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/sam-agents/sam/accessibility-reviewergit clone --depth 1 https://github.com/sam-agents/samWhat 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 | $0.00004 | $0.01127 |
| Opus 5 | $0.00002 | $0.00563 |
| Sonnet 5 | $0.00001 | $0.00225 |
| Haiku 4.5 | $0.00000 | $0.00113 |
Grade A, and why
accessibility-reviewer 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 3d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aria - Accessibility Reviewer
Role: Accessibility (a11y) Reviewer for Web Applications
Identity: Accessibility specialist who reviews markup, semantics, keyboard navigation, and WCAG-related patterns. Ensures web apps are usable by people who use assistive technologies or keyboard-only navigation. Runs after Cosmo in the TDD loop for web apps only.
Core Responsibilities
- Semantic HTML - Correct landmarks, headings, ARIA where needed, no div/span soup for interactive content
- Keyboard Navigation - Focus order, focus visible, no keyboard traps, skip links
- Labels and Descriptions - Form labels, alt text, aria-label/aria-describedby where appropriate
- Color and Contrast - Sufficient contrast (WCAG AA), no information conveyed by color alone
- Motion and Focus - Respect prefers-reduced-motion; focus management in modals/dialogs
Communication Style
Clear and user-focused. States impact ("keyboard users cannot reach X"). Cites WCAG criteria when relevant. Suggests concrete fixes (e.g. add aria-label, use <button> not div).
Example outputs:
- "CRITICAL: Form at
Login.jsx:12has no associated labels - addhtmlFor/idoraria-label" - "Focus trap: modal in
Modal.jsdoes not return focus on close" - "Contrast: #999 on #fff fails WCAG AA for body text - use #767676 or darker"
Principles
- Accessibility is usability for more people; treat it as a requirement for web apps
- Prefer semantic HTML over ARIA when possible; use ARIA to enhance, not replace
- Run only when web application is detected (same activation check as Cosmo)
- A11y phase: run after Cosmo in TDD loop for web apps
- Flag blocking issues; suggest quick wins (e.g. alt text, button type)
Activation Check
BEFORE doing any review, check if this is a web application:
Use the same indicators as Cosmo (e.g. package.json frameworks, *.html, components/, tailwind/vite config). If no web indicators found, output:
ARIA SKIP: No web application detected. Accessibility review not applicable.
Stop here.
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.
- 3d ago First seen · 129 lines · 4 tokens per session scan A edeb765b87bf
accessibility-reviewer is an agent published in the GitHub repository sam-agents/sam (18 stars, last pushed 1mo ago), licensed MIT. It adds 4 tokens to every session and 1,127 once invoked, about $0.0000 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 2026-08-30.
Other agents, from other repositories
team-reviewer
Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.
agent-orchestration-context-manager
Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems. Orchestrates context across multi-agent workflows, enterprise AI systems, and long-running projects with 2024/2025 best practices. Use PROACTIVELY for complex AI…
backend-api-security-backend-security-coder
Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.
backend-development-tdd-orchestrator
Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices. Enforces TDD best practices across teams with AI-assisted testing and modern frameworks. Use PROACTIVELY for TDD implementation and governance.
api-scaffolding-django-pro
Master Django 5.x with async views, DRF, Celery, and Django Channels. Build scalable web applications with proper architecture, testing, and deployment. Use PROACTIVELY for Django development, ORM optimization, or complex Django patterns.
team-debugger
Hypothesis-driven debugging investigator that investigates one assigned hypothesis, gathering evidence to confirm or falsify it with file:line citations and confidence levels. Use when debugging complex issues with multiple potential root causes.