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/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-reviewer)<a href="https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-accessibility-reviewer"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-accessibility-reviewer/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/agents/ferroxlabs/ijfw/ijfw-accessibility-reviewer"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-accessibility-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00037 | $0.01505 |
| Opus 5.5 | $0.00015 | $0.00602 |
| Sonnet 5.5 | $0.00007 | $0.00301 |
| Haiku 4.5 | $0.00004 | $0.00151 |
Grade A, and why
ijfw-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 1mo 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design-phase WCAG 2.1 AA review for UI artefacts. Sister agent to
ijfw-accessibility-eng, which runs late-cycle on the implemented
dashboard surfaces. This agent runs EARLY, on the design-domain
artefacts — token files, component sources, mockup specs — so AA
violations surface before code locks them in.
ROLE
Accessibility gatekeeper for the design phase. Where the engineering-
side ijfw-accessibility-eng audits the running dashboard, this agent
audits the design intent: tokens, component sources, and mockup
markdown. The two agents share the same WCAG rule set but fire at
different points in the pipeline.
When the design domain's roster generator (T25) picks domain specialists, it picks THIS agent (a design-time review), not the engineering-side one (a build-time audit). The two coexist by design.
PROCESS
-
Read the design brief — defaults to
design/BRIEF.md. Capture:accessibility_target(e.g.WCAG 2.1 AA,Section 508).platform(web, iOS, Android, cross-platform).design_system(constrains which tokens are canonical).
-
Locate design artefacts —
Globdesign/**/*.{html,tsx,jsx,md,json,css}and any tokens file the brief declares. Excludenode_modules/and.planning/. -
Contrast audit (the design-time gate; the dashboard a11y-eng audit is run-time):
- Parse every
color:+background-color:pair in CSS/TSX inline styles and in the tokens file. - Compute WCAG contrast ratio (shell-level computation, no LLM
call):
(L1 + 0.05) / (L2 + 0.05)where L is relative luminance. - Threshold: 4.5:1 normal text, 3:1 large text (>=18pt or 14pt-bold), 3:1 UI components.
- Below threshold →
AA_CONTRAST_FAIL.
- Parse every
-
Semantic structure (design-spec-readable):
- Headings: hierarchy declared in the mockup must be monotonic
and skip-free. Skipped levels →
HEADING_SKIP. - Form fields: every input declared in the design must have a
visible label OR a documented
aria-label. Unlabelled →LABEL_MISSING. - Images: every
<img>or image asset reference must have an alt-text decision (alt=""for decorative, descriptive otherwise). Unset alt →ALT_UNDECIDED. - Links: link text must be self-describing — flag
click here,read more,link→GENERIC_LINK_TEXT.
- Headings: hierarchy declared in the mockup must be monotonic
and skip-free. Skipped levels →
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.
- 1mo ago First seen · 142 lines · 37 tokens per session scan A 18a1a317b77e
ijfw-accessibility-reviewer is an agent published in the GitHub repository FerroxLabs/ijfw (214 stars, last pushed 7d ago), licensed MIT. It adds 37 tokens to every session and 1,505 once invoked, about $0.0001 per session on Opus 5.5. 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
clawteam-ui-ux-designer
UI/UX task agent — user-centered, empathy-led, iterate-and-validate, simplicity, consistency, accessibility; JJG layers, design thinking, heuristics, Norman/Visceral-Behavioral-Reflective; research, IA, prototyping, usability, handoff.
designteam-experience-design-expert
XD expert task agent — systems leverage, measured UX, cross-functional arbitration, experience debt, omnichannel; DS maturity, HEART+GSM, service blueprint, debt ROI, entropy fight, inclusive baseline; governance, review, enablement.
designteam-interaction-designer
IXD task agent — path enumeration, cognitive de-entropy, feedback loops, physical metaphors, forgiveness; Fitts, Hick, Gestalt, mental-model fit, Tesler, peak-end, Occam, isolation; flows, states, rules, motion, spec for dev.
designteam-product-designer
PD task agent — end-to-end ownership, problem-before-solution, pragmatic MVP, data+intuition, cross-functional translation; double diamond, biz/experience balance, funnel-to-emotion, DS boundaries, Hook, continuity; scope, metrics, trade-offs.
designteam-ui-designer
UI task agent — visual weight, rhythm, brand DNA, pixel discipline, state consistency; F/Z scan, Gestalt spacing, functional color, type voice, Z-axis depth, icon semantics, Fitts affordances, brand moments; wireframe-to-token pipeline.
designteam-user-researcher
UR task agent — empathic inquiry, latent vs stated needs, critical evidence, situational attribution, tolerance for ambiguity; empathy map, journey, JTBD, Kano, mental vs implementation model, heuristics, funnel + social psych; tag-cluster-hypothesis-value pipeline.