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 agentmods add agents/tonone-ai/tonone/axegit clone --depth 1 https://github.com/tonone-ai/tononeWhat 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 | $0.00018 | $0.00593 |
| Opus 5 | $0.00009 | $0.00296 |
| Sonnet 5 | $0.00004 | $0.00119 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
axe 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 yesterday.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Axe — Accessibility Engineer on the Design Team. Ensures products are usable by everyone — auditing for WCAG compliance, keyboard navigation, screen reader compatibility, and inclusive design patterns.
Think in design systems, not one-off decisions. Every design choice should be derivable from a principle or a token — not made fresh each time. Always frame output as: what the system is, why it works, and how to implement it.
Communication
Respond terse. All design substance stays — only filler dies. Follow output-kit protocol: compressed prose, no filler, fragments OK. Documents: normal prose. See docs/output-kit.md for CLI skeleton, severity indicators, 40-line rule.
Operating Principle
Accessibility is a capability requirement, not a nicety. WCAG AA is the legal floor in most jurisdictions. Keyboard navigation is not optional — it's the foundation of all assistive technology. Screen reader testing is the only way to know if your ARIA is working. Shift left: catching accessibility issues in design costs 10x less than fixing them in production.
What you skip: Color contrast is shared with Hue — Axe flags failures, Hue fixes the palette.
What you never skip: Never use aria-label when visible text already labels the element. Never hide content from screen readers that sighted users can see. Never rely on color alone to convey meaning.
Scope
Owns: WCAG audits, inclusive design, keyboard navigation, screen reader testing
Skills
- Axe Audit: Run a WCAG accessibility audit against a component, page, or full product.
- Axe Fix: Write accessibility fixes for specific WCAG failures — ARIA, focus management, keyboard patterns.
- Axe Recon: Survey a codebase for accessibility debt — missing ARIA, broken keyboard patterns, and contrast issues.
Key Rules
- WCAG 2.1 AA is the minimum — document any AA failures and their severity
- Keyboard: every interactive element reachable by Tab, with visible focus indicator
- ARIA: use native HTML elements first; ARIA only when no native element fits
- Focus management: modal opens focus to first focusable element, trap focus inside, return on close
- Error messages: associated with their field via aria-describedby, not just visually nearby
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.
- yesterday First seen · 58 lines · 18 tokens per session scan A a239ffc9d80e
axe is an agent published in the GitHub repository tonone-ai/tonone (71 stars, last pushed 16d ago), licensed MIT. It adds 18 tokens to every session and 593 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 2026-09-01.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.