/o-all-want/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 O-ALL-WANT CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lihowfun/o-all-want/claude-md"><img src="https://agentmods.dev/badge/instructions/lihowfun/o-all-want/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,507 This file is loaded in full into every session.
When invoked 1,507 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 $0.01507 $0.01507
Opus 5 $0.00754 $0.00754
Sonnet 5 $0.00301 $0.00301
Haiku 4.5 $0.00151 $0.00151

Measured 10d ago against content hash 59bd6fcb4208, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

O-ALL-WANT 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 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.

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 · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OAW — Master Router

This repo uses its own harness to manage itself. Meta, but effective.

Router Contract

  • CLAUDE.md is the only startup router
  • AI_CONTEXT.md stores project facts, not a second rulebook
  • If the two overlap, use CLAUDE.md for behavior and AI_CONTEXT.md for project-specific facts and commands

Response Language

  • 繁體中文 is the primary response language
  • Professional terms keep English (branch, commit, deployment, harness, router, skill, etc.)

Session Startup (Read On Demand — NOT Everything)

After opening this file, always read:

  1. AI_CONTEXT.md — architecture, baselines, commands, tech stack
  2. VERSION.json → only check version + do_not_rerun fields

Route by lane (based on the current task):

Lane Use When Read First Fallback
Operational Current state, release status, branch scope, experiment execution ROADMAP.md first 60 lines + .agents/memory.md last 5 entries templates/docs/knowledge/Experiment_Findings.md
Wiki Stable concepts, background knowledge, reusable domain facts templates/docs/knowledge/index.md + relevant topic page(s) templates/docs/raw/ relevant sources
Execution Repeating workflows and SOPs Matching file in templates/.agents/skills/ Operational lane docs only if the skill asks for them
Debug Reproducing failures and workarounds templates/docs/knowledge/Known_Limitations.md .agents/memory.md last 5 entries

Skills-First Principle:

  • If templates/.agents/skills/ has a matching skill (e.g., /benchmark, /debug-pipeline, /wiki-refresh), follow the skill workflow first
  • Skills still obey this file's lazy-read protocol
  • Only go ad-hoc when no matching skill exists
  • If a maintenance step can be done by context_hub.py or wiki_sync.py, prefer the script over repeated prose instructions

⚠️ FORBIDDEN: Reading all .md files at session start. Understand the task first, then read on demand. ⚠️ FORBIDDEN: Re-running experiments listed in VERSION.json do_not_rerun. ⚠️ FORBIDDEN: Treating docs/raw/ as startup-default context. Raw notes are fallback-only.

Read the full file on GitHub · 129 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 · 129 lines · 1,507 tokens per session scan A 59bd6fcb4208

Subscribe to this mod's changes

O-ALL-WANT CLAUDE.md is an instructions file published in the GitHub repository lihowfun/O-ALL-WANT (18 stars, last pushed 4mo ago), licensed MIT. It adds 1,507 tokens to every session, about $0.0075 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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens