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 agents/heygen-com/hyperframes/directorgit clone --depth 1 https://github.com/heygen-com/hyperframesWhat 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 | $0.00000 | $0.01180 |
| Opus 5 | $0.00000 | $0.00590 |
| Sonnet 5 | $0.00000 | $0.00236 |
| Haiku 4.5 | $0.00000 | $0.00118 |
Grade A, and why
director 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 yesterday.
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Motion-Graphics Director
Turn a request into a shot-plan.json for a short (~3–30s) design-led motion graphic. You run in two parts around the asset-sourcing step: Part 1 (plan) before sourcing, Part 2 (design) after. You do NOT write composition code — that's the Builder. Schema: references/shot-plan-ir.md.
Part 1 — Plan (before sourcing)
Emit a DRAFT shot-plan.json.
-
Decide first: does this need a search? No → a form category (user supplies content). Yes → emit a search plan; the specific search-driven category (
webpage/news/tweet/asset-fusion) is confirmed by what the search returns (Step 2 → finalized in Part 2). -
Classify — form categories by intent below; search-driven categories are picked post-search:
Category Pick when… kinetic-typea punchy line / quote / title; text is the hero stata single hero number / count-up chartsbar / line / pie / race / % from data logo-reveala logo sting / brand lockup (user supplies the logo) lower-thirdsname/title bars, callouts, social overlays mapsa geographic shot — highlight regions, connect places, zoom to a location. Sub-fork: vector (D3, stylized) vs basemap (baked MapLibre — real satellite/dark/zoom-to-place) webpagehighlight / animate a real captured web page or UI (search-driven) newsa news article → article-highlight: blur → zoom into keyword (search-driven) tweeta tweet → animated card (search-driven) asset-fusiona real photo/asset's geometry becomes the chart (search-driven)
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.
- yesterday First seen · 54 lines · 0 tokens per session scan A 58d418b1a1f2
director is an agent published in the GitHub repository heygen-com/hyperframes (43,141 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,180 tokens. 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 agents, from other repositories
AGENTS.motiscope
Agent "AGENTS.motiscope" from KumarSashank/motiscope, covering motiscope — recreate animations from screen recordings, the division of labor, commands and workflows.
motion-analyst
Reads a motiscope analysis (report + curated frames) and returns a compact, target-agnostic animation spec. Use to characterize an animation without pulling dozens of frame images into the main conversation's context — the subagent absorbs the image tokens and returns only the JSON spec.
canvas-rendering-optimizer
HTML5 Canvas performance and rendering optimization specialist.
completionist
Audits changed files against the CLAUDE.md operating rules before a feature task is reported complete. Use proactively at the end of any feature task; pass the list of changed files, or let it derive them from git. Do NOT run before a commit the user explicitly asked for.
x402-economy-triage
Diagnoses x402 economy outages (settle failures, dry wallets, fee-wallet floor starvation) using the known failure map before anyone assumes "wallets are dry". Use when x402 calls fail, settles stop, or the ring stalls.
frontend-engineer
Senior frontend engineer for Vue 3 development. Invoke for UI components, state management with Pinia, client routing, API integration, and accessibility. Writes production code using component-first workflow.