brand-make

A command that creates a logo, social graphic, document template, or marketing image using the currently selected brand profile. It saves the finished asset in the repository's output/ folder.

In plain words
What is it for?
Use it to request branded logos, social posts, banners, document templates, slide designs, one-pagers, hero images, ads, backgrounds, textures, or photos.
Why use it?
It removes the need to choose separate generation tools and manually apply brand colors, fonts, and visual rules. It also explains when a photographic image needs an external image service and permission.

Command

Install

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.

agentmods
npx agentmods add commands/localplugins/plugins/brand-make
Clone the repo
git clone --depth 1 https://github.com/localplugins/plugins
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 451 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.00451
Opus 5 $0.00016 $0.00226
Sonnet 5 $0.00007 $0.00090
Haiku 4.5 $0.00003 $0.00045

Measured yesterday against content hash f8479f83bc8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brand-make 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 yesterday.

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.

brand-forge/commands/brand-make.md · 35 lines

What it actually says

/brand-make

The hero command. Turn a plain-language request into a finished, on-brand asset.

Steps

  1. Resolve the active brand. Read brand/.active (or the single brand/ dir) via lib/brand.mjsresolveActive. If none exists, tell the user to run /brand-new and stop.
  2. Load + validate the profile with loadProfile / validateProfile. If validation fails, report the offending field and stop.
  3. Route by asset type (rule of thumb: text/geometry → vector; photographic → raster, which is opt-in):
    • logo / wordmark / monogram / favicon → generate-logo skill.
    • social post / story / banner / OG card / thumbnail → generate-social skill.
    • letterhead / slide / one-pager → generate-doc-template skill.
    • hero image / ad creative / background / texture / photo → generate-graphic skill (opt-in raster: needs BRAND_FORGE_RASTER=1 + an API key; if unset, say so and offer a vector alternative).
  4. Consider art-director for anything ambiguous or multi-asset — have it propose the asset set and composition before generating.
  5. Generate by calling the routed skill, writing files under output/ (SVG for vector assets; PNG for raster graphics, optionally with an SVG overlay).
  6. Enforce with the visual-guardian subagent (palette, contrast, clear-space, type). Apply fixes or surface flags.
  7. Report the saved paths and show a short preview/description of each asset.

Never auto-post or upload. Output is local files the user reviews.

Changes

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.

  1. yesterday First seen · 35 lines · 33 tokens per session scan A f8479f83bc8d

Subscribe to this mod's changes

brand-make is a command published in the GitHub repository localplugins/plugins (5 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 451 once invoked, about $0.0002 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.