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 manishiitg/coding-agent-loop --skill generated-video-qualitygit clone --depth 1 https://github.com/manishiitg/coding-agent-loopWrote 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/manishiitg/coding-agent-loop/generated-video-quality)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/generated-video-quality"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/generated-video-quality/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/manishiitg/coding-agent-loop/generated-video-quality"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/generated-video-quality.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 | $0.00067 | $0.01935 |
| Opus 5.5 | $0.00027 | $0.00774 |
| Sonnet 5.5 | $0.00013 | $0.00387 |
| Haiku 4.5 | $0.00007 | $0.00194 |
Grade A, and why
generated-video-quality 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 1mo 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quality checks specific to generated footage
Use this only for the final assembled delivery MP4, alongside video-quality;
do not run it after each generated preview clip. video-quality covers what
applies to every video this product makes:
decode/duration/dimensions, black frames and freezes, legible text, a
coherent edit, and a passing quality-report.json. Run it first and in
full -- this skill does not repeat it.
What this skill adds is the failure modes a camera cannot produce, because they only exist in generated footage: a face that drifts across shots, a sixth finger, a background that reflows between frames, motion that snaps rather than continues across a cut. A technical pass and a coherent-edit pass both miss these, because nothing about them fails to decode, and nothing about them is a black frame.
Add these checks to the same quality-report.json checks map
video-quality writes, alongside technical/visual/audio/content/
captions/promise -- one report, one file, not a second document to
reconcile:
"checks": {
"character_consistency": {"status": "pass", "evidence": ["officer.png vs shots 3,7,12: consistent"]},
"generation_artifacts": {"status": "pass", "evidence": ["no extra limbs, warped hands, or gibberish text observed"]},
"temporal_coherence": {"status": "pass", "evidence": ["motion continues across every stitch point checked"]},
"motion_plausibility": {"status": "not_applicable", "evidence": ["no complex physics in this cut"]},
"lip_sync": {"status": "pass", "evidence": ["dialogue in shots 2,5 reads in sync"]},
"clip_color_consistency": {"status": "pass", "evidence": ["black level/white balance consistent shot to shot"]},
"prompt_adherence": {"status": "pass", "evidence": ["each shot matches its shot-list framing and camera move"]},
"narration_alignment": {"status": "pass", "evidence": ["visuals match narration-manifest.md's measured durations"]}
}
Same discipline as the base contract: every check here is pass or
genuinely not_applicable with evidence, never not_applicable to hide a
check you didn't run. A candidate with no recurring character still runs
character_consistency as not_applicable -- it does not get skipped.
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.
- 1mo ago Changed · +2 lines dac44421f12b
- 2mo ago First seen · 170 lines · 67 tokens per session scan A 06d7fa841846
generated-video-quality is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 1,935 once invoked, about $0.0003 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.
Other skills, from other repositories
agency-geoai-ml-engineer
Geospatial machine learning specialist who builds models for feature extraction, object detection, image segmentation, and land cover classification from satellite and aerial imagery.
digital-health-clinical-asr-eval
Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipasource diagnostic). Not for ASR auth (/riva-asr).
digital-health-clinical-asr-finetune
Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for generic word boosting (use /finetune-asr).
cdf-curation-and-retrieval
NVIDIA CDF curation and retrieval. Cosmos Curator video and image pipelines (split, dedup, shard, annotate) with filtering, captioning, and embedding. Cosmos Dataset Search ingest, search, and capability qualification. TAO data mining embeddings and neighbor matching. Ships domain event catalogs, including workplace…
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.
kermt-continue-pretrain
Continue KERMT pretraining on a custom SMILES corpus with a groverbase, cmim, or hybrid checkpoint. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HFTOKEN if configured. Run containerized training and write model bundles, prepared data, logs, and checkpoints to user-selected…