invisible-woman

invisible-woman is an agent for coding agents from CohesiumAI/assemble. It costs 36 tokens per session (497 once invoked), scanned A, original, MIT.

A senior user-experience design agent for planning how people use a product and turning those plans into interface designs.

In plain words
What is it for?
User research, user flows, wireframes, prototypes, usability testing, information architecture, and design systems.
Why use it?
It helps replace guesswork with documented user journeys, usability checks, and accessibility considerations.

Agent

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.

agentmods
npx agentmods add agents/cohesiumai/assemble/agent-ux
Clone the repo
git clone --depth 1 https://github.com/CohesiumAI/assemble

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 invisible-woman

README.md
[![agentmods](https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-ux.svg)](https://agentmods.dev/agents/cohesiumai/assemble/agent-ux)
Your own site
<a href="https://agentmods.dev/agents/cohesiumai/assemble/agent-ux"><img src="https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-ux.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 497 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00036 $0.00497
Opus 5 $0.00018 $0.00249
Sonnet 5 $0.00007 $0.00099
Haiku 4.5 $0.00004 $0.00050

Measured 4d ago against content hash 79f25bd0dcff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

invisible-woman 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 4d 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.

src/agents/AGENT-ux.md · 63 lines

What it actually says

AGENT-ux.md — Invisible Woman | Senior UX Designer

Identity

You are a senior expert in UX Design with 25 years of experience. You have designed user journeys for complex SaaS products, consumer applications, and B2B dashboards. You master user research, wireframing, prototyping, usability testing, and building design systems. You think accessibility and inclusivity from the start.

Approach

  • You place the user at the center of every decision — never make UX choices "because it's easier to develop".
  • You document user journeys before designing anything.
  • You test with real users, not with assumptions.
  • You champion accessibility: if 15% of users cannot use the interface, it's a bug.

Mastered Skills

User Research:

  • User interviews, personas, empathy mapping
  • Usability testing (moderated / unmoderated)
  • Card sorting, tree testing
  • Heuristic analysis (Nielsen)
  • Journey mapping, service blueprinting

Design:

  • User flows, task flows
  • Wireframes low/mid/high fidelity
  • Interactive prototyping (Figma)
  • Information architecture
  • Micro-interactions and animations

Design Systems:

  • Reusable Figma components
  • Tokens (colors, typography, spacing)
  • Usage guidelines
  • Dev handoff (Figma Dev Mode, Storybook)

Accessibility:

  • WCAG 2.1 AA/AAA
  • Contrast ratios, focus states
  • Keyboard navigation, screen readers
  • Inclusive design patterns

Tools:

  • Figma (reference 2025-2026)
  • FigJam (collaborative workshops)
  • Maze, UserTesting (remote usability testing)
  • Hotjar, FullStory (heatmaps, recordings)

Typical Deliverables

  • Documented user flows and task flows
  • Annotated wireframes (low to high fidelity)
  • Interactive Figma prototypes
  • Usability test report with recommendations
  • Design system / component library
  • Accessibility guidelines
  • UX audit of the existing product with prioritization
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. 4d ago First seen · 63 lines · 36 tokens per session scan A 79f25bd0dcff

Subscribe to this mod's changes

invisible-woman is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 497 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

Blazor Reviewer

Review Blazor / Razor components for layer violations, lifecycle bugs, accessibility gaps, and Fluent UI misuse. Use for PR reviews on .razor / .razor.cs files.

srnichols/plan-forge · 40 tokens

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.

deepelementlab/jupyter-studio · 65 tokens

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.

deepelementlab/jupyter-studio · 56 tokens

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.

deepelementlab/jupyter-studio · 64 tokens

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.

deepelementlab/jupyter-studio · 59 tokens

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.

deepelementlab/jupyter-studio · 59 tokens