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/clipkit-video/clipkit/agents-mdgit clone --depth 1 https://github.com/clipkit-video/clipkitWhat 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 | $0.13093 | $0.13093 |
| Opus 5 | $0.06546 | $0.06546 |
| Sonnet 5 | $0.02619 | $0.02619 |
| Haiku 4.5 | $0.01309 | $0.01309 |
Grade A, and why
clipkit AGENTS.md scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
flat card with curl at the rim), `edge_highlight` (the whole light How it starts
The opening of the file, as written. The whole thing — 1,039 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clipkit — Authoring guide (AGENTS.md)
This file is the authoring-time context for AI tools (and humans) writing Clipkit videos. Paste it into a system prompt or attach it to a Claude project. For the formal protocol spec — element types, field semantics, conformance levels, normative MUST/SHOULD/MAY — see
PROTOCOL.md.
Clipkit is a protocol for describing motion-graphics videos as JSON.
A Source document is the list of elements (with timing and
animations) that a conforming runtime turns into frames or MP4.
There are two layers you work with as an author:
- Primitives — the element types defined by the Clipkit Protocol. The formal spec is in PROTOCOL.md. Section 1 below is a quick cheat sheet so you don't have to bounce out for common lookups, but PROTOCOL.md is the source of truth.
- Patterns — authoring-time TypeScript helpers in
@clipkit/patternsthat produce primitive elements. You never reference patterns in a Source JSON; you call them in TS/JS and inline their output. Patterns are documented in section 2 (Pattern catalog).
Section 3 (Recipes) walks through complete example videos showing how patterns compose into a full piece.
0. Which surface to use
Before authoring anything, pick the right surface for your context. There are two — they layer cleanly, no overlap.
| You are running in… | Use… | How |
|---|---|---|
| Claude Code, Cursor, Replit Agent, or any IDE-embedded AI with file + shell access | @clipkit/cli |
Write files (video.ts or a JSON source) using this doc as context. Run npx @clipkit/cli render, validate, or preview via Bash. Skip MCP entirely. |
| Claude.ai chat, Claude Desktop without local tools, or any chat-mode AI without filesystem access | @clipkit/mcp-server |
Call the MCP tools — set_project to build (the full creative canvas), create_promo to compose from prebuilt scenes, add_element/edit_element/delete_element to tweak, preview_still/validate_project/describe_project to check, open_in_editor/render_video to deliver. The server holds state for you. |
| A human developer | @clipkit/cli |
npx @clipkit/cli init my-video, edit files, npx @clipkit/cli render. Same path as IDE-embedded AI. |
| CI / a build script | @clipkit/cli |
One-shot clipkit render input.json --out out.mp4. |
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 · 1,039 lines · 13,093 tokens per session scan A 5b6373af3e4a
clipkit AGENTS.md is an instructions file published in the GitHub repository clipkit-video/clipkit (15 stars, last pushed 21d ago), licensed Apache-2.0. It adds 13,093 tokens to every session, about $0.0655 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
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.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.