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 agentmods add skills/squidbay/factory/creative-directornpx skills add squidbay/factory --skill creative-directorgit clone --depth 1 https://github.com/squidbay/factoryWrote 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/squidbay/factory/creative-director)<a href="https://agentmods.dev/skills/squidbay/factory/creative-director"><img src="https://agentmods.dev/badge/skills/squidbay/factory/creative-director.svg" alt="Measured on agentmods" 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 | $0.00101 | $0.00616 |
| Opus 5 | $0.00051 | $0.00308 |
| Sonnet 5 | $0.00020 | $0.00123 |
| Haiku 4.5 | $0.00010 | $0.00062 |
Grade A, and why
creative-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 3d 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.
What it actually says
Creative Director boot — thin loader
The Creative Director's home surface is the Claude Design canvas, where the boot is a paste: the full contents of seats/designer/BOOT-PROMPT.md placed at the canvas project root as the project's instructions. This skill exists for surfaces that load skills instead, and it is a snapshot — the repo copy is canon.
This card is now named for the seat: creative-director. Its parent folder still reads seats/designer/ — that one is an address, not a name, and the retired-folder sweep is a later step.
On invocation:
- Read
seats/designer/BOOT-PROMPT.mdfrom the factory repo, off livemain, in full — or ask the human to paste it if the repo is out of reach from this surface. - Follow it exactly: it will send you to
seats/_shared/BOOT-COMMON.mdfirst (the boot every seat shares — read it in full; §0 is the roster), then grounding links,MECHANICAL-RULES.md,seats/designer/OVERRIDES.md, and the top ofjournal.mdand the recorded brand decisions — and confirm the boot per RULE 17. - Hold the lane before anything else: read-only on code; deliverables travel export → the human →
inbox/drop/→ the PR Engineer opens. Never any other route.
Say in your first reply which file you booted from and that you read it off live main — that one sentence is how your human can tell the card was only a pointer, not the source (RULE 3).
What this card is, and what it is not. This loader is Factory-owned: it travels with the Factory, updates with it, and is deliberately kept small enough to be a contract rather than content. The boot material it points at — BOOT-PROMPT.md, GROUNDING.md, OVERRIDES.md, and anything your office adds beside them — is yours, and no Factory update overwrites it. That split is declared in .github/template-manifest.txt and enforced by the sync engine; it is why this card can keep improving while the seat behind it stays exactly as your office wrote it.
If this skill and the repo ever disagree, the repo wins — and say you noticed.
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.
- 3d ago First seen · 23 lines · 101 tokens per session scan A b412cd348a46
creative-director is a skill published in the GitHub repository squidbay/factory (5 stars, last pushed 13d ago), licensed MIT. It adds 101 tokens to every session and 616 once invoked, about $0.0005 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
tasteful-ui
UI design and implementation for real product surfaces with taste-first critique, reference routing, project-specific design briefs, variation comparison, and implementation verification. Use when Codex should redesign, build, polish, or critique frontend UI by reading project context, exploring taste, routing through…
accessible-web-animation-builder
Create performant web animations with proper accessibility and timing.
ai-game-world-asset-generator
Other tools generate sprites. CellCog builds game worlds. #1 on DeepResearch Bench (Apr 2026) for deep game design reasoning — character-consistent art, sprites, tilesets, music, UI, 3D models, GDDs, level design, and game prototypes, all cohesive across every asset.
ui-ux-pro-max
Use when designing, implementing, reviewing, or improving web, mobile, or desktop interfaces. Continue using it for visual, interaction, accessibility, responsive, typography, color, and stack-specific UI refinements. Do not use for backend-only logic, APIs, databases, infrastructure, or non-visual scripts.
ui-design-source
Use this skill when the user provides Figma material, design-export files, screenshots of design tools, PDFs, JSON, existing HTML, or asks for design-to-HTML/code fidelity. It adapts OpenDesign/Figma handoff discipline for UIDesigner without requiring a live Figma runtime.
takt
TAKT ワークフローエンジン。codex exec でサブエージェントを起動し、ワークフロー YAML（steps / initialstep）に従って マルチエージェントオーケストレーションを実行する。.