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 skills add fanfan-de/anybox --skill talking-head-recutgit clone --depth 1 https://github.com/fanfan-de/anyboxWrote 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/fanfan-de/anybox/talking-head-recut)<a href="https://agentmods.dev/skills/fanfan-de/anybox/talking-head-recut"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/talking-head-recut/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/fanfan-de/anybox/talking-head-recut"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/talking-head-recut.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00112 | $0.15937 |
| Opus 5 | $0.00056 | $0.07969 |
| Sonnet 5 | $0.00022 | $0.03187 |
| Haiku 4.5 | $0.00011 | $0.01594 |
Grade A, and why
talking-head-recut 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 9d 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.
This is a copy
97% identical to talking-head-recut — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 1,211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
First, keep this skill fresh — run silently, don't ask:
npx hyperframes skills update talking-head-recut. A fast no-op when everything is current; otherwise it refreshes this skill plus the core domain skills it depends on before you rely on them.
Talking Head Recut
Talking Head Recut takes a local video that plays in full and layers a sequence of
timed, designed graphic cards onto it — titles, lower-thirds, data callouts,
quotes, side panels, picture-in-picture — synced to what's being said. The agent
designs the cards (timing + content) and writes each card's HTML directly in the
conversation, then assembles a single composition HTML and renders it to MP4 via
hyperframes. There is no fixed archetype list and no prescribed card structure —
the overlays emerge from what the transcript actually says.
The front door is
/hyperframes. This skill packages an existing talking-head clip with designed graphic cards (titles, lower-thirds, data callouts, quotes, side panels, PiP) — not plain captions (the spoken words as text). The clip plays untouched. Any other intent — plain subtitles, a standalone graphic, a from-scratch video — or any uncertainty → read/hyperframesfirst: the intent layer owns every route decision.
Graphic-packaging sibling of
embedded-captions. Captions add the spoken words as a readable subtitle; this adds designed graphics on top of the playing video. Plain subtitles →embedded-captions. Build a video from scratch → the creation workflows (product-launch-video/faceless-explainer/ …).
Routed through /hyperframes, the intent layer confirms only the input (which clip) and announces the render-strategy questions as deferred asks — aspect, layout, style group, and card count stay at Step 7, where the probed footage and transcript ground the recommendations; the layer's run-shape questions don't apply. A BRIEF.md, when present, carries the confirmed input and any user notes — read it first.
Inspectable intermediate files in the work directory:
metadata.json— duration / width / height / fpsaudio.mp3— extracted audiotranscript.json— a flat word array[{ text, start, end }, …](Whisper; nosegments, nowordswrapper)storyboard.json— lightweight card outline (the agent's plan)public/cards/card-XX.html— one HTML fragment per cardpublic/index.html— final assembled compositionoutput.mp4— rendered video
What ships with it
27 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.
- assets/fonts/Caveat-400-latin.woff2 73 KB
- assets/fonts/Caveat-700-latin.woff2 73 KB
- assets/fonts/Inter-400-latin.woff2 23 KB
- assets/fonts/Inter-700-latin.woff2 24 KB
- assets/fonts/LXGWWenKaiTC-400-latin.woff2 19 KB
- assets/fonts/Virgil.woff2 60 KB
- assets/vendor/gsap.min.js 71 KB runs code
- media-contract.test.mjs 1.3 KB runs code
- NOTICE.md 1.8 KB
- references/DESIGN_INDEX.md 9.9 KB
- references/frames/clean.html 2.6 KB
- references/frames/hairline.html 5.7 KB
- references/frames/polaroid.html 5.2 KB
- references/layouts/overlay.html 5.3 KB
- references/layouts/pip.html 4.5 KB
- references/layouts/split.html 3.7 KB
- references/layouts/stack.html 3.4 KB
- references/styles/academic.html 5.9 KB
- references/styles/audit.html 6.0 KB
- references/styles/editorial.html 6.4 KB
- references/styles/geom.html 5.6 KB
- references/styles/minimal.html 4.0 KB
- references/styles/spotlight.html 4.8 KB
- references/styles/swiss.html 5.9 KB
- references/styles/terminal.html 6.8 KB
- references/styles/whiteboard.html 5.7 KB
- references/styles/xhs.html 7.0 KB
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.
- 9d ago First seen · 1,211 lines · 112 tokens per session scan A ec91591f991f
talking-head-recut is a skill published in the GitHub repository fanfan-de/anybox (57 stars, last pushed 29d ago), licensed MIT. It adds 112 tokens to every session and 15,937 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to talking-head-recut, differing in 22 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…