Borrowing it
Nothing to install: this file belongs to miikkij/aimeat-protocol. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/miikkij/aimeat-protocol/main/.claude/skills/aimeat-video/SKILL.mdgit clone --depth 1 https://github.com/miikkij/aimeat-protocolWrote 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/miikkij/aimeat-protocol/aimeat-video)<a href="https://agentmods.dev/skills/miikkij/aimeat-protocol/aimeat-video"><img src="https://agentmods.dev/badge/skills/miikkij/aimeat-protocol/aimeat-video/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/miikkij/aimeat-protocol/aimeat-video"><img src="https://agentmods.dev/badge/skills/miikkij/aimeat-protocol/aimeat-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00094 | $0.02275 |
| Opus 5.5 | $0.00038 | $0.00910 |
| Sonnet 5.5 | $0.00019 | $0.00455 |
| Haiku 4.5 | $0.00009 | $0.00228 |
Grade A, and why
aimeat-video 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 1mo 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Making a video of AIMEAT
Every video here shows the production node with real data. Nothing is mocked and no slide is
re-narrated: the deck says what is claimed, the video shows it moving. Three tools cover the
three kinds of footage, and all three live in aimeat/scripts/demo-video/, which is gitignored
on purpose (marketing tooling, plus login paths). They exist on Jouni's MAIN machine only, in the
main checkout, together with genimages/videos/ and its two worked examples: a fresh clone, a
worktree and his other machines do not have them (checked 2026-09-19, when neither folder was on
the machine the check ran on). So look first: ls aimeat/scripts/demo-video from the main
checkout. When it is absent, say so and ask, rather than rebuilding the tools from this page.
| You need | Tool | Output |
|---|---|---|
| A browser DOING things, scripted step by step (register, build a board, buy a listing) | record.mjs + cut.mjs with a scenes.<name>.json manifest |
genimages/videos/<name>/<name>.mp4 + <name>.marks.json |
| A browser WATCHING things happen that someone else does (an agent over MCP, a scheduled job) | watch.mjs --url=… --seconds=… --name=… |
same, plus live/NNNN.png every 5 s |
| A cut from stills and existing clips with narrator cards (pitch, overview, montage) | stills/render_cards.py + stills/build.py on a project folder with cut.json |
genimages/videos/<project>/out/<name>.mp4 |
aimeat/scripts/demo-video/README.md documents the manifest step types for the performer;
genimages/videos/mainos/README.md is the worked example of an ad cut from generated clips;
genimages/videos/pitch2026/cut.json is the worked example of a stills cut (the Maria01 pitch
video, ten scenes, 2:56).
Before the first capture
- ffmpeg on PATH, Python with Pillow, and for the performer
@playwright/test(already a devDep inaimeat/; run its scripts fromaimeat/so it resolves). - Signed-in state for the performer and the camera:
node scripts/demo-video/_login-state.mjs(fromaimeat/). It readsdocs/internal/prod-login-happydude500001.json(gitignored, main checkout only), signs in on aimeat.io and on the ORIGAMI origin, and writesgenimages/videos/_state/prod-owner-state.json, which everyscenes.*.jsonpoints at. The ORIGAMI session is bridge-based and goes stale; re-run this before a shoot rather than debugging a stale state. - Stills are captured with the Playwright MCP server in a 1920×1080 viewport
(
browser_resizefirst). Sign in through the app's own Sign In button: it opens the app-grant page on aimeat.io, and the credentials go into#aimeat-username/#aimeat-passwordthere. Apps on their own subdomains share that session afterwards. - A capture lands in the repo root by default. Move it into the project's
src/at once; no scratch files stay in the root.
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.
- 1mo ago Changed · +4 lines a507d3474de0
- 2mo ago First seen · 134 lines · 94 tokens per session scan A c8df8330c955
aimeat-video is a skill published in the GitHub repository miikkij/aimeat-protocol (10 stars, last pushed today), licensed MIT. It adds 94 tokens to every session and 2,275 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
coordinate-agent-work
Coordinate independent coding or research agents across host sessions and linked Git worktrees through AgentTool Collab's local journal. Use when starting or resuming credential-bound coordination, splitting parallel work, claiming before overlapping edits, polling or acknowledging events, attaching evidence…
capability-conductor
A guide for finding and combining existing agent skills for one task while keeping track of where each skill came from and what limits it has.
nen-math-card
Frame a mathematical challenge as a bounded proof, model, or measurement inquiry and decide whether it can construct, repair, choose, or clarify anything. Use when a user asks whether a math problem is useful, wants to turn a competition or puzzle into reusable understanding, needs to separate formal proof from world…
nen-common-ground
Model several explicitly stated decision boundaries as convex feasible regions and return either shared room, a small conflict witness, or an honest refusal of the model. Use when the user invokes Helly, common-ground geometry, 共域, local-to-global agreement, constraint reconciliation, or a KINGDOM challenge about…
scriptwriter-room
Focused on writers' room operations — creating rooms with a seed prompt, contributing signed scenes/dialogue/stage-directions/twists/chaos-cards/notes, subscribing to the SSE live stream, polling for new contributions. Use when the user wants to actually draft something with peers, draw a chaos card to seed a scene…
scriptwriter-rrr
Focused on the REAL RECOGNISE REAL cascade flow specifically — opening cascades with a peer, escalating depth, verifying chains, surfacing wall refusals with their meaning. Use when the user explicitly references RRR depth, cascade verification, alternation walls, or the "I know you know I know" mutual-recognition…