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 Gekkos-tech/agency-os --skill brandkitgit clone --depth 1 https://github.com/Gekkos-tech/agency-osWrote 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/gekkos-tech/agency-os/brandkit)<a href="https://agentmods.dev/skills/gekkos-tech/agency-os/brandkit"><img src="https://agentmods.dev/badge/skills/gekkos-tech/agency-os/brandkit/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/gekkos-tech/agency-os/brandkit"><img src="https://agentmods.dev/badge/skills/gekkos-tech/agency-os/brandkit.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 | $0.00129 | $0.01648 |
| Opus 5 | $0.00064 | $0.00824 |
| Sonnet 5 | $0.00026 | $0.00330 |
| Haiku 4.5 | $0.00013 | $0.00165 |
Grade A, and why
brandkit 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brand Kit — Premium Identity Image Direction
Direct an AI image model to produce brand identity imagery that looks like the work of a top-tier design studio, not a template generator. The output is a set of images: guideline boards, logo sheets, moodboards, mockup tiles.
Iron law: concept before prompt. Never generate a single image until you have written down the brand concept. A prompt without a concept produces generic "AI branding" — gradient blobs, meaningless geometric marks, ten fonts fighting each other.
Step 1 — Derive the brand concept
Before prompting, answer these four questions in writing (2–4 sentences total). Ask the user only if the answers cannot be inferred from context.
- Symbol — What ONE visual idea carries the brand? (a form, a letter construction, a natural object, a geometric operation). One symbol. Not three.
- Meaning — Why that symbol? What does it say about what the company does or believes? If you cannot state the meaning in one sentence, pick a different symbol.
- Personality — Three adjectives, ordered by priority (e.g. "precise, calm, quietly confident"). These drive every later vocabulary choice.
- Register — Pick exactly ONE aesthetic register from
references/registers.md(minimal, cinematic, editorial, dark-tech, luxury, playful-consumer). The register supplies the prompt vocabulary; do not mix registers within one brand kit.
Write the concept as a short block and reuse it verbatim at the top of every prompt in the set. This is what keeps a 6-image kit looking like one brand.
BRAND CONCEPT: [name] — [symbol] representing [meaning].
Personality: [adj1], [adj2], [adj3]. Register: [register].
Palette: [1 base + 1–2 neutrals + max 1 accent, with hex].
Type feel: [e.g. "grotesque sans, tight tracking, lowercase wordmark"].
Step 2 — Plan the deliverable set
A standard kit is 4–8 images. Choose from:
| Board | What it shows |
|---|---|
| Logo concept sheet | 3–6 mark explorations of the SAME symbol idea, black on white |
| Primary guideline board | Hero board: lockup, palette, type, one mockup, in a grid |
| Color & type board | Swatches with hex labels + type specimen lines |
| Visual-world moodboard | Photography/texture direction, no logos, 6–9 tiles |
| Mockup tiles | The identity applied to 1–2 real objects per image |
| Icon / app-mark board | The mark reduced to favicon and app-icon sizes |
What ships with it
1 file 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 · 97 lines · 129 tokens per session scan A ac6b7b888bfa
brandkit is a skill published in the GitHub repository Gekkos-tech/agency-os (5 stars, last pushed 2mo ago), licensed MIT. It adds 129 tokens to every session and 1,648 once invoked, about $0.0006 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
design-trends-2026
Apply 2026's top graphic design trends to any creative brief. Based on Kittl × Savee's 2026 Design Trends Report (10 trends + 2 honorable mentions), backed by Adobe, Figma, and Pinterest data. Use when: Designing a brand identity — pick the right aesthetic for your audience; Creating social media assets — use trending…
ux-sound-design
Create functional and emotionally resonant audio for digital products using Audio UX methodology—from notification sounds to complete sonic systems. Use when: Designing notification sounds for an app; Creating a complete audio system for a digital product; Adding audio feedback to UI interactions; Building accessible…
ai-storyboard-2x2
Créez des storyboards visuellement cohérents en utilisant la technique des 2x2 Grid Shots de PJ Ace, garantissant éclairage, personnages et décors uniformes entre les plans. Use when: Après avoir finalisé un script vidéo - Transformer le concept en visuels; Besoin de cohérence visuelle - Personnages et éclairage…
visual-brand-kit
Create visual identity systems for AI-generated content: colors, typography feel, photography style, composition rules, and prompt presets. Triggers on brand kits, visual guidelines, image style, and brand photography.
icons8
Fetch icons, illustrations, and photos from Icons8. Search 1.5M+ icons across 116 styles, vector illustrations, and 500K+ stock photos. Supports API (with key) and free CDN fallback (no key needed).
logo-generator
Generate custom logos with adaptive brainstorming and full brand kit export. Scans project context (README, package.json, CSS, existing assets) to inform design. Outputs favicons (16-512 + ICO), social images (OG, Twitter), dark/light/mono SVG variants, and an HTML preview.