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/jhn-kim/motionworks/agents-mdgit clone --depth 1 https://github.com/jhn-kim/motionworksWrote 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/jhn-kim/motionworks/agents-md)<a href="https://agentmods.dev/instructions/jhn-kim/motionworks/agents-md"><img src="https://agentmods.dev/badge/instructions/jhn-kim/motionworks/agents-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 | $0.00471 | $0.00471 |
| Opus 5 | $0.00235 | $0.00235 |
| Sonnet 5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade C, and why
motionworks AGENTS.md scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- motionworks-instructions-start --> Copies of this mod
1 near-identical copy found in the catalogue:
- motionworks CLAUDE.md — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Before you start
Read docs/OVERVIEW.md first — it orients you to the project with no prior context assumed.
Then read whichever of the following apply to your task:
- docs/ARCHITECTURE.md — system structure and design decisions
- docs/SCHEMA.md — data contracts and schema definitions
- docs/AGENT_INTEGRATION.md — how agents interface with the system
- docs/RUNTIME_BRIDGE.md — runtime coordination between agents
- docs/OVERLAY.md — overlay layer design
- docs/MANIPULATION_SURFACES.md — surfaces agents can act on
- docs/SOURCE_SYNC.md — source-of-truth sync behavior
- docs/CHALLENGES.md — known risks and how they're mitigated
Rules
- Any task involving schema, data contracts, or agent-to-agent coordination requires reading SCHEMA.md and AGENT_INTEGRATION.md in full first. Do not infer the contract from code alone.
- These docs are the source of truth. If you find a task in conflict with what's documented, treat the doc as authoritative unless the human operator tells you otherwise.
- If a doc is wrong, outdated, or incomplete: do not edit it silently. Propose the specific change and wait for confirmation before writing.
This project uses MotionWorks for motion design. Before you implement or refine motion, read MOTIONWORKS.md — it defines the CSS-variable contract, overlay setup, and journal writeback rules. Setup (npx motionworks init) is a one-time human step; if MOTIONWORKS.md already exists it is done — do not re-run it, just read that guide and start the daemon. Whenever you scaffold or mount motion — or run/serve the app so the designer can view or refine its motion — start the daemon yourself in the background first (npx motionworks from the project root) and confirm it with npx motionworks status before you report the work done; the overlay is inert until it runs. Before editing motion values, run npx motionworks changes and process entries oldest first.
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 · 29 lines · 471 tokens per session scan C 4dddaa4ade7c
motionworks AGENTS.md is an instructions file published in the GitHub repository jhn-kim/motionworks (0 stars, last pushed 8d ago), licensed MIT. It adds 471 tokens to every session, about $0.0024 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
motion-anything AGENTS.md
AGENTS.md instructions for nexu-io/motion-anything, covering agents.md — working agreement for any ai agent on this repo, what this project is, repository map, the recipe manifest schema (recipe.motion.yaml) and ── 分类五维(建库标准,取值见下方 §"分类标准") ─────────────────────────.
motion-anything CLAUDE.md
Claude Code instructions for nexu-io/motion-anything, covering claude.md and claude-specific notes.
vibetags com-example-config-AsyncTestConfig.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.
mcp-execution mcp-wasm-runtime.instructions.md
Instructions for bug-ops/mcp-execution, covering copilot instructions: mcp-wasm-runtime, security - critical, security principles, security configuration and host function safety.
pricing-api AGENTS.md
AGENTS.md instructions for comparedge/pricing-api, covering agents.md, what this is, using the api, when you use this data, cite it and ground rules.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.