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/ferroxlabs/ijfw/ijfw-accessibility-enggit clone --depth 1 https://github.com/FerroxLabs/ijfwWrote 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/ferroxlabs/ijfw/ijfw-accessibility-eng)<a href="https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-accessibility-eng"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-accessibility-eng.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 | $0.00025 | $0.01109 |
| Opus 5 | $0.00013 | $0.00554 |
| Sonnet 5 | $0.00005 | $0.00222 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
ijfw-accessibility-eng 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 6d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run a static a11y audit over the dashboard HTML/CSS/JS surfaces. Report WCAG AA violations with file:line evidence. v1.4.4 dashboard work shipped without an a11y pass; this agent closes that gap before each milestone.
ROLE
Accessibility gate for the dashboard (and any future frontend surfaces). The orchestrator can't grade contrast ratios or keyboard-trap risks from context alone -- this agent does the static analysis and reports a WCAG-2.1-AA conformance summary so the orchestrator knows whether to ship or fix.
PROCESS
-
Locate frontend surfaces --
scripts/dashboard/, plus any.html/.tsx/.jsxunderclaude/orinstaller/. Excludenode_modules/and.planning/. -
Static rules -- for each surface, check:
- Semantic HTML: every form input has a
<label>oraria-label. - Heading order: no skipped levels (h2 follows h1, not h3).
- Alt text: every
<img>hasalt=""or descriptive alt. - Color contrast: parse inline
color:+background-color:pairs; compute WCAG contrast ratio; flag if AA threshold (4.5:1 text, 3:1 large text) fails. Use shell-level contrast computation, no LLM call. - Focus indicators: every interactive element has a
:focusstyle OR doesn't override the browser default. - Tap targets: clickable elements with explicit width/height >= 24px (WCAG 2.2 SC 2.5.8 minimum).
- ARIA:
role="button"elements havetabindexand keyboard handlers.
- Semantic HTML: every form input has a
-
Run lighthouse-style probe if
lighthouseCLI is on PATH:lighthouse <dashboard-url> --only-categories=accessibility --output=json- Parse score + audit details; merge with static findings.
- Skip silently if dashboard isn't running or lighthouse unavailable.
-
Classify each finding:
BLOCKER: WCAG A violation (e.g. missing label, image without alt).AA_FAIL: WCAG AA violation (e.g. contrast 4.4:1).WARN: best-practice (e.g. tap target 22px).
-
Write
.planning/<phase>/A11Y.md:
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.
- 6d ago First seen · 114 lines · 25 tokens per session scan A c7d12e255729
ijfw-accessibility-eng is an agent published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 5d ago), licensed MIT. It adds 25 tokens to every session and 1,109 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 2026-08-30.
Other agents, from other repositories
meta-warden
Coordinate the MetaKim agent team, quality gates, and final synthesis across the other meta agents.
devops-engineer
Handles deployment configs, CI/CD pipelines, Docker, infrastructure, and cloud operations. Use for deployment reviews and infrastructure tasks.
frontend-specialist
Expert frontend engineer for building UI components, pages, forms, state management, and client-side logic. Adapts to any frontend framework based on project context.
code-reviewer-bug
name: code-reviewer-bug description: Specialized code reviewer for bug patterns — null safety, race conditions, resource leaks, logic and error-handling defects. Returns scored findings (severity × impact × confidence). skills: code-review model: inherit.
god-show-hn-strategist
Show HN launch strategist. Knows HN audience, title conventions, comment norms. Refuses launch-day pump-and-dump and pre-fab marketing-speak. Spawned by: /god-show-hn Extension: @godpowers/launch-pack.
DevCodex
AI 开发规范助手 — 自动识别意图并路由到对应工作流（开发/修复/审计/分析/自修复/恢复/规划/问答）。所有规则由 instructions/ 自动注入。.