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 Phantomlau3674/ai-film-director-workbench --skill ai-film-production-systemgit clone --depth 1 https://github.com/Phantomlau3674/ai-film-director-workbenchWrote 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/phantomlau3674/ai-film-director-workbench/ai-film-production-system)<a href="https://agentmods.dev/skills/phantomlau3674/ai-film-director-workbench/ai-film-production-system"><img src="https://agentmods.dev/badge/skills/phantomlau3674/ai-film-director-workbench/ai-film-production-system/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/phantomlau3674/ai-film-director-workbench/ai-film-production-system"><img src="https://agentmods.dev/badge/skills/phantomlau3674/ai-film-director-workbench/ai-film-production-system.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 | $0.00117 | $0.02781 |
| Opus 5 | $0.00059 | $0.01391 |
| Sonnet 5 | $0.00023 | $0.00556 |
| Haiku 4.5 | $0.00012 | $0.00278 |
Grade A, and why
ai-film-production-system 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 12d 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 — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Film Production System
This skill owns project truth and production gates. It does not write final AI
video prompts in chat. Final prompt text comes from the isolated
ai-video-prompt-generator LLM generator.
Required Reading
references/v2-production-protocol.mdbefore changing project state.references/manifest-contract.mdbefore editing manifests.references/theory/README.mdbefore changing film-theory production diagnostics, review checks, or theory-linked failure taxonomy.references/ai-drama-production-hypotheses.mdbefore designing, optimizing, or gating Douyin-style AI dramas, AI microdramas, AI manju/manhua-video, serial AI shorts, or public-case methodology migrations.references/director-dense-prompt-production-method.mdbefore approving complete timed prompts with micro-actions, camera geometry, visibility, continuity, transition, dialogue, sound, static action-tableau, cross-video handoff, representation-layer, or semantic-color contracts.references/storyboard-blender-seedance-workflow.mdbefore designing or reviewing storyboard-board, Blender/blockout previs, first/last-frame, control-pass, camera-path, or Seedance/Dreamina/Jimeng-style workflows.references/director-grade-asset-workflow.mdbefore planning a multi-shot film's character plates, environment plates, scene director packs, shot control packs, or multimodal provider selections.references/asset-prompt-authoring-method.mdbefore writing or reviewing prompts for character, costume, environment, prop, creature, vehicle, palette, storyboard, staging-map, start/end-frame, or static action-key assets.templates/manifest.schema.json,templates/assets.schema.json,templates/constraints.schema.json,templates/shot_plan.schema.json, and bible/provider schemas when changing validators.
Project Contract
One movie root contains:
_project/
PROJECT.yaml
CURRENT.yaml
manifests/
decisions/
audits/
constraints/
film_theory_contract.default.json
scorecard_theory_rules.default.json
episode-plans/
task-board/
failure-taxonomy/
providers/
01_script/
shot_plans/
02_assets/
refs/
registry/
assets.jsonl
audio_assets.jsonl
bibles/
characters/
scenes/
props/
audio/
subtitles/
03_prompts/
specs/
generated/
preflight/
lint/
04_jobs/
dreamina/runs/
providers/runs/
05_review/
trackers/
diagnostics/
scorecards/
06_edit/
playlists/
timelines/
releases/
exports/
99_archive/
What ships with it
60 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.
- agents/openai.yaml 537 B
- references/ai-drama-production-hypotheses.md 15 KB
- references/ai-drama-public-case-source-snapshot-20260705.md 13 KB
- references/all-things-grow-prompt-structure-snapshot-20260712.md 7.5 KB
- references/asset-prompt-authoring-method.md 9.4 KB
- references/director-dense-prompt-production-method.md 9.9 KB
- references/director-grade-asset-workflow.md 6.0 KB
- references/manifest-contract.md 2.0 KB
- references/storyboard-blender-seedance-workflow.md 10 KB
- references/theory/production-gate-index.jsonl 5.6 KB
- references/theory/README.md 2.2 KB
- references/theory/theory-index.jsonl 15 KB
- references/v2-production-protocol.md 3.9 KB
- scripts/build_episode_plan.py 5.1 KB runs code
- scripts/build_film_scorecard.py 2.6 KB runs code
- scripts/build_manifest.py 4.5 KB runs code
- scripts/build_release.py 1.8 KB runs code
- scripts/build_shot_plan.py 6.0 KB runs code
- scripts/build_timeline.py 2.4 KB runs code
- scripts/common.py 6.7 KB runs code
- scripts/create_review_tracker.py 1.3 KB runs code
- scripts/ingest_dreamina_batch.py 1.8 KB runs code
- scripts/init_film_project.py 4.6 KB runs code
- scripts/manage_tasks.py 12 KB runs code
- scripts/prepare_dreamina_batch.py 3.3 KB runs code
- scripts/prepare_ffmpeg_export.py 2.9 KB runs code
- scripts/prepare_provider_batch.py 4.1 KB runs code
- scripts/promote_review.py 1.9 KB runs code
- scripts/quick_validate.py 4.0 KB runs code
- scripts/register_asset.py 6.7 KB runs code
- scripts/register_audio_asset.py 2.5 KB runs code
- scripts/validate_file_layout.py 1.3 KB runs code
- scripts/validate_preflight.py 9.7 KB runs code
- scripts/validate_project_layers.py 12 KB runs code
- scripts/validate_project.py 2.5 KB runs code
- templates/assets.schema.json 3.1 KB
- templates/audio_assets.schema.json 623 B
- templates/character_bible.schema.json 808 B
- templates/constraints.default.json 547 B
- templates/constraints.schema.json 1.6 KB
- templates/CURRENT.yaml 836 B
- templates/edit_playlist.csv 80 B
- templates/episode_plan.schema.json 2.2 KB
- templates/episode_plan.template.json 162 B
- templates/failure_taxonomy.default.json 4.0 KB
- templates/failure_taxonomy.schema.json 356 B
- templates/ffmpeg_export.schema.json 641 B
- templates/film_scorecard.schema.json 1.3 KB
- templates/film_theory_contract.default.json 1.1 KB
- templates/film_theory_contract.schema.json 1.8 KB
- templates/manifest.schema.json 2.5 KB
- templates/model_profile.seedance2.0_vip.yaml 271 B
- templates/motif_dictionary.schema.json 342 B
- templates/production_gate.schema.json 824 B
- templates/PROJECT.yaml 447 B
- templates/project/PROJECT_STRUCTURE.txt 694 B
- templates/prop_canon.schema.json 657 B
- templates/provider_profile.dreamina.yaml 541 B
- templates/provider_profile.schema.json 904 B
- templates/scene_bible.schema.json 704 B
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.
- 12d ago First seen · 300 lines · 117 tokens per session scan A 0f87414aadb4
ai-film-production-system is a skill published in the GitHub repository Phantomlau3674/ai-film-director-workbench (15 stars, last pushed 2mo ago), licensed MIT. It adds 117 tokens to every session and 2,781 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
video-prompt-engineer
A workflow for converting a finished script or script excerpt into Seedance-ready storyboards and video prompts. Seedance is an AI video-generation system, and each storyboard covers a 10–15-second clip.
seedance-2-5-skill
Plan and generate controllable Seedance video using Seedream 5.0 Pro storyboards and Seedance 2.0 today, with a Seedance 2.5 route when available. Use for consistent people, products, objects, food, or scenes; storyboard-to- video; reference-to-video; first-and-last-frame image-to-video; extensions; and Atlas Cloud…
seedance-20
This skill should be used when creating, improving, or troubleshooting Seedance 2.0 video on any surface — Dreamina, Jimeng, CapCut, Doubao, Volcengine/Ark, BytePlus, Runway's Seedance route, fal, or third-party provider/router surfaces such as EvoLink, OpenRouter, Kie.ai, PiAPI, LaoZhang, Runware, ModelsLab, AI/ML…
universal-video-prompt-skill
Write one model-agnostic video prompt spec, then compile it to whichever video model you can actually call. Use for cross-model prompt work, model comparison matrices, reusing one brief across providers, or when the target model is not yet available and the work must proceed on another one.
seedance-shotlist-director
Generate a director's shotlist as an editable HTML production board for Seedance 2.0. Use whenever the user provides a script, scene breakdown, story idea, or treatment to turn into a numbered shotlist with English Seedance prompts — trigger on "make a shotlist", "director’s shotlist", "break this script into…
seedance-2-5-director
A guide for turning ideas, scripts or source materials into prompts for Seedance 2.5, a video-generation model from platforms such as Jimeng, Doubao, Volcano Engine and BytePlus ModelArk.