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 remediategit 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/remediate)<a href="https://agentmods.dev/skills/bromso/metapowers/remediate"><img src="https://agentmods.dev/badge/skills/bromso/metapowers/remediate.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 5.1 | $0.00011 | $0.00475 |
| Opus 5 | $0.00005 | $0.00237 |
| Sonnet 5 | $0.00002 | $0.00095 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade A, and why
remediate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Remediate
Fix the accessibility issues found in "$ARGUMENTS". Apply remediation patterns to resolve WCAG violations, starting with critical barriers.
Prerequisites
Read .metapowers/accessibility/$ARGUMENTS/03-report.md. If this file does not exist, tell the user:
Phase 3 (Report) has not been completed for "$ARGUMENTS". Run
/accessibility:report $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/$ARGUMENTS/03-report.mdfor prioritized issues and remediation steps - Read
plugins/accessibility/shared/remediation-patterns.mdfor common fix patterns
- Read
-
Fix issues by priority:
- Start with Critical severity issues
- Then Major, then Minor
- For each issue:
- Read the affected code
- Apply the recommended fix from the report
- Follow the remediation patterns in shared resources
- Verify the fix doesn't introduce new issues
- Commit each fix or group of related fixes
-
Log remediation progress:
- Track each issue: fixed, deferred, or cannot fix (with reason)
- Record commit hashes for each fix
- Note any issues that require design changes or stakeholder decisions
-
Write the artifact to
.metapowers/accessibility/$ARGUMENTS/04-remediate.mdwith sections:- Fixes Applied — each issue with what was changed and commit hash
- Deferred Issues — issues not fixed and why
- Design Decisions Needed — issues requiring stakeholder input
- New Considerations — any new issues discovered during remediation
Output
The remediation log written to .metapowers/accessibility/$ARGUMENTS/04-remediate.md. Present a summary to the user highlighting:
- Issues fixed vs. total
- Commits made
- Any deferred issues needing attention
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.
- 6d ago First seen · 50 lines · 11 tokens per session scan A e2464f409418
remediate is a skill published in the GitHub repository bromso/metapowers (1 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 475 once invoked, about $0.0001 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 skills, from other repositories
react-tanstack-router
Use when implementing routing in a React app (NOT Next.js) with TanStack Router — file-based routes, loaders, search params.
fusecore
Use when creating modules, understanding FuseCore structure, or implementing features in a FuseCore modular-monolith Laravel project.
laravel-blade
Create Blade templates with components, slots, layouts, and directives. Use when building views, reusable components, or templating.
laravel-livewire
Livewire 4 reactive components on Laravel 13 - wire:model, actions, events, Volt, Folio. Use when building reactive UI without JavaScript.
solid-nextjs
Use when applying SOLID principles to Next.js architecture — modular structure, file size limits, interface separation, JSDoc.
react-19
Use when implementing React 19.2 patterns — use(), useOptimistic, useActionState, useEffectEvent, Activity component, React Compiler.