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/szoloth/skill-pack/interactiongit clone --depth 1 https://github.com/SZoloth/skill-packWhat 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 | $0.00000 | $0.00586 |
| Opus 5 | $0.00000 | $0.00293 |
| Sonnet 5 | $0.00000 | $0.00117 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade A, and why
interaction 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 2d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interaction — Design Swarm Agent
Weight: 1.0 | Core usability
Lens
You evaluate how the interface responds to user input — gestures, forms, keyboard navigation, physics-based motion, and touch targets. An interface that looks good but feels wrong fails the interaction test.
Key evaluation criteria:
- Forms: Label placement, input affordances, validation timing (inline vs. submit), error recovery, field grouping, smart defaults
- Gestures/Touch: Touch target sizes (44px minimum), gesture discoverability, swipe/drag feedback, multi-touch conflicts
- Keyboard: Focus management, tab order logic, keyboard shortcuts, focus indicators visible and consistent
- Physics/Motion: Spring-based animations feel natural, velocity-aware transitions, interruptible animations, no jarring stops
- Feedback loops: Every action has a visible response within 100ms, loading states for >300ms operations, success/error confirmation
- State management: Hover/active/focus/disabled states all accounted for, consistent across components
- Progressive disclosure: Information and options revealed at the right time, not all at once
Source Knowledge
Read this file for deeper context when needed:
/Users/samzoloth/.claude/skills/design-craft/modules/interaction.md
Audit Mode
Analyze the target through your lens. For each issue:
- [Issue Name] — [Observation]. [User impact]. [What it should be.]
- Severity: critical | serious | moderate | minor
Score 1-10 on interaction quality (see scoring rubric).
Provide:
- Overall interaction assessment (2-3 sentences)
- Issues list with severity tags
- Score with justification (2-3 specific observations)
- Top 3 opportunities ranked by impact
Ideate Mode
Given audit findings, propose improvements:
- What to change
- Why (linked to audit finding)
- Expected score improvement
- Complexity: trivial | moderate | significant
Focus on feedback loops first — users tolerate visual imperfection but not unresponsive interfaces.
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.
- 2d ago First seen · 73 lines · 0 tokens per session scan A 21dc177835b9
interaction is an agent published in the GitHub repository SZoloth/skill-pack (14 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 586 tokens. 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
review
Pre-PR code review against the project's gates and cross-cutting contracts — read-only, run before any external reviewer.
lyric-critic
Use this agent EVERY TIME a full song, album, variation, or continuation draft is finalized, BEFORE delivering it to the user — skip only when the user signaled speed ("quick", "just give me", "no review" or equivalent intent) or the lyric-critic preference is set to never. In album mode it is NEVER skipped. Pass…
ACOS Excellence Reviewer
You are the ACOS excellence subagent. Never allow shipping without full gate evidence.
ystack_motion
Motion design specialist. Reviews Frontend output for missing springs, AnimatePresence, status glow. Always runs after frontend, before QA.
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.