pickle-brand

pickle-brand is a command for Claude Code from MrJPTech/macro-pickle. It costs 28 tokens per session (503 once invoked), scanned A, original, MIT.

A command that creates a JSON profile describing a brand's visual style, colours, preferences, and exclusions. The profile is used by an existing prompt-generation system.

In plain words
What is it for?
Use it to add a new client or store brand, verify that the profile loads, and apply it to image, video, or user-generated-content prompts.
Why use it?
It avoids manually assembling the same brand guidance whenever you generate images or other creative content.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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/mrjptech/macro-pickle/pickle-brand
Clone the repo
git clone --depth 1 https://github.com/MrJPTech/macro-pickle

Made for: Claude Code.

Wrote 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.

agentmods badge for pickle-brand

README.md
[![agentmods](https://agentmods.dev/badge/commands/mrjptech/macro-pickle/pickle-brand.svg)](https://agentmods.dev/commands/mrjptech/macro-pickle/pickle-brand)
Your own site
<a href="https://agentmods.dev/commands/mrjptech/macro-pickle/pickle-brand"><img src="https://agentmods.dev/badge/commands/mrjptech/macro-pickle/pickle-brand.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 503 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 5.1 $0.00028 $0.00503
Opus 5 $0.00014 $0.00251
Sonnet 5 $0.00006 $0.00101
Haiku 4.5 $0.00003 $0.00050

Measured 5d ago against content hash 7238d3b12df9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

pickle-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 5d 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.

.claude/commands/pickle-brand.md · 37 lines

What it actually says

/pickle-brand

Create a new brand profile so the engine can style generations with --brand <name>. No code change — the loader (scripts/lib/prompts/brand.ts) reads content/brands/*.json, and every rail (pnpm prompt|nano|img|fal, the clip + UGC packs) honors it.

Usage

  1. Survey existing: pnpm prompt --brands, then read a close template (content/brands/quiet-desk.json is the worked example — a product brand with palette, prefer/avoid lists, and a style sentence).
  2. Write content/brands/<name>.json with the real fields (match the existing profiles):
    • name — display name
    • style — the core look + voice, in a rich sentence
    • palette — array of named hex colors
    • prefer — array of must-haves
    • avoid — array of must-nots (garbled text, duplicate products, faces if faceless, etc.)
    • promptSuffix — short realism/quality tail appended to prompts
    • aspect — default ratio (e.g. 9:16, 1:1)
    • cast (optional) — IP-safe proxy names for any character/franchise the brand evokes
  3. Verify it loads: pnpm prompt --brands lists the new name.
  4. Use it: pnpm prompt --image --brand <name> …, pnpm nano --brand <name> …, or reference it from a clip scenes config.

House rules

  • cast = IP-safe proxies only — NEVER a copyrighted or real-person name in a final prompt.
  • A store that will also generate clips wants a matching content/clip-scenes/<store>.json (per-category scenes) — see /pickle-clips.
  • Brand profiles are data, not code — adding/editing one needs no build. Supabase-free.
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. 5d ago First seen · 37 lines · 28 tokens per session scan A 7238d3b12df9

Subscribe to this mod's changes

pickle-brand is a command published in the GitHub repository MrJPTech/macro-pickle (2 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 503 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.