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 J-StaR-Films-Studios/VibeCode-Protocol-Suite --skill zack-higgsfieldgit clone --depth 1 https://github.com/J-StaR-Films-Studios/VibeCode-Protocol-SuiteWrote 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/j-star-films-studios/vibecode-protocol-suite/zack-higgsfield)<a href="https://agentmods.dev/skills/j-star-films-studios/vibecode-protocol-suite/zack-higgsfield"><img src="https://agentmods.dev/badge/skills/j-star-films-studios/vibecode-protocol-suite/zack-higgsfield/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/j-star-films-studios/vibecode-protocol-suite/zack-higgsfield"><img src="https://agentmods.dev/badge/skills/j-star-films-studios/vibecode-protocol-suite/zack-higgsfield.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 45 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00149 | $0.03532 |
| Opus 5 | $0.00075 | $0.01766 |
| Sonnet 5 | $0.00030 | $0.00706 |
| Haiku 4.5 | $0.00015 | $0.00353 |
Grade A, and why
zack-d-films 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 8d 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.
`sandbox_exec({restart:true, command:"set -e; for b in ffmpeg ffprobe python3 curl jq; do command -v $b >/dev/null; done; python3 -c 'import faster_whisper'; mkdir -p zack/{blocks,audio,output}"})` How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zack-d-films
Recreates the Zack D Films production line — normally a 50-person team — as one Claude chat over Higgsfield MCP. The user experience follows five acts, in this exact order, matching the channel's real growth engine: SCRIPT → VISUALS → ANIMATION → VOICE → EDIT.
HOW TO READ THIS FILE: execute Phases 1→8 IN ORDER. Each phase has a GATE. Long templates live in
references/— read them when the phase says so.references/replication-troy.mdis the canonical worked example (the Trojan Horse short): when in doubt about any phase's output shape, imitate it.
Runtime contract
- Models are LOCKED: stills/character sheets →
seedream_v5_pro· animated blocks →gemini_omni· narration →seed_audio. Never substitute. - Aspect is 9:16 unless the user explicitly asks for 16:9. Pass
aspect_ratioexplicitly on EVERY image and video call — it never inherits. - All shell work (probe, Whisper timing, ffmpeg edit, upload) runs in
Higgsfield
sandbox_exec— never on the client. Preflight a fresh run with:sandbox_exec({restart:true, command:"set -e; for b in ffmpeg ffprobe python3 curl jq; do command -v $b >/dev/null; done; python3 -c 'import faster_whisper'; mkdir -p zack/{blocks,audio,output}"}) - Poll every job to a terminal state.
completedis the only good state. Onfailed/nsfw: RETRY LADDER (bottom of file). If no dedicated status tool is available,job_display({id})returns the job's status + result URLs; wait between polls withsandbox_exec({command:"sleep 50"})(~40–60s for images, poll video jobs every ~60s; blocks take 2–6 min). medias[].rolemay be auto-coerced by the server (e.g.image→image_referenceson seedream). That's fine — read theadjustmentsfield, don't fight it.- If a
gemini_omnicall returns a preset RECOMMENDATION instead of a job, resubmit the same call withdeclined_preset_idset to that preset's id. Never ask the user about it. - Maintain
zack/manifest.jsonin the sandbox (or an equivalent local notes block) recording: locked style formula, asset job ids, per-block prompts + job ids + statuses, narration job id, beat map, edit map. It is the resumable source of truth. - Never expose model names, phase names, or internal mechanics in chat. The user sees creative substance and approval gates only.
- Characters NEVER talk on screen (no lip-sync). The narrator is external. Every video prompt includes "characters only emote and gesture, they do NOT talk" and a mute/diegetic-only audio note.
- No real brand / studio / IP names in prompts. No on-screen text in generations (annotations are shapes, not words).
What ships with it
6 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.
- 8d ago First seen · 227 lines · 149 tokens per session scan A c54819156228
zack-d-films is a skill published in the GitHub repository J-StaR-Films-Studios/VibeCode-Protocol-Suite (24 stars, last pushed yesterday), licensed ISC. It adds 149 tokens to every session and 3,532 once invoked, about $0.0007 per session on Opus 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 2026-09-03.
Other skills, from other repositories
gpt-image-2-style-library
Choose GPT-Image2 / gpt-image-2 visual styles and industrial prompt templates from the awesome-gpt-image-2 style library. Use when an agent needs to create, rewrite, classify, or improve image-generation prompts with repository-backed templates, categories, style tags, scene tags, pitfalls, and example cases.
seedance-prompt
This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.
short-drama-storyboard
A workflow for turning a Chinese short-drama script and its visual facts into a shot-by-shot storyboard with frozen starting-frame prompts.
short-drama-video-prompts
A writing guide for turning approved short-drama storyboards and starting images into copy-ready prompts for generating video scenes. It covers both image-to-video prompts, which use a reference image, and text-to-video prompts, which describe the scene in words.
short-drama-develop
A Chinese-language writing workflow for turning novel, short-drama, or comic-drama ideas and source material into an adaptation plan, story direction, creative brief, story engine, and episode map.
short-drama-write
A writing workflow for creating or revising a shootable Chinese short-drama or animated-drama episode in Markdown.