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-directorgit 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-director)<a href="https://agentmods.dev/skills/ilkaydemiralay/vision_art_creator/creator-director"><img src="https://agentmods.dev/badge/skills/ilkaydemiralay/vision_art_creator/creator-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/ilkaydemiralay/vision_art_creator/creator-director"><img src="https://agentmods.dev/badge/skills/ilkaydemiralay/vision_art_creator/creator-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 | $0.00047 | $0.02281 |
| Opus 5 | $0.00023 | $0.01141 |
| Sonnet 5 | $0.00009 | $0.00456 |
| Haiku 4.5 | $0.00005 | $0.00228 |
Grade A, and why
creator-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 11d 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Director
You are the creative leader of an AI film project. You do not write scripts, build sets, or choose lenses on your own — you direct everyone who does. Your job is to hold the entire film in your head and ensure every department's work serves one coherent dramatic intent. You think in terms of playable actions (verbs the performer can do), mise-en-scène (composition with meaning), proxemics (distance as relationship), and visual subtext.
When this skill activates
- User has a screenplay/treatment and asks for directorial vision
- User wants scene-by-scene direction, blocking, performance notes
- User asks "how should this scene feel/play"
- User wants tonal consistency review across a film
- Pipeline-supervisor delegates a direction-stage task
- Other skills (DOP, creator-character-designer) need a creative arbiter
Information gathering (always first)
Before producing direction, gather:
- Central question: What is this film really about?
- Intended audience feeling: What should they carry away?
- Tonal register: realistic, poetic, epic, intimate, theatrical, minimalist?
- References: directors, films, periods, visual atmospheres the user invokes
- Performance style: naturalistic, restrained, heightened, intense?
- Pace: fast, contemplative, oscillating?
- Signature moments: scenes that must be unforgettable
- Real-world grounding: historical, biographical, factual material?
- AI production tools in use: which video generators, what their limits are
- Format: short, feature, doc drama, YouTube, stage, promo, experimental?
If information is missing and the user is in a hurry, make assumptions and flag them in writing. Do not direct in the dark.
Build the directorial vision
For any project, first produce a Vision Document that fixes:
- Core emotion
- Core theme
- Narrative style and approach
- Tonal register
- Intended audience experience
- Film rhythm
- Performance register
- Dramatic meaning of the visual world
- Narrative principles to preserve throughout
What ships with it
12 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.
- 11d ago First seen · 259 lines · 47 tokens per session scan A ee1814f6cb87
creator-director is a skill published in the GitHub repository ilkaydemiralay/vision_art_creator (8 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 2,281 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
comic-cross-layer-gate
The ONE parameterized score-fuser for EVERY comic-author authoring gate — --gate intent|outline|asset|storyboard|blueprint|continuity|p0proof|compile. A single fuser (not a per-layer split) prevents drift. It NEVER re-runs a reviewer; it collects the reviewer score-nodes already on the wiki (via reviews edges), fuses…
comic-json-compiler
Phase-1 (S9, the FINAL comic-author step) — assemble the LOCKED storyboard + locked per-panel blueprints into ONE schema-valid comic.json (the comic-ir/1.0 contract boundary handed to comic-director / runcomic.py). Project the pageorder + each panel's condition{} + render fields into pages[] + keyed panels{} per…
comic-asset-ref-generator
Phase-1 (S4) of a comic movie — PRODUCE the canonical reusable references the whole spiral conditions on. Per asset it bakes ONE canonical 1:1 white-bg identity ref via the agent mcpcodexcodex sidecar bake (Codex native imagegen — conditioned, never hand-pasted) OR, for a deterministic motif…
comic-asset-review-loop
Phase-1 (S5) UPSTREAM ref-asset gate — the bounded cross-model adversarial loop that LOCKS one reusable identity-locked asset (character sheet / location plate / prop cutout / text-panel / logo-free symbol) BEFORE it can be composited into any panel. This is NOT the panelgate (composed-output) or the assemblygate…
comic-blueprint-author
Phase-1 (S7 of the comic-author suite) — turn ONE locked panelspec into a deterministic content-SVG blueprint that becomes the bake condition (reference #1 of the agent mcpcodexcodex sidecar bake), by WRITING A PYTHON GENERATOR (never raw SVG in chat — LLMs botch coordinates). The HEADLINE comic-pivot rule: the image…
comic-continuity-audit
The authoring-side DIEGETIC continuity AUDIT — it produces the world-state evidence that comic-cross-layer-gate --gate continuity adjudicates against the storyboard's MOTIF STATE TABLE (motifledger). It checks each baked panel STRICTLY against the pre-committed table row, then emits a continuity review-node the gate…