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 big-emotion/agent-atelier --skill video-directorgit clone --depth 1 https://github.com/big-emotion/agent-atelierWrote 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/big-emotion/agent-atelier/video-director)<a href="https://agentmods.dev/skills/big-emotion/agent-atelier/video-director"><img src="https://agentmods.dev/badge/skills/big-emotion/agent-atelier/video-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/big-emotion/agent-atelier/video-director"><img src="https://agentmods.dev/badge/skills/big-emotion/agent-atelier/video-director.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 | $0.00000 | $0.01631 |
| Opus 5.5 | $0.00000 | $0.00652 |
| Sonnet 5.5 | $0.00000 | $0.00326 |
| Haiku 4.5 | $0.00000 | $0.00163 |
Grade A, and why
video-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 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Director
Owns the span between an approved script and a publishable file. It does not choose the subject, does not write the narration, and does not decide where the piece is published.
| Upstream | This skill | Downstream |
|---|---|---|
attention-architect — the script and why it holds |
format, assembly, captions, deliverables, packaging | content-strategist — where it goes and when |
The first rule
A project's approved format spec is authoritative and is not redesigned from a production session. Once an operator has approved a voice, a caption treatment and a brand ending, those are settled; changing them because a beat would be easier to time is how a channel stops looking like one channel.
Two modes follow from that:
--establish— the project has no format spec. Decide each item below once, with the operator, and write it down where the project keeps it.--produce— the project has one. Read it, follow it, and flag any place the script cannot be produced within it rather than quietly bending it.
What a format spec must settle
Each of these has burned a session somewhere when it was left implicit.
| Item | What must be written down |
|---|---|
| Voice | The exact voice identifier and provider. Never invent one, never silently substitute. Verify it still resolves before generating. |
| Hook delivery | Whether the hook is spoken. It should be: a silent title card followed by unrelated narration has been explicitly rejected on a working format. |
| Pacing | The silence after the hook (~0.7 s on a working format), comma pauses (0.15–0.30 s), strong punctuation and idea changes (0.35–0.70 s). Natural pauses already in the take count toward these — do not add identical silence after every mark. |
| Canvas and export | Aspect, resolution, container, codec, pixel format, frame rate, audio codec, fast-start metadata. |
| Captions | Face, case, size on the canvas, fill and outline, maximum words and characters per cue, maximum lines, vertical inset, maximum width, and the renderer's fractions. |
| Sequence | The beat order the format follows, matching the script's own shape. |
| Brand ending | Palette, faces, text order, logo treatment, entrance timing, hold duration. Use the official logo on its own layer — never regenerate an approximate one. |
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 · 129 lines · 0 tokens per session scan A 95b88bffb839
video-director is a skill published in the GitHub repository big-emotion/agent-atelier (3 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,631 tokens. 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 2026-09-08.
Other skills, from other repositories
add-azuredevops
Adds Azure DevOps connector to a Power Apps code app. Use when querying work items, creating bugs, managing pipelines, or making ADO API calls.
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
ci-fixer
A CI job fails on a named revision and the fix belongs in code, config or tests, not in the CI provider.
push-ci
Push to remote and monitor CI. Validates branch safety, executes git push WITH explicit user approval, then monitors CI run status via gh CLI. Use when: user says 'push', 'push and watch CI', 'ship it', 'push-ci'. Not for: committing (use /smart-commit), creating PRs (use /create-pr), merging (use /merge-prep).
azure-devops
Manage Azure DevOps projects, work items, repos, PRs, pipelines, wikis, test plans, security alerts, variable groups, environments/approvals, branch policies, and attachments. Use when user asks to: manage sprints, create/update work items, list repos, create PRs, run pipelines, search code, manage wiki pages, check…
cloudflare-workers-ci-cd
Complete CI/CD guide for Cloudflare Workers using GitHub Actions and GitLab CI. Use for automated testing, deployment pipelines, preview environments, secrets management, or encountering deployment failures, workflow errors, environment configuration issues.