ultrapowers: Instructions file for Claude Code

CLAUDE.md

ultrapowers CLAUDE.md is an instructions file for Claude Code from 7xuanlu/ultrapowers. It costs 512 tokens per session, scanned A, original, MIT.

Project instructions for UltraPowers, a coding workflow whose engine and command coordinate development tasks. They describe its required workflow, asynchronous JavaScript structure, checks, and model-routing rules.

In plain words
What is it for?
Use them when developing UltraPowers, especially when editing the workflow coordinator, running checks, creating feature branches, or following its test-driven process.
Why use it?
They give contributors the project-specific rules needed to modify the workflow engine without breaking its checks or bypassing its intended process.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is 7xuanlu/ultrapowers's own configuration. It tells Claude Code how to work on ultrapowers 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 ultrapowers configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 7xuanlu/ultrapowers. 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/7xuanlu/ultrapowers/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/7xuanlu/ultrapowers

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 ultrapowers CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/7xuanlu/ultrapowers/claude-md.svg)](https://agentmods.dev/instructions/7xuanlu/ultrapowers/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/7xuanlu/ultrapowers/claude-md"><img src="https://agentmods.dev/badge/instructions/7xuanlu/ultrapowers/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 512 This file is loaded in full into every session.
When invoked 512 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 $0.00512 $0.00512
Opus 5 $0.00256 $0.00256
Sonnet 5 $0.00102 $0.00102
Haiku 4.5 $0.00051 $0.00051

Measured 8d ago against content hash 866c0294c9fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ultrapowers 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 8d 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 · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@AGENTS.md

CLAUDE.md, Claude Code specifics for ultrapowers (shared principles are in AGENTS.md above)

Workflow

This repo's own development uses Superpowers skills (this is the dog-food): brainstorming → writing-plans → subagent-driven execution under strict TDD → requesting-code-review → finishing-a-development-branch. Worktree per feature (feature/<kebab>), PR before merge, never push to main directly. The skills own TDD, worktree, and model-routing rules, don't restate them.

The engine and command are the product, treat them as such

  • workflow/ultrapowers-development.js is the deterministic coordinator. It is loaded by the Workflow tool with top-level await/return and a single export, that's why npm run check compiles it as an async IIFE instead of node --check. Don't add a second export shape without updating tests/check-engine.sh.
  • skills/workflows-driven-development/SKILL.md is user-only (disable-model-invocation: true) and spends real tokens. It dispatches the engine by scriptPath (the engine is not registered by name in ~/.claude/workflows/, so it stays out of the slash list and the model can't dispatch it directly, bypassing the gates); do not re-implement the loop inside the skill. (Ships as a skills/ skill, not a commands/ file, so the slash picker shows the short name workflows-driven-development (ultrapowers) instead of the full /ultrapowers:workflows-driven-development path.)

After any edit

Run npm run check. For engine-behavior changes, run npm run test:rewitness (spends tokens) and confirm the vacuous test is CAUGHT and the good test passes. Don't claim an engine change works without one of these.

Distribution

The repo is a self-contained plugin marketplace: .claude-plugin/plugin.json + .claude-plugin/marketplace.json (source: "./"). It is also listed in the author's aggregator marketplace (7xuanlu/claude-plugins). Keep version in sync across plugin.json, marketplace.json, and package.json when you cut a release; tag it.

Read the full file on GitHub · 37 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. 8d ago First seen · 37 lines · 512 tokens per session scan A 866c0294c9fb

Subscribe to this mod's changes

ultrapowers CLAUDE.md is an instructions file published in the GitHub repository 7xuanlu/ultrapowers (10 stars, last pushed 2mo ago), licensed MIT. It adds 512 tokens to every session, about $0.0026 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 2026-08-31.

Related

Other instructions, from other repositories

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

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

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

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

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