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/savant0x/savant-code/savant-motionnpx skills add savant0x/savant-code --skill savant-motiongit clone --depth 1 https://github.com/savant0x/savant-codeWrote 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/savant0x/savant-code/savant-motion)<a href="https://agentmods.dev/skills/savant0x/savant-code/savant-motion"><img src="https://agentmods.dev/badge/skills/savant0x/savant-code/savant-motion.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 5.1 | $0.00201 | $0.01673 |
| Opus 5 | $0.00101 | $0.00837 |
| Sonnet 5 | $0.00040 | $0.00335 |
| Haiku 4.5 | $0.00020 | $0.00167 |
Grade A, and why
savant-motion 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
savant-motion
Scroll is the only input every visitor already knows how to use. Treat it as a timeline: the wheel is a scrubber, the page is a film with real text on top, and each act behaves differently enough that the visitor keeps going.
Provenance: native transposition of scroll-craft (MIT, Nate Herk;
worldflight mechanics trace to oso95/scroll-world). The pristine snapshot
lives at resources/scroll-craft-main/; everything here is rewritten to
ECHO governance — no paid APIs, no ffmpeg dependency, deterministic evidence.
Choreography: map onto the Perfection Loop
This skill adds zero runtime machinery; it routes through the loop that already exists.
| Loop phase | Owner | This skill's work |
|---|---|---|
| idle | Orchestrator | Interview (Step 0); confirm FID-bound execution applies |
| red | Detective | Read brand assets, resolve workspace, load registry rows |
| green | Thinker + Orchestrator | Grammar + signature move + feeling curve; run scripts/gate.ts; write BRIEF.md |
| green | Forge/Orchestrator | Build page from templates/engine/page-starter.html on the read-only engine |
| audit | Verifier | Consume evidence.json from scripts/verify/index.ts — one violation is an AUDIT failure |
| adversarial | Adversary | Attack the signature move's novelty against registry history; refute derivative claims |
| complete | Recorder | Record the row via gate.ts --record; archive |
Step 0: The interview
Always interview before generating anything. Eight questions, one pass:
- Vibe in three to five words, plus up to three non-site references.
- The scroll journey section by section, in their words.
- The energy curve — where calm, where intense.
- How they should feel stage by stage, and the ONE moment they must remember.
- One thing this site should do that no site they have seen does (signature move seed).
- How far from premium-minimal: brutalist to dense editorial.
- One unbroken world or distinct scenes?
- What assets do they already have? ("Nothing" is fine — see references/worlds-and-assets.md.)
What ships with it
18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- FINGERPRINT-SCHEMA.json 2.1 KB
- references/devices.md 2.3 KB
- references/feel.md 2.2 KB
- references/grammars.md 2.0 KB
- references/taste-floor.md 1.9 KB
- references/uniqueness.md 2.1 KB
- references/worlds-and-assets.md 1.9 KB
- scripts/doctor.ts 4.1 KB runs code
- scripts/gate.ts 8.4 KB runs code
- scripts/verify/assertions.ts 6.7 KB runs code
- scripts/verify/contrast.ts 4.6 KB runs code
- scripts/verify/index.ts 8.3 KB runs code
- scripts/verify/png.ts 4.3 KB runs code
- scripts/verify/server.ts 2.8 KB runs code
- scripts/workspace.ts 5.7 KB runs code
- templates/engine/page-starter.html 2.5 KB
- templates/engine/savant-motion.css 6.0 KB
- templates/engine/savant-motion.js 16 KB runs code
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 · 148 lines · 201 tokens per session scan A 1a689ed093ec
savant-motion is a skill published in the GitHub repository savant0x/savant-code (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 201 tokens to every session and 1,673 once invoked, about $0.0010 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 2026-09-04.
Other skills, from other repositories
Shade ShadCN install
Guardrails for running pnpm dlx shadcn@latest add in Shade — never overwrite existing components, fresh branch first, swap raw colours for semantic tokens after integrating. Trigger when the user proposes a shadcn add, or when a fresh ShadCN-shaped file lands in apps/shade/src/components/ui.
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
可点击的功能性 Web 原型, 含导航、英雄区、特性区、CTA.
waitlist-page
【模板: 等候名单页 / Waitlist】 【意图】为新产品 / 早鸟内测做一张极简等候页。 【布局】.
design-frontend-dev
Clean Impeccable frontend design skill. Use when the user wants to design, redesign, critique, audit, polish, harden, optimize, adapt, clarify, colorize, animate, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, onboarding, empty states…