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 instructions/ardha27/motion-superpowers/claude-mdgit clone --depth 1 https://github.com/ardha27/motion-superpowersWrote 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/instructions/ardha27/motion-superpowers/claude-md)<a href="https://agentmods.dev/instructions/ardha27/motion-superpowers/claude-md"><img src="https://agentmods.dev/badge/instructions/ardha27/motion-superpowers/claude-md.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 | $0.00272 | $0.00272 |
| Opus 5 | $0.00136 | $0.00136 |
| Sonnet 5 | $0.00054 | $0.00054 |
| Haiku 4.5 | $0.00027 | $0.00027 |
Grade A, and why
motion-superpowers CLAUDE.md 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.
What it actually says
Agent Instructions: Motion Superpowers
You are an expert motion graphics and creative engineering agent. When working in repositories with this skill, follow these rules strictly:
1. Grounded Research First
- Never invent metrics, benchmark results, or technical architecture claims.
- Look up official documentation and primary release notes before drafting video copy.
- Keep copy human: remove emojis from on-screen graphics, eliminate em dashes, and avoid marketing fluff.
2. Deterministic Frame Timelines
- All visual transitions and component states must be pure functions of the composition clock (
frame/useCurrentFrame()). - Never use non-deterministic JavaScript timers or random number generators without fixed seeds.
3. Style Rulebook Enforcement
- Select exactly one
MOTION.mddefinition fromreferences/at the start of a project. - Match all duration scales, easing equations, and stagger timings to that rulebook.
- Never mix spring parameters from different design systems inside the same scene.
4. Visual Test-Driven Development (TDD)
- Extract still frames at transition points (e.g. frame 15, 30, 60) to verify alignment and typography before rendering the full video.
- Probe the rendered output with
ffprobeto verify duration, dimensions, and audio stream integrity.
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 · 22 lines · 272 tokens per session scan A 31c9951d8242
motion-superpowers CLAUDE.md is an instructions file published in the GitHub repository ardha27/motion-superpowers (1 stars, last pushed 19d ago), licensed MIT. It adds 272 tokens to every session, about $0.0014 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 2026-08-31.
Other instructions, from other repositories
remocn CLAUDE.md
Claude Code instructions for Remocn/remocn, covering remocn, что это, целевая аудитория, архитектура and два уровня компонентов.
flowix CLAUDE.md
Claude Code instructions for text2future/flowix, covering claude.md, 命令, dev / prod 并存打包, macos 本地生产包 ad-hoc 签名 and macos 发布流水线（developer id 直分发 + notarization）.
rembric CLAUDE.md
Claude Code instructions for susomejias/rembric, covering claude.md, quick reference, claims need evidence, architecture and data access pattern.
pilot-shell CLAUDE.md
Claude Code instructions for maxritter/pilot-shell, a project described as: Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software with spec-driven development, TDD, persistent memory, quality gates, code intelligence, human oversight, and end-to-end verification.
sand AGENTS.md
AGENTS.md instructions for onorbumbum/sand, covering core beliefs by phase, interaction style, coding assistance and key references.
unknowns CLAUDE.md
Instructions for hiendinhngoc/unknowns, covering claude.md, repo shape, skill conventions, title and adding or changing skills.