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 marcoguillermaz/Tierward --skill accessibility-auditgit clone --depth 1 https://github.com/marcoguillermaz/TierwardWrote 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/marcoguillermaz/tierward/accessibility-audit)<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/accessibility-audit"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/accessibility-audit/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/marcoguillermaz/tierward/accessibility-audit"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/accessibility-audit.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 | $0.00000 | $0.05231 |
| Opus 5 | $0.00000 | $0.02616 |
| Sonnet 5 | $0.00000 | $0.01046 |
| Haiku 4.5 | $0.00000 | $0.00523 |
Grade A, and why
accessibility-audit scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Read Glob Grep Bash(curl:*) mcp__playwright__browser_navigate mcp__playwright__browser_evaluate mcp__playwright__browser_wait_for Agent Edit Write How it starts
The opening of the file, as written. The whole thing — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuration (fill in before first run)
Replace these placeholders:
[DEV_URL]- e.g.http://localhost:3000[SITEMAP_OR_ROUTE_LIST]- e.g.docs/sitemap.md[APP_SOURCE_GLOB]- e.g.app/**/page.tsx+components/**/*.tsx,src/**/*.vue,templates/**/*.html[DEV_COMMAND]- e.g.npm run dev,python manage.py runserver,swift runThen fill in the APCA probe selectors in Step 3 (see Stack adaptation section at end).
Single source of truth for accessibility checks across the project. Combines static grep-based checks (run in all modes) with live browser checks (axe-core WCAG scan + APCA contrast measurement) when a dev server is available.
Scope boundary:
- Owns: static a11y patterns (aria, tabindex, labels, focus, keyboard), axe-core WCAG 2.2 scan, APCA contrast computation.
- Not here: design token compliance and component adoption →
/ui-audit. Typography and aesthetic polish →/visual-audit. Viewport-specific a11y (WCAG 1.4.4 resize, 1.4.10 reflow, tap targets) →/responsive-audit.
Two execution modes:
- Static mode (dev server not running): Steps 0-2, 5 only. Can run concurrently with browser-based skills per pipeline.md.
- Full mode (dev server running): all steps including APCA contrast + axe-core scan. Sequential - shares the browser MCP session with other live audits.
- WCAG mode (
wcag): same as full, plus axe-corebest-practicetag.
Step 0 - Target resolution + mode selection
Parse $ARGUMENTS for an optional mode keyword and a target: token.
| Pattern | Meaning |
|---|---|
static |
Force static mode - skip Steps 3-4 even if dev server is available |
full |
Force full mode - fail if dev server is unreachable |
wcag |
Full mode + axe-core best-practice tag (more stringent) |
| No mode keyword | Auto - full if dev server responds, else static with a warning |
target:route:<path> |
Restrict live scan to a single route (e.g. target:route:/dashboard) |
target:file:<glob> |
Restrict static checks to matching files (e.g. target:file:src/**/page.tsx) |
target:role:<role> |
Restrict to routes accessible by that role (from [SITEMAP_OR_ROUTE_LIST]) |
| No target argument | Full audit - all page/component files from [SITEMAP_OR_ROUTE_LIST] |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 363 lines · 0 tokens per session scan A 31f6fdfe9a43
accessibility-audit is a skill published in the GitHub repository marcoguillermaz/Tierward (4 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,231 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
diagrams
Mermaid diagrams following the C4 model: context, container, component, sequence, ER and deployment. Use when saying "diagram", "visualize", or "architecture diagram".
preview-design
Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…
atomic-visual-options
Planning-phase visual comparison aid. Renders 2-4 side-by-side variants per decision dimension as a single throwaway, self-contained HTML file and captures the user's pick as typed terminal codes (e.g. "A2 B3"). Auto-fires on phrases like "show me a few options", "mock up some variants", "let me see this side by…
harness-engineering
Use when the user asks to improve, fix, or build their repository's AI harness — AGENTS.md, rules, skills, commands, hooks, guardrails, CI sensors — or to act on harness-score audit findings and raise their maturity level.
zhongguose-html-skill
An HTML-only presentation system using traditional Chinese colours and Chinese-style visual design. It helps organise source material into a report structure and produces a self-contained HTML file with its assets.
taste-profile
Build a scoped taste profile packet from examples, preferences, and explicit dislikes so downstream agents can make style decisions without inventing the user's taste.