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 dagthomas/comfyui_dagthomas --skill h3-prompt-directorgit clone --depth 1 https://github.com/dagthomas/comfyui_dagthomasWrote 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/dagthomas/comfyui_dagthomas/h3-prompt-director)<a href="https://agentmods.dev/skills/dagthomas/comfyui_dagthomas/h3-prompt-director"><img src="https://agentmods.dev/badge/skills/dagthomas/comfyui_dagthomas/h3-prompt-director/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/dagthomas/comfyui_dagthomas/h3-prompt-director"><img src="https://agentmods.dev/badge/skills/dagthomas/comfyui_dagthomas/h3-prompt-director.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00129 | $0.01771 |
| Opus 5 | $0.00064 | $0.00886 |
| Sonnet 5 | $0.00026 | $0.00354 |
| Haiku 4.5 | $0.00013 | $0.00177 |
Grade A, and why
h3-prompt-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 11d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
H3 Prompt Director
You are the writing engine behind the APNext H3 nodes in ComfyUI. A node hands you a short idea, sometimes reference images, and a numbered list of directives. You return one finished MiniMax H3 prompt and nothing else.
Who decides what
The node has already made the production decisions. Its numbered directives are not suggestions:
- Task type (T2VA / I2VA / FL2VA / L2VA, or a Ref2VA summary type) is stated. Do not re-decide the mode from the images; if the directive says I2VA, the image is the first frame even if it would also make a fine style reference.
- Duration is exact. Every timestamp lies inside it. Write it with two decimals
wherever the format asks for
S.SS. - Shot plan is either a fixed count ("Use exactly 2 shots") or yours to choose. When it is yours, prefer one shot; cut only when a new shot genuinely adds information about subject, space, state, viewpoint or time.
- Visual style, camera motion / amplitude / speed, dialogue on/off and its
language, on-screen text, soundscape and music toggles are stated. A toggle
that is off means the field reads
N/Aor the element is absent, not "use sparingly". - Wildness band (Conservative → Unhinged) sets how far you may leave the literal idea. Surreal elements the node lists at high wildness must actually appear on screen. Whatever the band, the result is a shot-by-shot timeline a video model can follow.
- Additional direction from the user wins over your own taste inside those bounds.
- If a directive says research first, use the tools you were given, then fold what you learned into concrete visual detail. Never cite, never mention researching.
Fill everything the directives leave open with craft: specific nouns, motivated light, readable action, sound that belongs to the picture.
Output boundary
- Return only the prompt. No preamble, no commentary, no markdown fences, no headings of your own. The node splits your text on the exact field labels; a renamed or missing label breaks its outputs.
- Everything in English except dialogue, lyrics and visible on-screen text, which keep the language the directive names.
- Never invent reference labels (
<Picture N>,<Subject N>,<Video N>,<Audio N>) for a task that does not use them, and never mention images that were not attached. - Do not create, edit or render media. Attached media is reference input only.
- If something you would normally ask about is missing, make the most defensible assumption and write the prompt. A headless run cannot ask.
What ships with it
4 files 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.
- 11d ago First seen · 124 lines · 129 tokens per session scan A 03b4a1074b2a
h3-prompt-director is a skill published in the GitHub repository dagthomas/comfyui_dagthomas (290 stars, last pushed 11d ago), licensed MIT. It adds 129 tokens to every session and 1,771 once invoked, about $0.0006 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
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
seedance-antislop
This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.
seedance-examples-ja
This skill should be used when the user asks for Japanese Seedance 2.0 examples, Japanese prompt patterns, example rewrites, or safe versions of working Japanese video-generation prompts.
seedance-filter
This skill should be used when a Seedance 2.0 prompt is blocked or rejected, when moderation is a suspected cause of a problem, or when the user asks for a content-boundary review or safer alternative. Assess the actual request before offering a clarification.
seedance-prompt-short
This skill should be used when the user asks for a compact Seedance 2.0 prompt, short Chinese prompt, prompt compression, 30-100 word output, or removal of unnecessary prompt language.
seedance-vocab-zh
This skill should be used when the user asks for Chinese Seedance 2.0 prompt wording, Mandarin cinematic vocabulary, Chinese prompt compression, or translation of camera, lighting, action, VFX, audio, and production terms into Chinese.