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 saranambiar/hyperframes-video-agent-skills --skill render-qa-and-surgical-changesgit 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/skills/saranambiar/hyperframes-video-agent-skills/render-qa-and-surgical-changes)<a href="https://agentmods.dev/skills/saranambiar/hyperframes-video-agent-skills/render-qa-and-surgical-changes"><img src="https://agentmods.dev/badge/skills/saranambiar/hyperframes-video-agent-skills/render-qa-and-surgical-changes/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/saranambiar/hyperframes-video-agent-skills/render-qa-and-surgical-changes"><img src="https://agentmods.dev/badge/skills/saranambiar/hyperframes-video-agent-skills/render-qa-and-surgical-changes.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 | $0.00083 | $0.00924 |
| Opus 5 | $0.00042 | $0.00462 |
| Sonnet 5 | $0.00017 | $0.00185 |
| Haiku 4.5 | $0.00008 | $0.00092 |
Grade A, and why
render-qa-and-surgical-changes 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.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Render QA And Surgical Changes
Use this skill when the video is nearly done or already approved and changes must be controlled.
Surgical Edit Rules
- Patch source artifacts, not the final MP4, when source scenes and assembly scripts exist.
- Re-render only affected scene(s).
- Rebuild the final assembly from the current approved timeline.
- Do not redesign, retime, or re-sync unrelated sections.
- Search for duplicated/carryover frames before declaring done.
- Extract proof frames at exact timestamps requested by the user.
Use templates/change-request.md before implementing a final tiny change.
QA Sequence
-
Probe the final render.
- Duration.
- Resolution.
- Frame rate.
- Audio stream.
- Sample rate and channels.
-
Extract proof frames.
- Scene boundaries.
- Changed timestamps.
- Caption style frames.
- Final CTA or ending frame.
-
Build a contact sheet.
- Include all risky timestamps.
- Include before/after frames for surgical changes.
-
Check audio.
- Narration present.
- Music bed audible where intended.
- Final silence or fade timing correct.
- No clipped words after trims.
-
Check theme and text.
- Search for stale colors.
- Search duplicated labels in carryover scenes.
- Verify logos and product footage were not recolored accidentally.
Read references/failure-modes.md for common regressions.
Scripts
Use repo scripts when available:
scripts/probe_media.pyscripts/extract_proof_frames.pyscripts/make_contact_sheet.pyscripts/build_ass_captions.pyscripts/scan_theme_colors.pyscripts/timeline_manifest_to_ffmpeg.py
Acceptance
Report:
- Final video path.
- Probe summary.
- Proof frame/contact sheet paths.
- Files changed.
- Exact checks performed.
- Any unverified subjective item.
Exact Timestamp Checks
When the user names a timestamp:
- Extract a frame at that exact time.
- Extract one frame slightly before if appearance timing matters.
- Extract one frame slightly after if disappearance timing matters.
- Inspect the rendered final, not only the source scene.
- If the same visual appears in the next scene, extract the boundary frame too.
What ships with it
1 file 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.
- 9d ago First seen · 150 lines · 83 tokens per session scan A 313e76110ed6
render-qa-and-surgical-changes is a skill published in the GitHub repository saranambiar/hyperframes-video-agent-skills (47 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 83 tokens to every session and 924 once invoked, about $0.0004 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
short-drama-delivery-audit
Internal deterministic delivery gate for meta-short-drama. Verifies real-provider image/video receipts, parent-owned paid-submission dispositions, runtime fallback evidence, decodability, and content-versus-final duration with ffprobe.
sprite-gen
Generate clean 2D game sprites and animation atlases with a component-row pipeline: base identity, numeric sprite-request SSoT, per-state layout guides, image-gen row strips, chroma-key alpha cleanup, connected-component frame extraction, cell-based atlas composition, QA reports, and runtime manifest framelayout. Its…
review-ugc-render
Mandatory pre-publish review gate for a UGC video render. Transcribes the finished render's AUDIO with Whisper and word-diffs it against the approved spoken script, then gates setfinalrender — blocking a render whose generated audio mis-voices a word (e.g. the approved "human-vetted" spoken as "human witted"), drops…
sc-skill
Capture deterministic macOS screenshots for testing, docs, release notes, and marketing assets. Use when asked to automate app screenshots, batch-generate screenshot sets, standardize window sizing/composition, or choose between Peekaboo and native macOS screenshot tooling.
Image Processing Testing
Testing image processing pipelines including format conversion, resize quality, metadata handling, watermark verification, and thumbnail generation.
hyperframes-cli
HyperFrames CLI dev loop — npx hyperframes for scaffolding (init), validation (lint, inspect), preview, render, and environment troubleshooting (doctor, browser, info, upgrade). Use when running any of these commands or troubleshooting the HyperFrames build/render environment. For asset preprocessing commands (tts…