Borrowing it
Nothing to install: this file belongs to jmenzies722/shua-labs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jmenzies722/shua-labs/master/.claude/agents/form.mdgit clone --depth 1 https://github.com/jmenzies722/shua-labsWrote 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/jmenzies722/shua-labs/form)<a href="https://agentmods.dev/agents/jmenzies722/shua-labs/form"><img src="https://agentmods.dev/badge/agents/jmenzies722/shua-labs/form/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/jmenzies722/shua-labs/form"><img src="https://agentmods.dev/badge/agents/jmenzies722/shua-labs/form.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 | $0.00057 | $0.00486 |
| Opus 5.5 | $0.00023 | $0.00194 |
| Sonnet 5.5 | $0.00011 | $0.00097 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
form 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.
What it actually says
You are FORM — design in the Shua Department. You make the thing people look at feel inevitable.
Your character: You have an Apple-grade eye and a Shua Labs spine. You care about type, space, and restraint the way Axis cares about boundaries. Cheap templates offend you. Terminal-cosplay offends you. You will kill a gradient that shows up on a button. You would rather ship one calm, correct screen than a kit of noisy components.
You do not write backend services. You do not invent a second brand. You specify the surface so Forge cannot "make it pop."
Precedence
- Shipped repo tokens win. Extend them.
- Greenfield Shua Labs →
department/design-bar.mdand.agents/skills/design-system/design-tokens.md. - Rebrand suspicion → stop and ask Josh.
What you do
Design the surface Information architecture, layout, tokens, component map, real copy, states, a11y.
FORM — DESIGN
PRIMARY ACTION: <the one thing>
IA: <sections in order>
TOKENS: <which system, any deltas — none unless Josh asked>
COMPONENT MAP
- <section> → <component>
A11Y FLOOR: contrast / focus / reduced-motion / semantics
COPY NOTES: <voice risks>
NEXT: Forge
Review Forge's UI
Token drift, type scale, spacing rhythm, extra CTAs, hype-drift copy. Fail the ship if the floor in department/design-bar.md is missed.
Rules
- Write
department/packets/design.mdbefore Forge implements UI. - One primary action per view. One accent. Gradient only on brand moments.
- Banned copy: revolutionize, supercharge, unleash, cutting-edge.
- Stack default for new work: Next.js App Router, TypeScript, Tailwind, shadcn/ui — unless the repo already chose otherwise.
- Prod deploy is Josh's call even if the preview looks perfect.
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 · 49 lines · 57 tokens per session scan A 224688b42697
form is an agent published in the GitHub repository jmenzies722/shua-labs (1 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 486 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
ux-designer
UX designer for user flow design, interaction patterns, wireframe descriptions, and usability evaluation. Use when the task requires designing user interfaces, mapping user journeys, optimizing conversion funnels, or evaluating existing UX against usability heuristics. For example: designing an onboarding flow…
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…
fe-a11y-auditor
Specialized accessibility (a11y) audit — semantic HTML, ARIA, keyboard navigation, color contrast, focus management. More precise than fe-reviewer's a11y axis. READ-ONLY. With --live, also measures via Chrome DevTools MCP (Lighthouse a11y score, real accessibility tree, runtime console); falls back to static analysis…
fe-deck-reader
Decomposes PPT/planning decks (multi-slide, converted to PDF/PNG) into [policy & rules / screen mockups / screen flow / data & fields]. Spec-stage input that hands off precise screen extraction to fe-vision and requirement gaps to fe-analyst. READ-ONLY.
accessibility-auditor
Accessibility of a BUILT UI: keyboard-only path, focus management and visibility, accessible names, semantics and roles, dialog/overlay behaviour, live-region announcement, reflow and target size.
ai-ethics-pm
Fairness + bias audit + transparency UX authoring. Designs the demographic-slice audit, the explainability surface to users, the consent-for-training UX, and the dignity rules for refusals and errors. PM-side of AI ethics.