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 telus-labs/stagecraft --skill accessibility-auditgit clone --depth 1 https://github.com/telus-labs/stagecraftWrote 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/telus-labs/stagecraft/accessibility-audit)<a href="https://agentmods.dev/skills/telus-labs/stagecraft/accessibility-audit"><img src="https://agentmods.dev/badge/skills/telus-labs/stagecraft/accessibility-audit.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 | $0.00077 | $0.01550 |
| Opus 5 | $0.00039 | $0.00775 |
| Sonnet 5 | $0.00015 | $0.00310 |
| Haiku 4.5 | $0.00008 | $0.00155 |
Grade A, and why
accessibility-audit 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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility audit
Use this skill at Stage 6b (after QA) when the change touched UI. Audits the affected pages/components for WCAG violations using axe-core, pa11y, or Lighthouse. Produces pipeline/accessibility-report.md and writes pipeline/gates/stage-06b.json.
When to use
- Frontend changes shipped at Stage 4 (new component, modified flow, redesigned page).
- Updates to forms, inputs, dialogs, navigation, or anything keyboard/screen-reader-relevant.
- New routes/pages added to the app.
When to skip (with audit_skipped_reason set)
- Backend-only changes (no UI surface).
- Doc-only changes.
- Internal tools with no public/customer surface AND no a11y commitment in the brief.
Procedure
1. Identify what to audit
Read pipeline/brief.md and pipeline/design-spec.md for the scope. Cross-reference with the Stage 4 PR summaries (pipeline/pr-frontend.md) to find:
- Specific routes / page URLs.
- Specific React/Vue/Svelte components.
- Any flows the brief flagged as keyboard-only or screen-reader-critical.
If the change has no UI surface, write the gate with audit_skipped_reason: "<reason>", status: "PASS", all violations zero, and move on.
2. Pick a method
| Tool | Best for | Output shape |
|---|---|---|
axe-core (via @axe-core/cli or programmatic) |
Most thorough; integrates with Playwright/Cypress | JSON with violations grouped by impact |
| pa11y | Quick CLI sweep of URLs | HTML/JSON report per page |
| Lighthouse (a11y audit) | Holistic page score (covers perf + a11y) | JSON with categories.accessibility.audits |
| Manual (screen reader walkthrough) | Custom interactions Playwright/cypress-axe miss | Notes in the report |
In order of recommendation: axe-core programmatic (deepest) → Lighthouse CI (CI-friendly) → pa11y (simplest standalone) → manual (only when automated tools can't reach the flow).
3. Run the audit
axe-core via @axe-core/cli:
npx @axe-core/cli https://localhost:3000/account/notifications \
--tags wcag2a,wcag2aa --save axe-report.json
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 · 149 lines · 77 tokens per session scan A bad487587cdb
accessibility-audit is a skill published in the GitHub repository telus-labs/stagecraft (6 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 1,550 once invoked, about $0.0004 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
vscode-visual-regression
Write Storybook stories and visual regression tests for the Kilo VS Code extension webview UI.
om-module-scaffold
Build a complete standalone business app, module, or CRUD vertical slice using Open Mercato discovery, commands, APIs, ACL/setup, UI, events, search, migrations, and tests. Use for customer management, deal-pipeline changes, CRM lead capture, library/booking/rental systems, "create a module", "add CRUD entity"…
om-troubleshooter
Diagnose and fix standalone Open Mercato bugs across scope, commands, locking, fields, generated registries, UI hydration, cache/search, bootstraps, queues, and providers. Use for "fix bug", "why does this fail", "regression", "debug", "napraw błąd", or a failing test.
react-web
React web development with hooks, React Query, Zustand.
accessibility-a11y
WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing.
ring:checking-frontend-quality
Checking frontend quality against changed UI via ring:qa-frontend in accessibility, visual, e2e, or performance mode and aggregating pass/fail verdicts. Use when a frontend change needs standalone a11y, visual-snapshot, Playwright e2e, or Lighthouse/Core-Web-Vitals validation outside the dev cycle. Skip for…