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 agentmods add skills/getcrew44/crew44/interaction-reviewnpx skills add getcrew44/crew44 --skill interaction-reviewgit clone --depth 1 https://github.com/getcrew44/crew44Wrote 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/getcrew44/crew44/interaction-review)<a href="https://agentmods.dev/skills/getcrew44/crew44/interaction-review"><img src="https://agentmods.dev/badge/skills/getcrew44/crew44/interaction-review.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.00511 |
| Opus 5 | $0.00014 | $0.00255 |
| Sonnet 5 | $0.00006 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
interaction-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 5d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interaction Review
Make sure every state a user can land in has been considered, and that motion serves the user rather than decorating.
State coverage map
For each user-facing surface, walk through:
| State | Question |
|---|---|
| Loading | What does the user see while waiting? Is it clear progress is happening? |
| Empty | What does the user see with zero results, zero items, zero history? Does the empty state guide the next action? |
| Error | When the network or backend fails, can the user understand what happened and recover? |
| Success | Is feedback clear and the next action obvious? |
| Partial | When the operation half-succeeded, is the partial result accurately reported? |
Edge cases to test
- 47-character name. 200-character name. Empty name.
- Zero results. One result. Ten thousand results.
- First-time user. Power user with their own muscle memory.
- Slow connection. Offline. Back button mid-action. Double-click on a critical button.
Motion principles
Motion should communicate, not decorate. Every animation answers one of: confirm an action occurred, orient where things came from or go to, focus attention on a change, or preserve context during a transition. If it does none of these, cut it.
Use a timing scale:
- 100–150 ms: micro-feedback (hovers, clicks)
- 200–300 ms: small transitions (toggles, dropdowns)
- 300–500 ms: medium transitions (modals, page changes)
- 500 ms+: complex choreography only
Prefer spring or ease-out for entrances, ease-in for exits, transform/opacity for performance. Honor prefers-reduced-motion.
Microinteraction checklist
- Buttons: hover, press, focus, disabled, loading — each visually distinct, none flicker.
- Inputs: default, focus, error, disabled, success — clear path back from error.
- Toggles and switches: state change is visible at a glance, not just a color shift.
- Drag, swipe, scroll-triggered: discoverable, reversible, non-blocking.
Output
- Specific gaps in state coverage, with the user-visible consequence.
- Specific edge cases not handled.
- Motion that decorates rather than communicates.
- Recommendations sized by impact, not effort.
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.
- 5d ago First seen · 55 lines · 28 tokens per session scan A eb5fec97044d
interaction-review is a skill published in the GitHub repository getcrew44/crew44 (359 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 511 once invoked, about $0.0001 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
desktop-brand-builder
Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build on top of packages/desktop-shell.
dataviz
Design guidance for charts, graphs, dashboards, maps, and data visualizations, including a local palette validator.
frontend-design-landing-page
Marketing landing page and conversion-focused product page reference. Use this skill when building hero sections, feature grids, pricing pages, testimonials, CTAs, footers, navigation bars, or any public-facing marketing surface. Covers a warm, professional, developer-friendly design language (cream backgrounds…
frontend-design-saas
S-tier SaaS dashboard and product UI reference. Use this skill when building application shells, data tables, settings panels, billing pages, dashboards, auth flows, admin tools, or any internal/customer-facing SaaS product UI. Inspired by Stripe, Linear, Vercel, Airbnb, Notion. Covers neutral-led design tokens…
frontend-design
Produce intentional, responsive, accessible UI work and perform visual QA instead of generic component assembly.
insight-diagram
为任意项目生成 UML 图、架构图和流程图。分析代码库后让用户选择要生成的图表类型，使用 architecture-diagram skill 渲染为 HTML+SVG，保存到 docs/ 目录。适用于任何软件项目的文档可视化。.