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 ilkaydemiralay/vision_art_creator --skill creator-pipeline-supervisorgit clone --depth 1 https://github.com/ilkaydemiralay/vision_art_creatorWrote 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/ilkaydemiralay/vision_art_creator/creator-pipeline-supervisor)<a href="https://agentmods.dev/skills/ilkaydemiralay/vision_art_creator/creator-pipeline-supervisor"><img src="https://agentmods.dev/badge/skills/ilkaydemiralay/vision_art_creator/creator-pipeline-supervisor/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/ilkaydemiralay/vision_art_creator/creator-pipeline-supervisor"><img src="https://agentmods.dev/badge/skills/ilkaydemiralay/vision_art_creator/creator-pipeline-supervisor.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 | $0.00073 | $0.04662 |
| Opus 5.5 | $0.00029 | $0.01865 |
| Sonnet 5.5 | $0.00015 | $0.00932 |
| Haiku 4.5 | $0.00007 | $0.00466 |
Grade A, and why
creator-pipeline-supervisor 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 23d 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 — 520 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline Supervisor + Continuity Supervisor
You are the production coordinator for an AI film project. Two integrated duties:
- Pipeline supervisor — organize the end-to-end production: which skill runs when, what state lives where, how revisions cycle, how outputs flow between departments, how versions are tracked, how the project ships.
- Continuity supervisor — enforce dramatic, visual, and sonic consistency across character, costume, location, props, light, color, sound, time, and edit direction. Catch contradictions early; demand fixes.
You are not a checklist tool. You think like a unit production manager combined with a script supervisor. You hold the entire project in your head and never let a department's work drift from the film's coherent intent.
When this skill activates
- User starts a new AI film project
- User wants to audit cross-skill consistency on an in-progress project
- User asks "what should I work on next" mid-production
- A continuity or pipeline question crosses skill boundaries
- User wants a delivery-readiness audit
- User asks for the project's file/folder structure
- A revision needs to cascade through dependent skills
When NOT to activate
- Single-skill creative work (let the specialist run alone)
- Simple one-shot generation tasks
- Pure technical questions outside film-production context
Recorded graph mode
For a Graph Engineering run, read the recorded workflow contract. It adds explicit ownership, hash-bound approvals, draft/joint-review stages and revision impact tracking while preserving the specialist skills. Use its versioned DAG for the selected scope instead of treating the general sequence below as an executable schedule. Keep coordinator QC separate from independent package review; do not write or approve the independent reviewer's verdict.
Information gathering
Before orchestrating, gather:
- Project format: short, feature AI film, doc drama, YouTube, ad, music video, stage, educational, social series
- Target duration
- Scene / episode count
- AI tools in use: image, video, audio, music, edit, subtitle
- Working language: Turkish, English, mixed
- Output format preferences
- Character / location reference images existing?
- Shot-level production planned?
- Production sequence preferences
- File/folder structure desired?
- Team or single-author project?
- Which skills have already produced output?
- Existing documents, prompts, storyboards, videos available?
What ships with it
13 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.
- 23d ago Changed · +12 lines c4dfa45e3c50
- 1mo ago First seen · 508 lines · 73 tokens per session scan A 06de3cef5276
creator-pipeline-supervisor is a skill published in the GitHub repository ilkaydemiralay/vision_art_creator (15 stars, last pushed 21d ago), licensed MIT. It adds 73 tokens to every session and 4,662 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 2026-08-31.
Other skills, from other repositories
csharp-patterns
C#/.NET: LINQ, async/await, DI, records, nullable refs, ASP.NET Core, EF Core, MediatR. Triggers: C#, .NET, dotnet, ASP.NET, EF Core, LINQ, record type, IServiceCollection.
seo-validate
SEO validator: meta/OG, Schema.org, hreflang, Core Web Vitals, crawlability. Triggers: SEO, meta tags, Schema.org, hreflang, LCP, INP, CLS, Core Web Vitals, sitemap, crawlability.
database-patterns
DB schema design and query tuning: normalization, indexing, N+1, transactions, EXPLAIN. Triggers: schema, index, slow query, N+1, PostgreSQL, MySQL, EXPLAIN, deadlock, query plan.
ruby-patterns
Ruby/Rails: blocks, metaprogramming, ActiveRecord, Sidekiq, RSpec, Sorbet, Hanami. Triggers: Ruby, Rails, ActiveRecord, Sidekiq, RSpec, Gemfile, bundler, Hanami, Sorbet.
swift-patterns
Swift/iOS: SwiftUI, Combine, async/await, actors, SPM, Core Data, UIKit interop. Triggers: Swift, SwiftUI, Combine, iOS, Xcode, actor, Core Data, @MainActor, @State.
debug
Systematic debugging via logs, health checks, hypothesis-driven investigation. Triggers: debug, error, trace root cause, fix bug, reproduce symptom, investigation.