Borrowing it
Nothing to install: this file belongs to bromso/metapowers. 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/bromso/metapowers/main/CLAUDE.mdgit clone --depth 1 https://github.com/bromso/metapowersWrote 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/bromso/metapowers/claude-md)<a href="https://agentmods.dev/instructions/bromso/metapowers/claude-md"><img src="https://agentmods.dev/badge/instructions/bromso/metapowers/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.
<a href="https://agentmods.dev/instructions/bromso/metapowers/claude-md"><img src="https://agentmods.dev/badge/instructions/bromso/metapowers/claude-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 | $0.01464 | $0.01464 |
| Opus 5.5 | $0.00586 | $0.00586 |
| Sonnet 5.5 | $0.00293 | $0.00293 |
| Haiku 4.5 | $0.00146 | $0.00146 |
Grade A, and why
metapowers 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metapowers
Structured, repeatable workflows for digital production domains. 283 skills across 16 plugins.
Architecture
- Monorepo: Bun + Turborepo workspaces
- Plugins (
plugins/): Each domain is a plugin with SKILL.md files, hooks, and shared resources - Packages (
packages/): CLI (create-metapowers), skill-validator, plugin-tools, figma-mcp - Evals (
plugins/<domain>/evals/<skill>/):claude plugin evalsuites, run withbun run evals(scripts/run-evals.sh) - Docs (
apps/docs/): Fumadocs + Next.js static site deployed to GitHub Pages
Plugin Structure
Every plugin follows this pattern:
plugins/<domain>/
├── .claude-plugin/plugin.json # Plugin manifest
├── hooks/hooks.json # Quality gate hooks
├── shared/ # Templates and reference docs
└── skills/<skill-name>/SKILL.md # One SKILL.md per skill
SKILL.md Format
---
name: <skill-name> # must equal the directory name
description: <Verb-first sentence>. Use when <user's situation, ≥6 words>. Not for <x>; see /<plugin>:<skill>. # 120–400 chars; "Not for" optional
argument-hint: "<arg>" # when the skill takes an argument
---
# Skill Name
What the skill does with "$ARGUMENTS" placeholder.
## Prerequisites
What must exist before running (or "None").
## Process
Numbered steps with clear instructions.
## Output
Where the artifact is written and what to present.
Conventions
- Descriptions start with a verb: "Create", "Analyze", "Review" — enforced by skill-validator
- Artifacts: All stored in
.metapowers/<domain>/<project>/with numbered prefixes (01-, 02-, etc.) - Commits: Conventional commits (
feat(domain):,fix(docs):,docs:,ci:) - Formatting: Biome for linting and formatting (
bun run check,bun run format) - Testing: Vitest for packages (
bun run test) - Skill validation:
bun run lint:skillsvalidates all 283 SKILL.md files
Commands
bun run build # Build all packages
bun run test # Run tests
bun run lint:skills # Validate all SKILL.md files
bun run check # Biome lint check
bun run format # Biome auto-format
bun run changeset # Create a changeset for npm release
claude plugin validate . --strict # Validate plugin manifests
bun run check:plugins # phase-deps, hooks, counts (plugin-tools), plus the
# apps/docs data and skill-page checks below
bun run evals --dry # List eval cases; fail if a prompt names its skill (free)
bun run evals [plugin…] # Run claude plugin eval per plugin — spends Claude credits,
# capped per plugin by EVALS_MAX_COST_USD (default 10)
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.
- 2d ago Changed · +1 lines · +80 tokens per session 417e146b2122
- 3d ago Changed · +29 lines · +635 tokens per session c11322ac50c3
- 1mo ago First seen · 89 lines · 749 tokens per session scan A f2a145800c3d
metapowers CLAUDE.md is an instructions file published in the GitHub repository bromso/metapowers (2 stars, last pushed 3d ago), licensed MIT. It adds 1,464 tokens to every session, about $0.0059 per session on Opus 5.5. 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.
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).
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.