Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/bromso/metapowers/agents-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/agents-md)<a href="https://agentmods.dev/instructions/bromso/metapowers/agents-md"><img src="https://agentmods.dev/badge/instructions/bromso/metapowers/agents-md.svg" alt="Measured on agentmods" 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 | $0.00988 | $0.00988 |
| Opus 5 | $0.00494 | $0.00494 |
| Sonnet 5 | $0.00198 | $0.00198 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
metapowers AGENTS.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 3d 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 — 89 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. This project provides skills that guide you through proven methodologies across 10 domains.
Available Domains & Skills
Design (/design:*)
Five-phase design thinking process for component design.
/design:empathize <component>— Research user needs and existing patterns/design:define <component>— Create component contract with specs/design:ideate <component>— Explore multiple design approaches/design:prototype <component>— Build the component in Figma via MCP/design:test <component>— Validate against WCAG and component contract
Research (/research:*)
Four-phase Double Diamond methodology for structured discovery.
/research:discover <topic>— Broad research and data gathering/research:define <topic>— Synthesize into problem statement/research:design <topic>— Generate and evaluate solutions/research:deliver <topic>— Validate and produce recommendations
Development (/development:*)
Process-oriented software development workflow.
/development:plan <feature>— Break feature into implementation tasks/development:build <feature>— Execute plan with TDD discipline/development:test <feature>— Write tests and validate coverage/development:debug <issue>— Systematic root cause investigation/development:review <feature>— Pre-merge code review/development:ship <feature>— Finish branch (merge/PR/cleanup)
Marketing (/marketing:*)
RACE Framework marketing process.
- Strategy phase: customer-research, competitor-profiling, pricing-strategy, product-marketing-context, launch-strategy
- Reach phase: content-strategy, seo-audit, programmatic-seo, ai-seo, social-content, site-architecture, directory-submissions, competitor-alternatives
- Act, Convert, Engage phases with additional skills
Branding (/branding:*)
Five-phase brand creation with compliance auditing.
/branding:discover <brand>— Research market and audience/branding:strategy <brand>— Define positioning and values/branding:verbal <brand>— Develop voice, tone, messaging/branding:visual <brand>— Define colors, typography, logo usage/branding:guidelines <brand>— Package into brand manual/branding:audit <content>— Score brand compliance (Kapferer Brand Prism)
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.
- 3d ago First seen · 89 lines · 988 tokens per session scan A db1e2e77b1b1
metapowers AGENTS.md is an instructions file published in the GitHub repository bromso/metapowers (1 stars, last pushed 4mo ago), licensed MIT. It adds 988 tokens to every session, about $0.0049 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.
Other instructions, from other repositories
token-saver CLAUDE.md
Instructions for ppgranger/token-saver, covering token-saver plugin, how it works and important rules.
auto-pilot AGENTS.md
AGENTS.md instructions for IronRookieCoder/auto-pilot, covering 项目概况 and 同步更新规则.
auto-pilot CLAUDE.md
Claude Code instructions for IronRookieCoder/auto-pilot, covering 项目概况 and 同步更新规则.
Starlight-Intelligence-System AGENTS.md
AGENTS.md instructions for frankxai/Starlight-Intelligence-System, covering frank dna, standards, multi-agent systems & agent harnesses, 1. what makes sis unique and 2. the swarm harness process.
Starlight-Intelligence-System GEMINI.md
Gemini CLI instructions for frankxai/Starlight-Intelligence-System, covering starlight central command: starlight-intelligence-system and core mandates.
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).