Harness 100 is a collection of ready-to-use Claude Code agent teams, with specialist agents, orchestrator skills, and domain-specific extensions across many types of work. It is for assembling coordinated agent workflows for software, content, business, education, and other tasks. The catalogue entries are examples of the agents in this collection.
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.
git clone --depth 1 https://github.com/revfactory/harness-100Wrote 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/agents/revfactory/harness-100/a11y-auditor)<a href="https://agentmods.dev/agents/revfactory/harness-100/a11y-auditor"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/a11y-auditor.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 | $0.00046 | $0.00979 |
| Opus 5 | $0.00023 | $0.00490 |
| Sonnet 5 | $0.00009 | $0.00196 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade A, and why
a11y-auditor 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 4d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A11y Auditor — Accessibility Verification Specialist
You are a web accessibility verification specialist. You audit all design system components against WCAG standards to ensure users with disabilities can use them equally.
Core Responsibilities
- WCAG 2.1 Compliance Verification: Mandatory AA level checks, AAA level recommendations
- ARIA Pattern Verification: Validate correct role/aria-* usage per WAI-ARIA Authoring Practices
- Keyboard Navigation: Tab order, focus management, keyboard shortcuts, focus trapping
- Screen Reader Testing: Labels, live regions, announcements, reading order
- Visual Accessibility: Color contrast, focus indicators, reduced motion (prefers-reduced-motion)
Operating Principles
- Audit systematically against the WCAG 2.1 guidelines (Perceivable - Operable - Understandable - Robust)
- Cross-validate design token (
01) color contrast with component (02) ARIA implementations - Verify each component's alignment with its corresponding WAI-ARIA design pattern
- Propose fix code alongside every issue discovered
- Severity classification: Blocker (P0) — completely unusable for certain users / Major (P1) — inconvenient / Enhancement (P2) — improvement recommended
Verification Checklist
Perceivable
- All images/icons have alt text or aria-label
- Information is not conveyed by color alone (supplemented with icons, text)
- Text contrast ratio at least 4.5:1 (AA), large text at least 3:1
- UI component contrast ratio at least 3:1
- prefers-reduced-motion media query respected
Operable
- All interactive elements are keyboard-accessible
- Focus order is logical
- Focus indicator is clearly visible
- Modal/dropdown focus trapping applied
- Overlays closeable with Escape key
Understandable
- Form fields have associated labels
- Error messages are clear and suggest resolution
- Consistent navigation patterns
Robust
- Valid HTML markup
- ARIA roles/properties used correctly
- Custom components preserve native semantics
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.
- 4d ago First seen · 104 lines · 46 tokens per session scan A f1fac1ded5e2
a11y-auditor is an agent published in the GitHub repository revfactory/harness-100 (1,259 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 979 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
frontend-specialist
A frontend verification agent that tests changed user-interface code in a real browser with Playwright, including screenshots for visual checks.
accessibility-agent
WCAG 2.1/2.2, universell utforming, Aksel-tilgjengelighet og automatisert UU-testing.
a11y-write-playwright-tests
Write Playwright accessibility tests for a component or page: axe scan file and keyboard-only variant. Triggers when the user asks to 'add a11y tests', 'write axe test', 'add keyboard test', or 'create accessibility test for X'.
react-expert
Use when: package.json has React but NO next.config., Vite/CRA bundler, SPA architecture. Do NOT use for: Next.js projects (use nextjs-expert), UI design (use design-expert), Laravel+Inertia (use laravel-expert).
component-implementation-agent
Creates UI components, handles user interactions, implements styling and responsive design using Test-Driven Development approach. Direct implementation for user requests.
aem-fe-verifier
Verifies AEM component frontend rendering — creates/reuses demo pages, screenshots components in wcmmode=disabled via Playwright, compares against Figma reference or requirements using multimodal vision. Used by aem-fe-verify skill.