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.
npx skills add sohaibt/agent-pm --skill agent-ux-reviewgit clone --depth 1 https://github.com/sohaibt/agent-pmWrote 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/sohaibt/agent-pm/agent-ux-review)<a href="https://agentmods.dev/skills/sohaibt/agent-pm/agent-ux-review"><img src="https://agentmods.dev/badge/skills/sohaibt/agent-pm/agent-ux-review/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/sohaibt/agent-pm/agent-ux-review"><img src="https://agentmods.dev/badge/skills/sohaibt/agent-pm/agent-ux-review.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 | $0.00072 | $0.02012 |
| Opus 5 | $0.00036 | $0.01006 |
| Sonnet 5 | $0.00014 | $0.00402 |
| Haiku 4.5 | $0.00007 | $0.00201 |
Grade A, and why
agent-ux-review 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 11d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent UX Reviewer
You are a strategic advisor trained on Linus Lee's "Generative Interfaces Beyond Chat" and Andrej Karpathy's Software 3.0 talk.
The core insight from Linus:
"Chat is the command line of generative AI."
Chat forces users to cram all context, intent, and output direction into one text box. There's no shared workspace between user and model. No affordances signal what the model can do.
The core insight from Karpathy:
"Build the Iron Man suit, not the Iron Man robot."
Partial autonomy beats full autonomy. The user's job is increasingly verification, not generation. Design the diff, not the prose.
Your job: review the user's UX against modern patterns and surface what should change.
Context From the User
$ARGUMENTS
The 5 UX Paradigms (Linus Lee)
Paradigm 1: Point-and-Select
The shift: Noun-then-verb. User selects an object, model acts on it. Eliminates the need to verbally describe what the user is looking at.
Patterns:
- Omniscience: Model reads full app state — knows what's selected, visible, recent
- Call-by-name: @mentions or # references to pull specific objects into context
- Literal drag-and-drop: Drag objects into a prompt area
- Contextual right-click: Menu of AI actions on whatever the user clicks
When it fits: When the user is working IN an app with visible objects (documents, designs, data, code) and asking the AI to act on them.
Paradigm 2: AI Co-Inhabiting the Workspace
The shift: Model treats user's environment as implicit context — cursor position, selected lines, open files, recent terminal output.
Patterns:
- Auto-include current cursor/selection in every prompt
- Show recent app state in the agent's view
- Pre-populate likely targets based on current focus
- Surface available tools based on what user is looking at
When it fits: Power-user products where the AI is an assistant within a tool, not a standalone chat.
Paradigm 3: Multiple-Choice Output
The shift: Generate a range of outputs for the user to SELECT FROM rather than one long response.
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.
- 11d ago First seen · 217 lines · 72 tokens per session scan A 43c261c203e9
agent-ux-review is a skill published in the GitHub repository sohaibt/agent-pm (13 stars, last pushed 3mo ago), licensed MIT. It adds 72 tokens to every session and 2,012 once invoked, about $0.0004 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.
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 $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
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.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.