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 bestdeejay-design/agent-skills --skill frontend-a11ygit clone --depth 1 https://github.com/bestdeejay-design/agent-skillsWrote 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/bestdeejay-design/agent-skills/frontend-a11y)<a href="https://agentmods.dev/skills/bestdeejay-design/agent-skills/frontend-a11y"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/frontend-a11y/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/bestdeejay-design/agent-skills/frontend-a11y"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/frontend-a11y.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 254 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
- medium MCP Rug Pull · line 68 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 217 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 252 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00237 | $0.03951 |
| Opus 5 | $0.00118 | $0.01975 |
| Sonnet 5 | $0.00047 | $0.00790 |
| Haiku 4.5 | $0.00024 | $0.00395 |
Grade A, and why
frontend-a11y 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 11d 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
frontend-a11y
frontend-perfection owns measurable layout/perf/SEO/tokens polish and only
touches ~12 basic a11y rules (img-alt, button/link-name, form-label, aria-valid,
landmark-unique, plus lang/dir/headings). This skill owns the deep
accessibility domain — the full Front-End-Checklist Accessibility category
(95 rules), split into three checkable tiers so the right tool runs at the
right time.
- static — offline Python (
scripts/a11y_audit.py), no browser, no network. Markup structure, ARIA validity, headings, landmarks, tables, forms, media tracks, lists, and a few CSS signals. - runtime — Playwright + axe-core (
scripts/a11y_axe.mjs, optional npm deps). Computed contrast, ARIA parent/child relationships, live regions, focus order, modal traps, reflow at 400% zoom, touch targets. - manual — screen-reader testing and human-judgement rules (NVDA/JAWS/
VoiceOver/TalkBack, plain language, seizure flashing). Checklist-only; the
report records them as
severity: manualso they are not silently skipped.
When to use
- User asks to "audit accessibility", "check WCAG", "run axe", "test keyboard navigation", "find focus traps", "verify contrast", "проверь доступность".
- The
/frontendorchestrator routes the a11y domain here;mobile-frontendcalls it for touch-target / orientation / reflow checks. - After
frontend-perfectionpasses its 12 basic rules and you need the other 83.
Composition
- vs
frontend-perfection— it owns layout/perf/SEO/tokens + 12 a11y rules (incl. computed contrast). This skill owns the remaining 83 a11y rules. Do NOT re-implement raw-hex token checks or computed-contrast here — those live infrontend-perfection/a11y_axe.mjs. Runfrontend-perfectionfirst for the shared baseline, thenfrontend-a11yfor depth. - vs
mobile-frontend— it callsfrontend-a11yfor the mobile-a11y rules (touch target size, orientation, reflow at 400%, reduced motion). - vs
/frontend— the orchestrator runsfrontend-perfection+ this skill- (optionally)
a11y_axe.mjsfor the full a11y picture.
- (optionally)
What ships with it
3 files 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.
- 11d ago First seen · 261 lines · 237 tokens per session scan A 4d8102823f02
frontend-a11y is a skill published in the GitHub repository bestdeejay-design/agent-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 237 tokens to every session and 3,951 once invoked, about $0.0012 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
workflow
Use when a task is too large for turn-by-turn orchestration and should run through the big-task workflow lane: system-wide changes, large migrations, repo-wide audits, high-confidence verification, or tasks explicitly asking to run a workflow. Claude Code uses native dynamic workflows; Codex, OpenCode, and Grok use…
skill-compiler
Automatic solved-to-skill compiler — detects novel task completions and autonomously drafts new SKILL.md files. Stolen from Hermes Agent's learning loop (NousResearch, 2026-05-11).
context-compactor
9-section context compression with analysis scratchpad. Adapted from Claude Code's /compact system (2026-03-31).
daemon-loop
Autonomous recurring agent tasks — converts workflows into persistent background daemons that run on intervals. Stolen from Boris Cherny's Claude Code /loop pattern (2026-03-31).
trade-journal-analyzer
Unified post-trade analytics: journal pattern extraction + drawdown classification. Absorbs: drawdown-classifier.
Deep Research Loop
Multi-step web research, compilation, and synthesis workflow. Scrapes multiple sources, cross-references claims, and produces a structured research brief.