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/alphaaiservice/cortex/gen-brandgit clone --depth 1 https://github.com/alphaaiservice/cortexWhat 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 | $0.00047 | $0.14042 |
| Opus 5 | $0.00023 | $0.07021 |
| Sonnet 5 | $0.00009 | $0.02808 |
| Haiku 4.5 | $0.00005 | $0.01404 |
Grade A, and why
gen-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 — 1,516 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brand Identity Generator — SVG Logos & Complete Design System
Generate a complete brand identity package for: $ARGUMENTS
This command creates:
- BRAND_GUIDE.md — comprehensive brand guidelines document
- 7 SVG/JSON files — logos, favicon, icons, OG image, PWA manifest
- Design tokens — Tailwind-ready color system, typography, spacing
- All generated directly by Claude — no external API keys needed
Section 0: Input Parsing & Context Detection
Parse $ARGUMENTS to determine the product name, description, and domain.
0a. Detect Input Type
IF $ARGUMENTS is empty:
→ Ask: "What product should I create branding for? Provide a name and description, or a path to a PRD file."
→ STOP and wait for user input.
IF $ARGUMENTS ends with .md or starts with ./ or / (file path):
→ Read the file
→ Extract product name from the first H1 heading or "Product Name" field
→ Extract description from the first paragraph or "Description" field
→ Extract target audience, features list, and industry/category
→ SET INPUT_TYPE = "prd"
IF $ARGUMENTS is a quoted string or plain text:
→ Parse format: "ProductName — description" or "ProductName: description" or just "ProductName"
→ If no separator found, use the full text as product name
→ SET INPUT_TYPE = "brief"
0b. Extract Brand Inputs
Extract and store:
PRODUCT_NAME = [extracted product name — capitalize properly]
PRODUCT_DESC = [one-line description — what the product does]
PRODUCT_DOMAIN = [detected domain: fintech/healthtech/edtech/ecommerce/productivity/devtools/social/ai/security/analytics/marketing/hr/logistics/legal/gaming/media/travel/food/realestate/general]
TARGET_AUDIENCE = [who uses this product — extracted from PRD or inferred from description]
KEY_FEATURES = [top 3-5 features — extracted from PRD or inferred]
BRAND_MOOD = [inferred mood: professional/playful/bold/elegant/minimal/warm/techy/corporate]
0c. Validate Inputs
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 · 1,516 lines · 47 tokens per session scan A eae03734dec8
gen-brand is a command published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 26d ago), licensed MIT. It adds 47 tokens to every session and 14,042 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.
Other commands, from other repositories
slidev:redraw-diagrams
Extract inline diagrams and regenerate in all platforms (Mermaid, PlantUML, Excalidraw).
presentation
Create, outline, review, or improve a presentation deck.
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.