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/decocms/studio/brandnpx skills add decocms/studio --skill brandgit clone --depth 1 https://github.com/decocms/studioWhat 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 | $0.00000 | $0.01575 |
| Opus 5 | $0.00000 | $0.00788 |
| Sonnet 5 | $0.00000 | $0.00315 |
| Haiku 4.5 | $0.00000 | $0.00158 |
Grade A, and why
brand 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 2d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brand — build an organization brand
Create and maintain an org's brand as a folder the whole platform reads: colors, type, voice, logo and a deck theme. Use this whenever someone asks to "set up our brand", "make a brand kit", "apply our colors/fonts", or before producing branded artifacts (decks, pages, emails). One brand = one folder; everything that generates output consumes it.
Quick reference
| Task | How |
|---|---|
| See a complete example | read examples/tokens.css and examples/brand.md (in this skill folder) |
| Create a brand | write the files into org/home/brands/<name>/ (steps below) |
| Build a deck theme | slides-create … --theme org/home/brands/<name>/slides-theme.html (see the slides skill) |
| Edit later | the user edits it in Studio's Library → Brands (or you rewrite the files) |
Convention
A brand is org/home/brands/<name>/ (<name> is lowercase kebab, e.g.
acme):
| File | What |
|---|---|
tokens.css |
Visual source of truth — CSS custom properties in the --brand-* namespace. |
brand.md |
The brand bible — voice, tone, color/type usage, components, do/don't (prose for agents). |
logo.svg (or .png) |
The logo. Name it logo.*. |
slides-theme.html |
Optional deck theme for the slides skill. |
The Library renders this folder as a first-class Brand (color bands, type specimens, components & deck preview, all editable). Keep the file and token names exactly as below so it groups them correctly.
tokens.css — the token system
Everything lives under --brand-* in :root. Use these families/names — the
Library editor groups by them and consumers (decks, pages) map onto them:
- Color ramps —
--brand-<family>-50 … 950(11 steps) forprimary,secondary,accent,neutral; plus a flat alias--brand-primary(= the 500),--brand-secondary,--brand-accentfor the common case. - Semantic —
--brand-{success,warning,error,info}, each with-bgand-fgvariants. - Surfaces / text (roles) —
--brand-bg,--brand-bg-subtle,--brand-bg-elevated,--brand-fg,--brand-fg-muted,--brand-fg-subtle,--brand-border,--brand-border-strong,--brand-ring. - Type —
--brand-font-display,--brand-font-body,--brand-font-mono; scale--brand-text-xs … 5xl; weights--brand-fw-{regular,medium,semibold, bold};--brand-leading-*,--brand-tracking-*. Load web fonts with an@importat the top of the file. - Spacing —
--brand-space-1 … 20(4px base). - Radius —
--brand-radius+--brand-radius-{sm,md,lg,xl,full}. - Shadows —
--brand-shadow-{sm,md,lg}(+ an optional brand glow). - Motion —
--brand-duration-{fast,base,slow},--brand-ease.
What ships with it
2 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.
- 2d ago First seen · 124 lines · 0 tokens per session scan A 3f7c3acf5036
brand is a skill published in the GitHub repository decocms/studio (402 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,575 tokens. 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 2026-08-30.
Other skills, from other repositories
mcp-assistant
Use when a task needs connected MCP servers, external services, dynamic MCP tool discovery, schema inspection, sandboxed MCP execution, or routing across many possible MCP tools.
pr-finish-pass
Final-polish pass on the current PR or feature branch before it lands. Rebases on origin/main, force-pushes, drives CI to green, then reviews the diff for correctness/perf/security/reliability bugs, flaky test patterns banned by make lint-test-patterns, sloppy comments a senior engineer would not write, cross-crate…
mcp-cli
Use when running, automating, integrating, or troubleshooting the MCP CLI (mcpa | mcp-ts), including local or remote discovery, authentication, schema inspection, tool calls, and gateway lifecycle errors.
harn-release
Use for Harn release prep, version bumps, publishing, tags, and release notes.
harn-apps
Keep app behavior in Harn while shared hosts draw the view and provide files, network, and browser features.
harn-mcp
Use for MCP client connections, server definitions, inbound roots/sampling/elicitation, and deterministic MCP fixtures.