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 0xhughs/director-skills --skill cinematic-image-promptinggit clone --depth 1 https://github.com/0xhughs/director-skillsWrote 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/0xhughs/director-skills/cinematic-image-prompting)<a href="https://agentmods.dev/skills/0xhughs/director-skills/cinematic-image-prompting"><img src="https://agentmods.dev/badge/skills/0xhughs/director-skills/cinematic-image-prompting/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/0xhughs/director-skills/cinematic-image-prompting"><img src="https://agentmods.dev/badge/skills/0xhughs/director-skills/cinematic-image-prompting.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 | $0.00049 | $0.00766 |
| Opus 5 | $0.00024 | $0.00383 |
| Sonnet 5 | $0.00010 | $0.00153 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
cinematic-image-prompting 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 12d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cinematic-image-prompting
When to use
- The user wants still image prompts, character sheets, location references, prop/costume concepts, keyframes, posters, thumbnails, concept art, or scene stills.
- The user needs image prompts before video generation to lock identity, composition, or style.
- The task requires photorealism, cinematic language, texture, camera/lens terms, or negative/positive constraints.
When not to use
- The user asks for moving video prompts only.
- The user asks to adapt a finished prompt to a named model only.
- The user wants actual image generation rather than prompt writing, unless paired with image generation tools.
Required inputs
- Subject or asset type
- Purpose of image
- Creative intent
- Continuity anchors
- Style/genre/tone
Optional inputs
- Target model
- Aspect ratio
- Reference images
- Text/logo needs
- Photorealism level
- Negative constraints
Workflow
- Start with creative intent: who/what, why this image exists, emotional read, and audience impression.
- Build cinematic execution: subject specificity, action/pose, environment, framing, lens feel, lighting direction/quality, color, texture, and realism level.
- Add continuity anchors from the bible: face, wardrobe, prop state, location geography, palette, and design rules.
- Select format: natural prose, priority stack, shot card, or model-specific export through model-adaptation.
- Handle exclusions according to model behavior: true negative field where supported, positive restatement where not.
- Create variants only by changing one meaningful variable at a time.
- Add quality checklist and revision hooks.
Decision logic
- If character consistency matters, create a clean reference sheet before dramatic scene stills.
- If the image contains text, route to model-adaptation and choose a model/profile that supports text better.
- If the style is too broad, ask for or infer one strong visual anchor plus specific execution details.
- If the target model is unknown, output a universal prompt brief and flag model-dependent fields.
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.
- checklists/image_prompt_quality_checklist.md 334 B
- examples/shot_list_to_image_prompts.md 360 B
- references/image_prompt_components.md 1.2 KB
- references/lighting_and_photorealism.md 1.1 KB
- references/negative_prompt_patterns.md 925 B
- references/prompt_anatomy.md 818 B
- templates/character_reference_sheet_prompt.md 666 B
- templates/cinematic_still_prompt.md 496 B
- templates/keyframe_prompt.md 412 B
- templates/location_reference_prompt.md 419 B
- templates/prop_prompt.md 340 B
- tests/image_prompt_completeness_tests.md 264 B
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.
- 12d ago First seen · 81 lines · 49 tokens per session scan A 41e9c8bf3cec
cinematic-image-prompting is a skill published in the GitHub repository 0xhughs/director-skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 766 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
writers-room-story-engine
Orchestrates modular story development by diagnosing the current phase and routing to the right story skill for foundations, worldbuilding, scene writing, or revision. Use when building a story from scratch, improving an outline, strengthening narrative structure, or guiding story development in staged workflows.
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
higgsfield-troubleshoot
Use when a Higgsfield generation fails, produces poor quality, looks wrong, doesn't match the prompt, or the user needs to fix or improve an output.
higgsfield-motion-design
End-to-end motion-design / animated-ad creation flow on Higgsfield via the MCP connector. Use when the user wants to create motion design, animate a logo, make a video from an image, build an animated ad or brand promo, turn a product into motion, or says 'make a motion', 'motion design', 'animate this', 'make a video…
setup-matt-pocock-skills
A setup skill that configures engineering skills for a repository, including its issue tracker, labels, and documentation layout. A repository is the project folder managed by version control.
frontend-design
A design guide for building polished web interfaces such as pages, dashboards, forms, navigation, and reusable UI components. It covers HTML, CSS, JavaScript, and common frontend frameworks.