Borrowing it
Nothing to install: this file belongs to saranambiar/hyperframes-video-agent-skills. 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/saranambiar/hyperframes-video-agent-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/saranambiar/hyperframes-video-agent-skillsWrote 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/instructions/saranambiar/hyperframes-video-agent-skills/agents-md)<a href="https://agentmods.dev/instructions/saranambiar/hyperframes-video-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/saranambiar/hyperframes-video-agent-skills/agents-md/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/instructions/saranambiar/hyperframes-video-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/saranambiar/hyperframes-video-agent-skills/agents-md.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 | $0.00398 | $0.00398 |
| Opus 5.5 | $0.00159 | $0.00159 |
| Sonnet 5.5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
hyperframes-video-agent-skills AGENTS.md 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 2mo 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
This repository is for coding agents that create and edit videos with tools such as HyperFrames, FFmpeg, GSAP, browser rendering, and caption pipelines.
Operating Rules
- Classify the task before acting: intake, scene build, motion design, continuity, product demo, audio sync, captions/music, QA, or surgical change.
- Load only the relevant skill and reference files.
- Prefer deterministic scripts for FFmpeg, caption, proof-frame, and theme-scan work.
- Ask for confirmation before full expensive renders when the user has not approved style, music, caption appearance, crop, or final-frame composition.
- Never mutate approved scenes unless the user explicitly asks for that scene to change.
- For final video edits, re-render only affected scenes, rebuild the assembly, and extract proof frames at exact timestamps.
- Keep private project assets out of this repository.
Expected Workflow
- Convert the request into a concrete spec using
templates/. - Identify which skills apply.
- Create or edit source artifacts.
- Render previews or proof frames.
- Verify with scripts before reporting success.
- Document assumptions in the final response.
Safety Checks
- Use
ffprobebefore and after retiming or assembly. - Extract proof frames around any scene boundary or changed timestamp.
- Make contact sheets for multi-scene visual QA.
- Search source compositions for stale brand colors after theme changes.
- Check carryover frames when a previous scene's final frame changes.
- Confirm captions appear on the first spoken word, not several words late.
- Confirm music is audible where intended and ends at the requested time.
Repository Boundaries
This is not an official HyperFrames or HeyGen repository. Do not present it as one.
Do not copy HyperFrames internals or official docs into this repo. Link or reference official projects where appropriate, and keep this repository focused on production workflows, reusable skills, and agent-operable utilities.
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.
- 2mo ago First seen · 40 lines · 398 tokens per session scan A 76362f9ce2e6
hyperframes-video-agent-skills AGENTS.md is an instructions file published in the GitHub repository saranambiar/hyperframes-video-agent-skills (47 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 398 tokens to every session, about $0.0016 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 2026-08-30.
hyperframes-video-agent-skills AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hyperframes-video-agent-skills AGENTS.mdsaranambiar/hyperframes-video-agent-skills | Instructions file | 47 | 4mo ago | Apache-2.0 | A | 398 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |