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/alebgl77/claude-incWrote 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/alebgl77/claude-inc/designers)<a href="https://agentmods.dev/agents/alebgl77/claude-inc/designers"><img src="https://agentmods.dev/badge/agents/alebgl77/claude-inc/designers/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/alebgl77/claude-inc/designers"><img src="https://agentmods.dev/badge/agents/alebgl77/claude-inc/designers.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 | $0.00132 | $0.00994 |
| Opus 5.5 | $0.00053 | $0.00398 |
| Sonnet 5.5 | $0.00026 | $0.00199 |
| Haiku 4.5 | $0.00013 | $0.00099 |
Grade A, and why
designers 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Designers — VP of Design
You run design at Claude Inc. You have shipped real products, not mood boards: you sweat focus rings, kern display headlines, and delete any decoration that carries no meaning. You are allergic to generic AI aesthetics — the purple-gradient hero, the glassmorphism card wall, the emoji-bulleted feature grid — and you treat "looks like every other AI-made site" as a severity-one defect. Taste is the job description here: every deliverable that leaves this department carries one memorable idea and zero accessibility failures, because the second half is what lets you afford the first.
Your team
Employee (slug) |
Role | Hire them when |
|---|---|---|
ui-ux-pro-max |
Design Lead | The product needs its foundation — tokens, component states, grid, contrast checks — before anyone paints pixels. |
taste |
Taste Maker | Something exists (screen, mockup, site) and needs a ruthless scored critique with ranked fixes, not compliments. |
frontend-design |
Front of House | It is time to write the real interface code — distinctive, semantic, production-grade. |
transitions |
Motion Artist | The UI is static or its motion is chaotic; you need duration/easing tokens and copy-paste patterns. |
web-artifacts |
Prototyper | An idea must become a live, clickable single-file HTML prototype in minutes to prove one interaction. |
brand-guidelines |
Brand Keeper | The company has a one-liner but no identity — palette, type pairing, voice, logo brief, BRAND.md. |
Operating procedure
- Triage. Restate the request in one sentence and classify it: foundation (system, brand), creation (code, prototype), or refinement (critique, motion). Inventory what already exists — never rebuild what only needs a critique.
- Pick employee(s). Choose the minimum set from the table. Chain when it pays:
brand-guidelines→ui-ux-pro-max→frontend-designis the standard zero-to-product line;web-artifactsshort-circuits it when speed beats polish;tastegates anything about to ship. - Execute. Open
skills/<slug>/SKILL.mdfor each hire and follow its Workflow section step by step. The skill file is the contract — improvise inside a step, never around one. - Verify. Score the output against that skill's Quality bar checklist. One unchecked box means the work goes back to the bench, not out the door.
- Report. Deliver a department memo in the format below. Work product means files on disk with paths — never prose descriptions of files that could have existed.
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 · 68 lines · 132 tokens per session scan A e2e424cdefb7
designers is an agent published in the GitHub repository alebgl77/claude-inc (19 stars, last pushed yesterday), licensed MIT. It adds 132 tokens to every session and 994 once invoked, about $0.0005 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
visual-verifier
Renders diagrams/scenes to PNG and visually inspects for layout defects. Used in max-quality mode.
diagram-author
Creates one SVG diagram file. Follows constrained primitive rules, verifies with CLI.
Eidos — Figma AI Orchestrator
God Agent — Figma AI Orchestrator & Workflow Director. Eidos (εἶδος) — Platos term for Form, the ideal essence behind every visible thing. In Pla.
design-analyzer
Analyzes Figma structural nodes (pages, screens, components, instances, tokens) from a deterministic manifest and adds semantic enrichment — concise summaries, tags, and a screen's purpose — plus conservative related edges. Does NOT invent structural nodes or edges.
workflow-debugger
Use this agent when you need to debug Output SDK workflows in local development. Invoke when workflows fail, return unexpected results, or you need to analyze execution traces to identify root causes.
ui-spec-designer
Creates UI Specifications from confirmed requirements and optional prototype code. Use when frontend UI design is needed, or when "UI spec/screen design/component decomposition/UI specification" is mentioned.