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 skills/sma1lboy/rove/clinpx skills add Sma1lboy/rove --skill cligit clone --depth 1 https://github.com/Sma1lboy/roveWhat 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 | $0.00101 | $0.01945 |
| Opus 5 | $0.00051 | $0.00972 |
| Sonnet 5 | $0.00020 | $0.00389 |
| Haiku 4.5 | $0.00010 | $0.00194 |
Grade A, and why
hyperframes-cli 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 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.
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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HyperFrames CLI
Everything runs through npx hyperframes unless project instructions specify a local wrapper. Obey the local wrapper exactly. Requires Node.js >= 22 and FFmpeg.
Workflow
- Scaffold —
npx hyperframes init my-video(orcapturefrom a URL) - Write — author HTML composition (see
../core) - Lint —
npx hyperframes lint - Validate —
npx hyperframes validate(runtime errors + contrast) - Visual inspect —
npx hyperframes inspect - Preview —
npx hyperframes previewopens Studio, the timeline editor where the user can manually edit anything (not just watch). Review there, then ask before rendering. - Render — pick the variant:
- Iterate:
npx hyperframes render --quality draft - Deliver:
npx hyperframes render --quality high --output out.mp4 - CI / cross-host repro:
npx hyperframes render --docker --strict --output out.mp4 - Cloud (long / large):
npx hyperframes lambda render ./my-project --width 1920 --height 1080 --wait(see Lambda below)
- Iterate:
Run lint, validate, and inspect before preview. lint catches missing data-composition-id, overlapping tracks, and unregistered timelines. validate loads the composition in headless Chrome and reports runtime console errors plus WCAG contrast issues. inspect seeks through the timeline and reports text spilling out of bubbles/containers or off the canvas — and, when a *.motion.json sidecar is present, verifies motion intent (entrances firing under seek, stagger order, in-frame, liveness) against that same seeked timeline.
For motion-heavy work, prefer snapshot-driven iteration and a *.motion.json sidecar — see references/lint-validate-inspect.md for the discipline and motion-verification spec.
Agent Conventions
Cross-cutting rules that hold for every command:
--jsonis available on every command exceptrender,preview, andplay. Use it for any agent / CI invocation of the supported commands; output includes a_metaenvelope (cli version, latest available, update advice).renderreports status via stdout + exit code only — verify success with the post-render check below;preview/playare servers, no JSON.doctor --jsonalways exits 0, even when the environment is broken. Gate on the payload'sokfield:npx hyperframes doctor --json | jq -e '.ok' > /dev/null. This insulates pipelines from CLI release churn.- Non-TTY mode is auto-detected. When
stdoutis not a TTY (CI, agents, piped output) the CLI auto-switches to non-interactive;initthen requires--example. Pass--non-interactiveto force this mode even on a TTY. - CI gating on render:
--strictfails on lint errors,--strict-allfails on warnings too,--strict-variablesfails on undeclared--variableskeys. - Paths in
--jsonare redacted —$HOMEbecomes the literal$HOMEso output is safe to paste into bug reports and agent contexts. - Render is user-gated. Never auto-render once the checks pass. Pause at
preview, tell the user the video is editable in Studio, and render only after they approve. - Post-render verification. After
renderreturns exit 0, confirm the output file exists and has plausible size before reporting success:[ -s "$OUTPUT" ] || echo "render produced no output". The CLI prints◇ <path>on success; for long renders also sanity-check duration withffprobe -i "$OUTPUT" -show_format -v error.
What ships with it
6 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.
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 · 109 lines · 101 tokens per session scan A 99d150dcc9a0
hyperframes-cli is a skill published in the GitHub repository Sma1lboy/rove (114 stars, last pushed 2d ago), licensed MIT. It adds 101 tokens to every session and 1,945 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
algorithmic-art
Create original interactive generative art with p5.js, seeded randomness, and meaningful parameter exploration. Use for algorithmic art, flow fields, particle systems, procedural compositions, or browser-based generative sketches; do not use for static poster design, ordinary product UI, or photorealistic image…
canvas-design
Create original static visual artwork as PNG or print-ready PDF, including posters, covers, wall art, editorial compositions, and one-page visual pieces. Use when the deliverable is a static canvas rather than product UI, a slide deck, a document, or interactive generative art.
animated-video
Use when creating animated product launch videos, GSAP timelines, or visual motion assets.
ffmpeg
Video and audio processing with FFmpeg. Use for format conversion, resizing, compression, audio extraction, and preparing assets for Remotion. Triggers include converting GIF to MP4, resizing video, extracting audio, compressing files, or any media transformation task.
hyperframes-media
Audio and media assets for HyperFrames compositions, produced by one shared audio engine (scripts/audio.mjs) — multi-provider TTS (HeyGen / ElevenLabs / Kokoro local), background music + sound effects (HeyGen audio-library retrieval by default, with local Lyria / MusicGen BGM generation and a bundled SFX library as…
lyria
Generate and validate music with Google Lyria 3 through the Gemini Interactions API. Use before calling OpenMontage googlemusic, designing Lyria 3 Clip or Pro prompts, using image-to-music or custom lyrics, choosing between Lyria 3 and Lyria RealTime, diagnosing Google music-generation failures, or preparing…