sable-ux

sable-ux is an agent for Claude Code from robertsfeir/atelier-pipeline. It costs 41 tokens per session (800 once invoked), scanned A, original, Apache-2.0.

A UX design agent that creates user-flow and interaction documents for a software product. UX means how people use a product, including screens, actions, feedback, errors, and accessibility.

In plain words
What is it for?
Use it to document user flows, empty/loading/populated/error/overflow states, interactions, transitions, and accessibility guidance.
Why use it?
It turns a feature request into concrete screen behavior and states that designers and developers can follow.

Agent for Claude Code

Written for Claude Code: hooks in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Part of the atelier-pipeline plugin — 4 skills, 7 commands, 14 agents, 8 hooks shipped together

Good fit Use it to document user flows, empty/loading/populated/error/overflow states, interactions, transitions, and accessibility guidance.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/robertsfeir/atelier-pipeline/sable-ux
Install

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.

Clone the repo
git clone --depth 1 https://github.com/robertsfeir/atelier-pipeline

Made for: Claude Code.

Or install atelier-pipeline, the plugin that ships this one along with the rest of its 4 skills, 7 commands, 14 agents, 8 hooks.

Wrote 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.

agentmods badge for sable-ux

README.md
[![agentmods](https://agentmods.dev/badge/agents/robertsfeir/atelier-pipeline/sable-ux/github.svg)](https://agentmods.dev/agents/robertsfeir/atelier-pipeline/sable-ux)
Your own site
<a href="https://agentmods.dev/agents/robertsfeir/atelier-pipeline/sable-ux"><img src="https://agentmods.dev/badge/agents/robertsfeir/atelier-pipeline/sable-ux/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.

agentmods 80×15 button for sable-ux

Your own site · 80×15
<a href="https://agentmods.dev/agents/robertsfeir/atelier-pipeline/sable-ux"><img src="https://agentmods.dev/badge/agents/robertsfeir/atelier-pipeline/sable-ux.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 800 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.00800
Opus 5 $0.00020 $0.00400
Sonnet 5 $0.00008 $0.00160
Haiku 4.5 $0.00004 $0.00080

Measured 9d ago against content hash 8c1a43b59214, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sable-ux 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 9d 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.

.claude/agents/sable-ux.md · 73 lines

What it actually says

Your job is to create user experience documents, design user flows, interaction patterns, state designs, and accessibility guidelines. You write UX docs to docs/ux/. You are the producer counterpart to the Sable reviewer persona.

  1. Design system check. Follow the detection and loading rules in {config_dir}/references/design-system-loading.md. Read tokens.md (always) + the domain file matching the UX work (see selective loading table). Record which files you loaded. If no design system is found, note "no design system found" and proceed -- this is not an error.

  2. Read existing UX docs. Read all files in docs/ux/ for context and consistency.

  3. Extract scope. From Eva's <task>, identify: which screens or flows to design, the user goals each flow serves, and any explicit constraints.

  4. Design the flows. For each screen:

    • User flow: entry point → steps → exit points. Name each step.
    • Five states: empty, loading, populated, error, overflow. Specify what appears in each — not "show a spinner" but "spinner centered, no other content, aria-label='Loading {thing}'".
    • Interaction patterns: what happens on click, input, transition, error. Be specific about feedback.
  5. Accessibility. Keyboard navigation path, ARIA roles for non-standard elements, focus management on modal/drawer open/close, minimum contrast ratios.

  6. Write the UX doc to docs/ux/{feature}-ux.md. Sections: Design System (tokens used or "no design system found"), User Flows, State Designs (per screen), Interaction Patterns, Accessibility Notes.

  7. DoD. Verify: all five states specified for every screen, accessibility requirements present, design system tokens referenced where a design system was loaded, doc written to docs/ux/.

Include in the DoR section:

Design system: [Loaded: file1.md, file2.md | No design system found]

Return exactly one line to Eva: sable-ux: UX doc written to docs/ux/{feature}-ux.md.

Changes

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.

  1. 9d ago First seen · 73 lines · 41 tokens per session scan A 8c1a43b59214

Subscribe to this mod's changes

sable-ux is an agent published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 800 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 2026-08-30.

Related

Other agents, from other repositories

design-advisor

Use after architect, before/parallel to pm, for any UI-bearing feature (landing pages, dashboards, admin panels, web apps, React Native apps). Picks a design system, enumerates the component inventory, writes text-form wireframes, and locks the a11y + responsive + (mobile) platform-integration contract. Outputs…

avelikiy/great_cto · 89 tokens

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.

VandanaAjayDubey111/great-pm · 54 tokens

usability-auditor

Runs a full usability audit on an interactive mockup or prototype — derives personas and use cases, walks every workflow end to end, hunts for process gaps, audits AI-task progress visibility and content necessity, and writes a detailed usability report. Use when asked to usability-test, audit, or pressure-test a…

Evolvlabsai/Exolvra-Genesis · 82 tokens

designer-agent

UI/UX designer — design systems, visual direction, component specs, layouts, color palettes, typography, interaction patterns. Works BEFORE frontend-agent to establish aesthetic direction and after to review visual quality. Does not write application logic — only design specs and styled components. Triggers on…

ushibo/brigade · 108 tokens

ux-designer

Expert UX Designer with 30 years of experience in user experience and product design. Provides UX strategy, design critique, and usability guidance. Advisory only - does not modify code.

Ibrahim-3d/orchestrator-supaconductor · 39 tokens

designer

Generates design system, component specs, and visual direction for this project. Produces design tokens and component descriptions that Frontend Developer implements.

OrodruinLabs/nazgul · 30 tokens