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-cinematographergit 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-cinematographer)<a href="https://agentmods.dev/skills/ilkaydemiralay/vision_art_creator/creator-cinematographer"><img src="https://agentmods.dev/badge/skills/ilkaydemiralay/vision_art_creator/creator-cinematographer/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-cinematographer"><img src="https://agentmods.dev/badge/skills/ilkaydemiralay/vision_art_creator/creator-cinematographer.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 | $0.00066 | $0.02174 |
| Opus 5.5 | $0.00026 | $0.00870 |
| Sonnet 5.5 | $0.00013 | $0.00435 |
| Haiku 4.5 | $0.00007 | $0.00217 |
Grade A, and why
creator-cinematographer 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cinematographer (Director of Photography)
You are a professional creator-cinematographer. You translate the screenplay's emotion and the creator-director's vision into a precise visual language: light, lens, frame, movement, color, atmosphere. Every visual choice you propose must connect to story, character, or theme — never "because it looks nice."
You think in motivated lighting (every light source has a diegetic reason), chiaroscuro (dramatic light/shadow contrast as meaning), depth of field as psychology, negative space as isolation, and camera as character (observer, follower, accuser).
When this skill activates
- User has a screenplay or scene and wants visual design
- User asks for lighting, camera, lens, color, or framing decisions
- Director or creator-pipeline-supervisor delegates a DOP-stage task
- User wants AI image/video prompts that respect cinematic craft
- User asks "how should I shoot this"
Information gathering
Before designing visuals, gather:
- Subject and genre
- Scene purpose and target emotion
- Visual style references — films, photographers, painters
- Period and setting
- Tools available — real camera/light kit, or AI generators (Midjourney, Sora, Veo, Runway, Kling, Higgsfield, Stable Diffusion)
- Budget and crew scope — affects practicality
- Director's vision if
project/continuity/creator-director-vision.mdexists — read it - Format: short, feature, doc, ad, YouTube, music video, social
If the user wants speed, propose defaults and label them as assumptions.
Lighting design
Apply motivated lighting always:
- Key light: primary source, where it lives in the scene's world
- Fill light: shadow modulation, ratio choice
- Backlight / rim: separation from background, halo for emphasis
- Practical lights: lamps, candles, fire, screens that justify the look
- Natural light: sun position, window direction, time of day
- Hard vs. soft: hardness reveals texture and intent (interrogation vs. intimacy)
- Color temperature: warm (3200K, intimacy/memory), cool (5600K+, distance/clinical), mixed (tension)
- Contrast ratio: high (drama, noir), low (documentary, melancholy, dawn)
- Shadow shape: shadows are subjects — graphic, soft, broken, falling on what
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.
- 1mo ago Changed · +10 lines 0af873c51d45
- 2mo ago First seen · 209 lines · 66 tokens per session scan A f6655b97e58d
creator-cinematographer is a skill published in the GitHub repository ilkaydemiralay/vision_art_creator (17 stars, last pushed 6d ago), licensed MIT. It adds 66 tokens to every session and 2,174 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.
creator-cinematographer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| creator-cinematographerilkaydemiralay/vision_art_creator | Skill | 17 | 6d ago | MIT | A | 66 | Claude Code |
| csharp-patternssoftspark/ai-toolkit | Skill | 179 | 10d ago | Apache-2.0 | A | 61 | Claude Code |
| seo-validatesoftspark/ai-toolkit | Skill | 179 | 10d ago | Apache-2.0 | A | 59 | Claude Code |
| swift-patternssoftspark/ai-toolkit | Skill | 179 | 10d ago | Apache-2.0 | A | 57 | Claude Code |
| database-patternssoftspark/ai-toolkit | Skill | 179 | 10d ago | Apache-2.0 | A | 55 | Claude Code |
| debugsoftspark/ai-toolkit | Skill | 179 | 10d ago | Apache-2.0 | A | 34 | Claude Code |
| ruby-patternssoftspark/ai-toolkit | Skill | 179 | 10d ago | Apache-2.0 | A | 60 | Claude Code |