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 commands/geo-mena/distill/brand-mapgit clone --depth 1 https://github.com/geo-mena/distillWrote 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/commands/geo-mena/distill/brand-map)<a href="https://agentmods.dev/commands/geo-mena/distill/brand-map"><img src="https://agentmods.dev/badge/commands/geo-mena/distill/brand-map.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 5.1 | $0.00018 | $0.01286 |
| Opus 5 | $0.00009 | $0.00643 |
| Sonnet 5 | $0.00004 | $0.00257 |
| Haiku 4.5 | $0.00002 | $0.00129 |
Grade A, and why
brand-map 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 6d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Load the distill-design skill, then map the brand described in $@ to Distill design tokens, producing the override CSS, the component adapter notes, and the voice translation guidelines.
Workflow:
-
Read
plugins/distill-design/SKILL.mddecision tree rows "Just need design tokens" and "Style a product/dashboard", thenplugins/distill-design/DESIGN-SYSTEM.md§ "Color", § "Typography", and § "Content fundamentals" before mapping. -
Parse $@ for brand inputs: brand name, primary brand color (hex), accent or secondary color (if any), font preference (system / serif / specific webfont), voice samples or tone descriptors, and the target surface (dashboard, marketing site, docs portal, internal tool). If a critical input is missing (no primary color, no surface type), ask one clarifying question. Otherwise commit.
-
State the mapping rationale in 2–3 lines before producing the artifact: which Distill conventions stay (paper background, low saturation, hairline borders, 1.5–2px strokes, no gradients, no shadows on body content) and which brand inputs map onto which Distill slots.
-
Produce three deliverables in order:
a. Token override CSS — a
:root { ... }block that overrides the relevant--*variables fromplugins/distill-design/tokens/colors_and_type.css. Map the brand primary onto a Distill slot semantically (data → salmon, conditioning → blue, attention/memory → lavender; pick the closest match for the brand's intended emotional register). Keep--paper,--ink,--ink-soft,--ink-muted,--hairline, all spacing tokens, and the type scale untouched unless the brand explicitly requires divergence. Output the CSS as a code block, ready to drop into the consumer app over the base import.b. Component adapter notes — a numbered list mapping the user's expected UI surfaces (buttons, inputs, cards, navigation, data tables, charts) onto the closest existing primitives in
plugins/distill-design/. ReuseCitation,Figure,MathBlock,TensorVector,Arrow,OperatorNode,SubNetBlock,PointerGlyphbefore proposing anything new. Where Distill has no equivalent (cards, app-shell sidebar, multi-column dashboards), follow the pushback from the SKILL decision tree: propose a figure-container or article-excerpt block instead of a card; propose breakouts or sequential figures instead of multi-column.c. Voice translation table — three columns: typical brand phrasing (input), Distill-voice rewrite (output), one-line note on the rule applied (e.g. "dropped marketing superlative", "rewrote in first-person plural"). Include 4–6 representative pairs covering: hero headline, feature description, CTA button label, error message, empty-state copy, footer microcopy. Use the user's voice samples from $@ as input where provided.
Voice and prose constraints (non-negotiable):
- English only. Never translate the artifact, even if this conversation is in another language.
- Sentence case for headings and CTAs. Title case only for proper nouns and named methods.
- No emoji anywhere. No exclamation points in body. No contractions in formal sections.
- No marketing superlatives ("revolutionary", "powerful", "robust", "comprehensive", "elegant", "seamless", "cutting-edge", "next-generation"). State what the thing does.
- No year literals in the brand artifact unless the topic genuinely requires dating something.
- First-person plural ("we") for narration in voice rewrites; second person ("you") only when addressing user actions directly.
Visual constraints (non-negotiable):
- Background
#fdfdfd(paper) — never pure white, never a colored fill. - Body color
rgba(0,0,0,0.8)(≈#333). Pure#000reserved for h1 only. - Strokes 1.5–2px in
#666(or the brand-overridden equivalent in the same low-saturation register) withstroke-linecap="round". No multi-color icons, no gradients, no shadows on body content. - If the brand primary is fully saturated, desaturate it to fit the Distill register before mapping (e.g.
#3b82f6brand blue →#81bee4-adjacent shade, kept under the Distill saturation ceiling). State this transformation explicitly in the rationale so the user can override if they reject the desaturation.
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.
- 6d ago First seen · 49 lines · 18 tokens per session scan A 4ab2650cbeb6
brand-map is a command published in the GitHub repository geo-mena/distill (2 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 1,286 once invoked, about $0.0001 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 commands, from other repositories
brand
Generate a full editorial brand-guidelines book for any URL. 14 chapters covering brand essence/archetype, colour, typography, spacing, shape, iconography, motion, components, voice, accessibility, tokens, and how-to-use guidance. Print-ready, dark-mode toggle, hand-off-ready single HTML.
pair
Fuse two extracted designs into a single hybrid identity. Pick which axis (colour, typography, spacing, shape, motion, voice, components) comes from which site. Defaults to "visual A × voice B" — same colours/spacing as the first URL, type/voice/components from the second.
theme-swap
Recolour an extracted site's design around a new brand primary. OKLCH hue rotation preserves perceptual lightness — neutrals, type, spacing, and motion stay untouched. Side-by-side HTML preview + recoloured tokens (DTCG, Tailwind, shadcn, Figma).
dna
Place a design in the measured design space — nearest systems, per-axis percentiles, outliers.
extract
Extract the complete design language from a URL — DTCG tokens, Tailwind, Figma vars, motion, voice, components.
fidelity
Measure how faithfully a clone reproduces a site — pixel-diff plus motion-fidelity into one 0-100 score, a letter grade, a ranked correction plan, and a shareable card.