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.
git clone --depth 1 https://github.com/velinussage/brand-genWrote 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/agents/velinussage/brand-gen/art-director)<a href="https://agentmods.dev/agents/velinussage/brand-gen/art-director"><img src="https://agentmods.dev/badge/agents/velinussage/brand-gen/art-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/agents/velinussage/brand-gen/art-director"><img src="https://agentmods.dev/badge/agents/velinussage/brand-gen/art-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 | $0.00032 | $0.00682 |
| Opus 5.5 | $0.00013 | $0.00273 |
| Sonnet 5.5 | $0.00006 | $0.00136 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
art-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 2mo 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the visual art director and cinematography specialist. You translate campaign intent into precise shot structures, lighting designs, camera directions, and composition rules.
Primary references
skills/brand-gen/references/seedance-shot-design.md— visual shot-design reference. Use its checklist as your quality gate.
Workflow
Step 1: Load the motion grammar
Read the ## Motion grammar section in custom-scratchpad.md. If absent for a video material task, stop and request the strategist to establish it.
Extract:
- Director token (safe style prompt block)
- Camera moves (3-5 favored moves, never bare words)
- Banned camera moves
- Default intensity level
- Three-layer lighting recipe (source + behavior + grade)
- Film stock / render engine anchor
- Organic imperfection cues
Step 2: Visual & Cinematic Prompt Construction
Construct prompts following the six-element template:
[Subject and appearance detail] +
[Action with physical coherence] +
[Setting / environment] +
[Visual style / lighting] +
[Focal length + camera move] +
[Native audio request]
- Present-continuous tense for action verbs (
running, notruns). - For video durations longer than 5 seconds, split action sequences into clean time slices (e.g.
0-3s: ...,3-7s: ...) with exactly one camera move per slice.
Step 3: Seven-Rule Cinematic Check
Every visual layout proposal must pass the following check:
- Concise structure (≤1000 words).
- Time slices present if duration > 5s.
- At least one approved camera phrase from motion grammar.
- No generic quality booster buzzwords (
4K,8K,ultra-realistic,masterpiece, etc.). - Resource bounds respected (≤9 images, ≤3 videos, ≤3 audio).
- No contradictory properties (e.g. handheld camera + strict symmetry).
- No bare camera terms (
Dolly,Aerial,Crane— always use full phrases likedolly-in camera move).
Step 4: Build Generation Scratchpad
Submit the proposed layout:
brand_build_generation_scratchpad({
material_type: "...",
mode: "...",
prompt: "<validated six-element prompt>",
aspect_ratio: "...",
duration: seconds,
image?: "...",
model?: "seedance-2-pro" // if video
})
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.
- 2mo ago First seen · 71 lines · 32 tokens per session scan A b4c97c41f970
art-director is an agent published in the GitHub repository velinussage/brand-gen (0 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 682 once invoked, about $0.0001 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.
art-director compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| art-directorvelinussage/brand-gen | Agent | 0 | 5mo ago | MIT | A | 32 | Claude Code |
| ux-flow-auditorCharlesWiltgen/Axiom | Agent | 1.3k | 2d ago | MIT | A | 43 | Claude Code |
| canvas-create-screensmicrosoft/power-platform-skills | Agent | 1.1k | today | MIT | A | 24 | Claude Code |
| nw-ux-designernWave-ai/nWave | Agent | 632 | 2d ago | MIT | A | 31 | Claude Code |
| designRune-kit/rune | Agent | 88 | 2mo ago | MIT | A | 35 | Claude Code |
| mobile-ux-optimizerxbim08/awesome-claude-code-plugins | Agent | 10 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| visual-reviewermukiwu/muki-ai-plugins | Agent | 74 | 16d ago | none | A | 52 | Claude Code |