Berd is an open-source desktop application for working with AI agents through a graphical interface. It is intended for people who want to use different AI models and an integrated Goose backend from a desktop app. The catalogue entries add agent skills, agents, and instructions for working within Berd.
Borrowing it
Nothing to install: this file belongs to block/berd. 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/block/berd/main/.agents/skills/assistive-ux/SKILL.mdgit clone --depth 1 https://github.com/block/berdWrote 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/skills/block/berd/assistive-ux)<a href="https://agentmods.dev/skills/block/berd/assistive-ux"><img src="https://agentmods.dev/badge/skills/block/berd/assistive-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.
<a href="https://agentmods.dev/skills/block/berd/assistive-ux"><img src="https://agentmods.dev/badge/skills/block/berd/assistive-ux.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00054 | $0.00597 |
| Opus 5.5 | $0.00022 | $0.00239 |
| Sonnet 5.5 | $0.00011 | $0.00119 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
assistive-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 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assistive UX
Use this skill for Berd product intelligence moments that teach, suggest, or adapt settings based on user behavior.
Before changing code, read docs/assistive-ux.md. Treat that doc as the source
of product intent and architecture.
Core Rule
Keep assistive state separate from user settings:
User settings answer: what should the product do?
Assistive UX answers: what has the app shown, observed, accepted, retired, or applied?
Do not store guidance lifecycle state inside a feature setting. Do not use assistive state as the source of truth for product behavior.
Types
discover: teaches that a control, setting, or capability exists. It should not change settings.suggest: notices a repeated behavior and asks before changing a setting.autoApply: changes a reversible local setting only after strong evidence, then explains the change and offers undo.
Use autoApply conservatively. Never auto-apply changes involving secrets,
credentials, permissions, destructive actions, provider setup, billing-like
behavior, or hard-to-reverse choices.
Implementation Workflow
- Define or update the rule in
src/shared/assistive-ux/registry.ts. - Keep lifecycle reads and writes in
src/shared/assistive-ux/runtime.tsandsrc/shared/assistive-ux/state.ts. - Render the moment from the relevant feature surface.
- Retire the moment when the user accepts it, dismisses it, sees it enough times, or manually changes the related setting.
- If the moment changes a setting, call the setting's public setter and provide an undo path when the change is automatic.
- Keep stored signals coarse. Do not store chat text, file paths, provider secrets, credentials, or message contents.
UX Checklist
Before shipping, confirm:
- The moment appears close to the behavior it helps with.
- The copy explains the next action without selling the feature.
- The primary workflow still has visual priority.
- The moment has a clear retirement path.
- Repeated exposure is capped.
- Manual setting changes stop or reset related guidance.
- The behavior works in light and dark themes.
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 · 77 lines · 54 tokens per session scan A 6c0ce3077f43
assistive-ux is a skill published in the GitHub repository block/berd (1,007 stars, last pushed 2d ago), licensed Apache-2.0. It adds 54 tokens to every session and 597 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.