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 frankxai/claude-skills-library --skill film-release-gategit clone --depth 1 https://github.com/frankxai/claude-skills-libraryWrote 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/frankxai/claude-skills-library/film-release-gate)<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/film-release-gate"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/film-release-gate/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/frankxai/claude-skills-library/film-release-gate"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/film-release-gate.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 | $0.00072 | $0.01039 |
| Opus 5.5 | $0.00029 | $0.00416 |
| Sonnet 5.5 | $0.00014 | $0.00208 |
| Haiku 4.5 | $0.00007 | $0.00104 |
Grade A, and why
film-release-gate 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
film-release-gate
The entry point for narrative film work. It does two jobs: it sequences the
other artifacts in the film-excellence pack, and it defines done.
It is the film equivalent of web-release-gate, and it works the same way:
you don't get to self-certify.
Read order (do not skip)
- The repo's own
film-design.mdandfilm-taste.mdif they exist — they outrank everything below. DOCTRINE.md— the five laws and the refusal listLANGUAGE.md— before any dialogue is writtenfilm-design.md(pack template) — the token contractCREW.md— which chair, which modelPIPELINE.md— the eight stages
Sequence
Refuse to jump stages. The most common and most expensive error in generative film production is starting at stage 7.
1 BIBLE → turn stated in one line, formal rule declared
2 CHARACTERS → Word Ledger + locked visual string per principal
3 BEATS → timecoded, turn located between 2:30 and 3:10
4 SCRIPT → LANGUAGE.md checklist passes
5 LOOK+SOUND → sound map written BEFORE any frame is generated
6 SHOTLIST → rule_check = yes on every row
7 GENERATE → character IDs reused, every generation logged
8 CUT → assembled to the sound map, then this gate
If a user asks to "just generate some shots" before stage 5 exists, say what is missing and what it will cost — a bin of unusable clips and a face that drifts — then offer the shortest real path: bible and beats first, one hour.
The gate
Certification requires all of the following as artifacts, not assertions:
- The turn, in one line, in the form they think X; actually Y
- The formal rule, declared, plus the two places it hurt (shot ids)
- Sound map: bed per location · foley on three actions · music in/out · the planned silence with its function and duration
- Three hand shots, timecoded
- Three deliberate imperfections, timecoded
- Language pass logged — the eleven-item checklist from
LANGUAGE.md - Speech-free ≥ 20% of runtime, measured not estimated. Speech-free means nobody is talking; room tone and foley continue. Do not accept a signal-free track as evidence — that is a dropout. A deliberate total silence is a separate, timecoded entry in the sound map
- Generation ledger complete — every shot reconstructible from seed
- Cold watch: one person who did not make it watched at 1× with no scrubbing and can answer what did she want and what changed
- Runtime inside the target window
- Submission copy passes the language refusals in
film-taste.md
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 First seen · 107 lines · 72 tokens per session scan A cbe99bb6f55a
film-release-gate is a skill published in the GitHub repository frankxai/claude-skills-library (47 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 1,039 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 2026-09-03.
Other skills, from other repositories
token-saver
Token optimization guide for Claude Code. This skill should be used when the user wants to reduce API costs, learn model routing strategies, or understand how to use free/cheaper tools (Ollama, Haiku) instead of burning expensive Claude tokens on routine tasks. Triggers on: save tokens, reduce costs, token tips, cheap…
wayfinder
A planning method that maps a large, uncertain project into linked decision tickets in a repository's issue tracker. An issue tracker is a system for recording and organizing project work.
scaffold-exercises
A directory scaffold for course exercises, with sections, exercise folders, and optional problem, solution, or explanation versions. It creates the required Markdown files and checks the result with the repository's linter.
domain-modeling
A practice for building and maintaining a project’s domain model: the shared terms, concrete scenarios, and recorded architecture decisions that describe what the software is about.
migrate-to-shoehorn
A testing guide for Shoehorn, a TypeScript library that lets tests provide only the fields they need from a larger data type.
ask-matt
A skill router that helps choose the right workflow or skill for the current task. It maps work from an initial idea through building and shipping, with separate paths for research, prototypes, and multi-session projects.