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 skills add bromso/metapowers --skill evaluategit 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/skills/bromso/metapowers/evaluate)<a href="https://agentmods.dev/skills/bromso/metapowers/evaluate"><img src="https://agentmods.dev/badge/skills/bromso/metapowers/evaluate/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/skills/bromso/metapowers/evaluate"><img src="https://agentmods.dev/badge/skills/bromso/metapowers/evaluate.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 | $0.00011 | $0.00561 |
| Opus 5.5 | $0.00004 | $0.00224 |
| Sonnet 5.5 | $0.00002 | $0.00112 |
| Haiku 4.5 | $0.00001 | $0.00056 |
Grade A, and why
evaluate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluate
Evaluate "$ARGUMENTS" for accessibility issues. Run automated and manual checks, discover barriers, and map each issue to specific WCAG success criteria.
Prerequisites
Read .metapowers/accessibility/$ARGUMENTS/01-scope.md. If this file does not exist, tell the user:
Phase 1 (Scope) has not been completed for "$ARGUMENTS". Run
/accessibility:scope $ARGUMENTSfirst, or use--skip-checksto bypass.
If --skip-checks is present in $ARGUMENTS, skip this check and log to .metapowers/accessibility/$ARGUMENTS/skip-log.md.
Process
-
Read context files:
- Read
.metapowers/accessibility/$ARGUMENTS/01-scope.mdfor audit scope and target pages - Read
plugins/accessibility/shared/wcag-21-aa-criteria.mdfor the full criteria reference
- Read
-
Automated evaluation:
- Read the source code of the target pages/components
- Check for: missing alt text, missing form labels, heading hierarchy violations, missing ARIA attributes, color contrast issues, missing lang attribute, keyboard trap risks
-
Manual evaluation:
- Trace keyboard navigation flow — can all interactive elements be reached and operated?
- Check focus visibility — is focus indicator visible on every interactive element?
- Check reading order — does DOM order match visual order?
- Check form error handling — are errors identified and described in text?
- Check dynamic content — are updates announced via ARIA live regions?
-
Map each issue to WCAG criteria:
- For each issue found, identify the specific WCAG success criterion violated
- Classify severity: Critical (blocks access), Major (significant barrier), Minor (inconvenience)
- Note the location (file, line, component)
-
Write the artifact to
.metapowers/accessibility/$ARGUMENTS/02-evaluate.mdwith sections:- Issues Found — each issue with WCAG mapping, severity, location
- Conformance Status — per-principle pass/fail summary
- Critical Barriers — issues that completely block access
- Positive Findings — what's already working well
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.
- 1mo ago First seen · 51 lines · 11 tokens per session scan A de0de2ab0513
evaluate is a skill published in the GitHub repository bromso/metapowers (2 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 561 once invoked, about $0.0000 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 skills, from other repositories
design-method
Use when starting any design task — resolves register, sets the 3 dials, locks Gate 0, and routes to the right move and target skill.
design-webapp
Use when building or extending a dashboard, SaaS screen, or any authenticated app surface — use design-web instead for a marketing site.
design-web
Use when building or revising a marketing/landing/campaign page, register brand locked at Gate 0 — use design-webapp for app screens instead.
motion-art-direction
Use when a film needs a look before any scene code — ads, launch teasers, brand films, type-led films with no screenshots, or whenever a draft looks flat (white ground, small tiles, centered text, fades, slow camera drift, logo opener). Locks .motion/look.md at Gate 0 (3 text sketches → challenger locks the tone blind…
motion-craft
Use when deciding how a film beat looks and moves — motion density (a gesture in progress at every moment: 0.75 s gesture-free max, CTA still ≤ 1.2 s, beats every 0.5-1 s, ≥ 1 onset/s) with read time ≥ 0.25 s/word, one primary gesture with subordinate details, the two film types (cut-based edit, one continuous…
design-motion
Use when adding or reviewing motion on an already-settled layout or component — never to hide or compensate for an unfinished one.