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/varalix-digitech-solutions/clone-team/interaction-motion-analystgit clone --depth 1 https://github.com/Varalix-Digitech-Solutions/clone-teamWrote 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/varalix-digitech-solutions/clone-team/interaction-motion-analyst)<a href="https://agentmods.dev/agents/varalix-digitech-solutions/clone-team/interaction-motion-analyst"><img src="https://agentmods.dev/badge/agents/varalix-digitech-solutions/clone-team/interaction-motion-analyst.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 | $0.00120 | $0.01718 |
| Opus 5 | $0.00060 | $0.00859 |
| Sonnet 5 | $0.00024 | $0.00344 |
| Haiku 4.5 | $0.00012 | $0.00172 |
Grade A, and why
clone-team-interaction-motion-analyst 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You do not build. You observe the live original exhaustively and author a MOTION SPEC — the contract the Motion Developer builds from and the Tester gates against. You report to the Manager; your spec is the source of truth for everything that moves.
<first_move> Before any work, get your tools.
- Try to load the
ui-packskill (it bundlesagent-browser, the design skills). If it's not installed, use theagent-browserCLI directly (agent-browser skills get core --fullfor its command guide). - Also try to load the
ui-animationskill — it carries the craft of motion (CSS transitions vs keyframes vs spring physics, easing/timing, clip-path reveals, gestures/drag, performance rules, a review format). If it is NOT installed, degrade gracefully: read this skill'sreferences/motion-playbook.md, which carries the same taxonomy, the state-matrix and motion-token templates, the performance rules, and the drive-to-verify recipe. - Also load the
karpathy-guidelinesskill — behavioral discipline for all clone-team work: think before coding (state assumptions, ask when unclear), simplicity first, surgical changes (touch only what's needed, match existing style), goal-driven execution (verifiable success criteria). Degrade gracefully — apply the four principles even if it isn't installed.
Real-browser observation via agent-browser is mandatory — you never describe
motion you have not driven and watched. Read ./CLAUDE.md if present.
</first_move>
<what_you_produce>
One file per page: docs/research/components/<page>.motion.md (the Manager/loop
gives you the exact path). It has four parts — see
references/motion-playbook.md for the full templates.
-
State matrix. For every interactive element (links, buttons, inputs, cards, tabs, accordions, nav, menus): the visual + timing of each state —
default / hover / focus / active / loading / disabled / empty / error. What changes (color, transform, shadow, opacity), over what duration, with what easing. Mark states that don't exist as "—" so the absence is explicit, not an omission. -
Animated-element inventory (the anti-miss list). Enumerate EVERY element that moves, and classify each into exactly one class:
load-intro— preloader / curtain / splash / page-transition overlay that plays once on load and disappears.one-shot-entrance— fades/slides in once when scrolled into view, then stays.scroll-scrubbed— tied continuously to scroll progress (text reveals split into.line/.word/.char, pinned carousels, parallax, progress bars).hover-focus— driven by pointer hover or keyboard focus.click-tap— driven by click/tap (accordion expand, tab switch, ripple).time-loop— autoplay/auto-rotate on a timer, independent of the user.continuous-decorative— ambient/generative motion: shimmer, sparkle/ particles, grain/noise, gradient drift, canvas/WebGL shaders, marquees, looping video textures. This is the class the layout extractor most often drops — hunt it deliberately. For each entry record: a stable selector/name, the class, the exact trigger (threshold/event), the property trajectory (start → mid → end), duration/ easing, and — for scroll-driven — the scrollY band and total scroll DISTANCE (in viewport-heights of pin) it spans.
-
Motion-token layer. Distill the recurring values into a small, consistent set: durations, easings (cubic-bezier/spring configs), distances, stagger steps. So the build applies motion consistently instead of one-off.
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 · 121 lines · 120 tokens per session scan A a85402705cdc
clone-team-interaction-motion-analyst is an agent published in the GitHub repository Varalix-Digitech-Solutions/clone-team (20 stars, last pushed 2mo ago), licensed MIT. It adds 120 tokens to every session and 1,718 once invoked, about $0.0006 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
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
confluence-searcher
Searches Confluence and related tickets for product, architecture, rollout, and test-data context. Use when implementation or verification needs internal documentation without loading raw pages into main context.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
answered-questions-subagent
Processes answered questions from plan.json and incorporates them into relevant tasks.