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 tmj-90/gaffer --skill accessibility-reviewgit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/tmj-90/gaffer/accessibility-review)<a href="https://agentmods.dev/skills/tmj-90/gaffer/accessibility-review"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/accessibility-review/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/tmj-90/gaffer/accessibility-review"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/accessibility-review.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 | $0.00106 | $0.01580 |
| Opus 5.5 | $0.00042 | $0.00632 |
| Sonnet 5.5 | $0.00021 | $0.00316 |
| Haiku 4.5 | $0.00011 | $0.00158 |
Grade A, and why
accessibility-review 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 16d 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.
Accessibility review lens
Inaccessible UI is a correctness defect: a control a keyboard cannot reach does not work for that user. Judge the rendered result, not the intent — read the markup the component produces, trace keyboard and focus behaviour through the code, and use the automated audit the repo already has. Each finding names the control, the WCAG 2.2 success criterion (SC) it fails, and the fix. Only Level A and AA failures on UI the ticket added or changed can block.
Steps
- Identify the UI the diff adds or changes and how a user operates it: controls,
forms, dialogs, menus, tabs, live regions, media, drag interactions. If the diff has no
UI, write "no UI — n/a" and stop. Call
search_lorefor the repo's a11y conventions and shared components (a shared accessibleDialogorButtonis usually the fix). - Use the automated audit the repo provides (jest-axe / vitest-axe in component
tests,
@axe-core/playwrightin browser tests, eslint-plugin-jsx-a11y). Its findings are findings; its silence proves little — automated rules cover only part of WCAG (focus order, names that make sense, announcements need reading). Do not install tools; run an existing command at most once. - Trace the keyboard path through the code: Tab order follows visual order (no
positive
tabindex); every interactive element is focusable and operable (Enter/Space on buttons, arrows inside menus, tabs and listboxes per the ARIA Authoring Practices pattern, Escape closes); focus is visible and not hidden behind sticky headers or overlays; no trap; a dialog moves focus in on open, contains it, and returns it to the trigger on close. - Read it as a screen reader would: native elements before ARIA (
<button>, not a clickablediv); every control has an accessible name that includes its visible label; images meaningfulaltoralt=""; icon-only buttons named; state exposed (aria-expanded,aria-pressed,aria-selected,aria-invalid); headings and landmarks structured; status changes (errors, toasts, results) announced via a live region or focus move. - Check visuals and input: contrast and colour, reflow, target size, dragging and motion as listed below.
- Rate each finding. Blocking: a Level A or AA failure on a control or content the
ticket added or changed. Note (never grounds for CHANGES unless an AC names it): a
pre-existing A/AA failure in adjacent code the diff did not change; platform guideline
gaps (44×44 pt iOS, 48×48 dp Android),
prefers-reduced-motionnot honoured, AAA and best practice beyond the ticket. Only blocking findings justifyRECOMMEND CHANGES. - Record each finding with
record_ac_evidence(evidence_type: manual_note: control, SC number, fix), then let thereview-ticketverdict carry the result.
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.
- 16d ago Changed · +18 lines · +13 tokens per session 8b357bfc652f
- 19d ago First seen · 71 lines · 93 tokens per session scan A 32bcf525d912
accessibility-review is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 17d ago), licensed Apache-2.0. It adds 106 tokens to every session and 1,580 once invoked, about $0.0004 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 2026-09-28.
Other skills, from other repositories
test-audit
Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.
code-review
Comprehensive code review with distinct aspect based sections. Use when reviewing code, checking for security issues, finding type safety problems, auditing code quality, or when user asks to review code, PRs or changes. Three-phase workflow runs static tools, LLM judgment, and writes diagnostic log.
spec-drift-check
Audits a WP brief for drift against current code — extracts claims, verifies each, emits PROCEED/STOP verdict. Use when starting a new WP, before consuming a spec as binding, or when a doc references paths/lines/functions.
besimple-broccoli-blind
Non-interactive wrapper: plan-sketch -> auto-pick recommended options -> plan-write -> plan-critique-loop -> implement-from-plan -> claude-simplify-wrapper -> dedup -> code-review-loop. No PR creation and no Linear comments.
code-review-loop
Iterative review+fix loop for BASESHA..HEAD: generate findings, apply accepted fixes, run checks, commit, and re-review up to 3 iterations or until clean.
dedup
Dedupe-only pass for BASESHA..HEAD: remove duplicate code introduced by the diff or reuse existing shared utils; applies changes + commits.