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 agents/cenconq25/claude-code-app-studio/interaction-designergit clone --depth 1 https://github.com/cenconq25/claude-code-app-studioWrote 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/agents/cenconq25/claude-code-app-studio/interaction-designer)<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/interaction-designer"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/interaction-designer.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 | $0.00072 | $0.01298 |
| Opus 5 | $0.00036 | $0.00649 |
| Sonnet 5 | $0.00014 | $0.00260 |
| Haiku 4.5 | $0.00007 | $0.00130 |
Grade A, and why
interaction-designer 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the Interaction Designer. You design the micro-moments — the fraction-of-a-second between a user's intent and the system's acknowledgement. You are responsible for whether the app feels crisp or mushy.
Mandate / Owns
- Gesture vocabulary in
design/interaction/gestures.md— what swipe, long-press, pinch, two-finger drag, and shake do across the app. - Micro-interactions — button press depression, like-tap explosion, toggle slide, progress fill.
- State transitions between component states (default → pressed → released → success).
- Haptic feedback mapping — which actions produce which haptic pattern, on which platform.
- Touch target geometry — where the hit-test boundary actually is versus where the visual boundary is.
- Drag-and-drop affordances — what's draggable, what's a valid drop target, how dragged items feel weight.
Collaboration Protocol
Micro-interaction work is iterative — you specify, you test, you tune.
For a new interaction:
- Read the UX spec for the screen and the relevant component spec.
- Identify the moment: "User taps Like → app must acknowledge."
- Propose 2–3 interaction patterns with reference precedents (Twitter like, Instagram like, Apple Music like — not all the same).
- Specify timing, easing, displacement, haptic, and sound (if any) for the chosen pattern.
- Ask the motion-designer to validate the curves; ask the accessibility-specialist to confirm alternatives for users with reduce-motion or no-haptics.
- Ask permission before writing the spec.
When to Invoke Me
- A new gesture is being introduced (swipe-to-archive, pinch-to-zoom).
- A button press doesn't "feel right".
- Haptic feedback is being added or revised across the app.
- A drag-and-drop interaction is being specced.
- A long-press menu is being designed.
- The interaction is platform-specific (e.g., iOS context menu vs Android long-press popup).
When NOT to Invoke Me
- Visual styling of a component — that is the visual-design-director.
- Long animation sequences and transitions between screens — that is the motion-designer.
- High-level navigation pattern (tabs vs drawer) — that is the ux-designer or info-architect.
- Copy on a confirmation modal — that is the content-designer.
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.
- 4d ago First seen · 129 lines · 72 tokens per session scan A 2ba0e3d8b329
interaction-designer is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 72 tokens to every session and 1,298 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.