Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/open-video-ai/open-videonpx agentmods add skills/open-video-ai/open-video/h3-videoWrote 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/open-video-ai/open-video/h3-video)<a href="https://agentmods.dev/skills/open-video-ai/open-video/h3-video"><img src="https://agentmods.dev/badge/skills/open-video-ai/open-video/h3-video/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/open-video-ai/open-video/h3-video"><img src="https://agentmods.dev/badge/skills/open-video-ai/open-video/h3-video.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 | $0.00103 | $0.03471 |
| Opus 5.5 | $0.00041 | $0.01388 |
| Sonnet 5.5 | $0.00021 | $0.00694 |
| Haiku 4.5 | $0.00010 | $0.00347 |
Grade A, and why
h3-video scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf http://127.0.0.1:8188/system_stats || ( How it starts
The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenVideo skill · v0.1.0
Brand: OpenVideo (always lead with this). MiniMax H3 is the model OpenVideo drives.
Job: use OpenVideo so an agent produces good product video, not a random diffusion click. Quality comes from prompt craft + correct mode + validated settings, not secret samplers.
0. Paths (env-first)
Recommended sibling layout (any parent dir name; no machine-absolute paths):
parent/
├── open-video/ # THIS product — CLI, backends, skills ← work here
└── lab/ # ComfyUI + weights (not git)
| What | Path / env |
|---|---|
| Product root (CLI, skills) | $OPEN_VIDEO_ROOT (this checkout) |
| Install / pull / run | From product root: ./scripts/install.sh, python -m open_video … |
| Lab engine + weights | $OPEN_VIDEO_LAB / $H3_LAB (sibling lab/ with ComfyUI + h3_models/) |
| Weights env | export OPEN_VIDEO_MODELS=$H3_LAB/h3_models |
| ComfyUI URL | export OPEN_VIDEO_COMFYUI=http://127.0.0.1:8188 (default) |
Resolve product root (never hardcode a machine path):
# Prefer env, else directory of this skill → repo root
export OPEN_VIDEO_ROOT="${OPEN_VIDEO_ROOT:-$(cd "$(dirname "$0")/../.." 2>/dev/null && pwd)}"
cd "$OPEN_VIDEO_ROOT"
Lab harness (same ComfyUI) when you keep a sibling runtime:
export OPEN_VIDEO_LAB="${OPEN_VIDEO_LAB:-$OPEN_VIDEO_ROOT/../lab}"
export H3_LAB="${H3_LAB:-$OPEN_VIDEO_LAB}"
export OPEN_VIDEO_MODELS="${OPEN_VIDEO_MODELS:-$H3_LAB/h3_models}"
Product = open-video/ checkout. lab/ is runtime only — never the product root.
1. Quality hierarchy (what actually moves the needle)
| Rank | Lever | Rule |
|---|---|---|
| 1 | 3-field prompt | Official structure; concrete visible/audible detail; camera type+amplitude+speed; dialogue in <d>[lang]…</d> |
| 2 | Mode | T2V / I2V / FL2VA chosen correctly from inputs |
| 3 | Resolution / steps | 1344×768, 20 steps, res_multistep + simple (defaults in harness) |
| 4 | Quant | INT8 on 5090-class (the only tier pull installs); lower VRAM → recommend-quant may suggest nf4/w4, which are manual + experimental — never auto-installed |
| 5 | Duration | 5–10 s sweet spot (max 15 s / shot); multi-shot via cut times or open-video director skill |
| 6 | Review | Watch / extract frames; fix prompt; re-run. Dual vision gate only when shipping |
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 scan C → A 24b3aabd7ec9
- 1mo ago First seen · 307 lines · 103 tokens per session scan C 8383e461a3b4
h3-video is a skill published in the GitHub repository open-video-ai/open-video (118 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 103 tokens to every session and 3,471 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
video-gen
Use when generate videos with AI models — Runway, Kling, Sora, Pika, Seedance 2.0, Grok Imagine, Veo. Text-to-video, image-to-video, video extension, multi-modal references. Use when generating video from text prompts, animating images, or creating AI video content.
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
bio-ortholog-inference
Pull pre-computed ortholog calls from public databases (OrthoDB, Ensembl Compara, OMA browser, eggNOG, PANTHER, KEGG Orthology, HomoloGene) via their REST APIs. Use when orthologs are already curated upstream, when the question is "what is the X ortholog of Y" rather than "how to infer orthology de novo", when…
bioprobench
Score an LLM's biological-protocol reasoning on the BioProBench benchmark: protocol QA, step ordering, error detection, protocol generation, and LLM-judged error reasoning; or generate the responses.
alphafold2
Predict protein structure for monomers and multimers with AlphaFold2 via the ColabFold runner (Mirdita et al. 2022, github.com/sokrypton/ColabFold; AlphaFold2 Jumper et al. 2021). Reach for this skill to fold a sequence or complex with the AF2/AF2-Multimer evoformer, to validate designed sequences by self-consistency…
audit-dataset
Audit tabular datasets before analysis or training for schema drift, missing values, duplicate rows or IDs, target imbalance, and entity or group leakage across splits using pure-stdlib helpers.