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 rules/bromso/metapowers/cursorrulesgit clone --depth 1 https://github.com/bromso/metapowersWhat 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 | $0.00300 | $0.00300 |
| Opus 5 | $0.00150 | $0.00150 |
| Sonnet 5 | $0.00060 | $0.00060 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
cursorrules 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 yesterday.
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.
What it actually says
Metapowers
Structured, repeatable workflows for digital production domains. This project provides skills across 10 domains: Design, Research, Development, Marketing, Branding, Accessibility, Project Management, Coaching, Leadership, and Legal.
How to Use
Each domain has skills in plugins/<domain>/skills/<skill-name>/SKILL.md. Read the SKILL.md file for the domain you need and follow its process.
Key Domains
- Design — Design thinking: empathize → define → ideate → prototype → test
- Research — Double Diamond: discover → define → design → deliver
- Development — Plan → build → test → debug → review → ship
- Marketing — RACE: strategy → reach → act → convert → engage
- Branding — Discover → strategy → verbal → visual → guidelines + audit
- Accessibility — WCAG-EM: scope → evaluate → report → remediate → retest
- Coaching — Expert feedback: ux, code, copy, a11y, strategy
- Leadership — Assess → vision → build → develop → sustain + 7 tools
Artifacts
All outputs are stored in .metapowers/<domain>/<project>/ as numbered markdown files.
Skills Location
Skills are in plugins/<domain>/skills/<skill-name>/SKILL.md. Each contains structured instructions with prerequisites, process steps, and output format.
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.
- yesterday First seen · 27 lines · 300 tokens per session scan A 6cb631523767
cursorrules is a cursor rule published in the GitHub repository bromso/metapowers (1 stars, last pushed 4mo ago), licensed MIT. It adds 300 tokens to every session, about $0.0015 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 cursor rules, from other repositories
cursorrules
Cursor rule "cursorrules" from Wolfe-Jam/faf-cli, covering faf:start, .cursorrules, authored from project.faf — faf-cli v6, stack and faf:end.
aria-core
ARIA core — five-phase knowledge lifecycle (capture → govern → promote → apply → refresh), knowledge taxonomy, ideas backlog routing, project tier. Consulted whenever ARIA behavior is in question.
awp-auto
When the user says awp auto, awp auto strict, or runs the Kanban Auto command — enforce the per-task loop (not batch delivery).
test-plan
Plan Katalon True Platform/TestOps testing for a release, sprint, or feature. Use when you need to translate quality goals into scope, prioritize testing by requirement coverage and risk, decide what to test first, or build the executable plan structure (folders, suites, and sprint/release association) that stands in…
cli-forge-schema
Generate GitHub-compatible Mermaid diagrams — auto-picks diagram type, splits complex ones, converts tables/kanban/PERT.
STAGE_S5_TEST_POINTS
AIDocxWorkFlow Stage 5 — 测试点生成（独立阶段）.