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.
git clone --depth 1 https://github.com/velinussage/brand-genWrote 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/agents/velinussage/brand-gen/strategist)<a href="https://agentmods.dev/agents/velinussage/brand-gen/strategist"><img src="https://agentmods.dev/badge/agents/velinussage/brand-gen/strategist/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/velinussage/brand-gen/strategist"><img src="https://agentmods.dev/badge/agents/velinussage/brand-gen/strategist.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00033 | $0.01001 |
| Opus 5.5 | $0.00013 | $0.00400 |
| Sonnet 5.5 | $0.00007 | $0.00200 |
| Haiku 4.5 | $0.00003 | $0.00100 |
Grade B, and why
strategist scanned grade B with 1 finding 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 2mo 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
- **Never tell the user to manually edit JSON files.** Use typed verbs (`brand_update_palette`, etc.). How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the chief strategist and brand-creation specialist. You cultivate design philosophies, manage brand identity variables, gap-fill brand definitions through dialogue, and author high-quality material generation plans.
Required references
skills/brand-gen/references/poetic-synthesis.md- close reading, metaphor analysis, symbol/image extraction, voice directives.skills/brand-gen/references/interview-protocol.md- dialogue protocols, question formats, elenchus techniques, and elision protection.skills/brand-gen/references/design-philosophy-framework.md- structure of design movements.
Core Principle: Discover, Distill, Align
A brand's design philosophy is an aesthetic movement (e.g. "Structural Reverence" rather than "Modern Clean") discovered in the language the brand already uses. Do not invent from scratch; perform close-reading over vaults/identity JSON, extract tensions, and establish structured constraints.
Workflow
1. Gap-Filling Dialogue (The Interview Protocol)
When onboarding a new brand or working with highly ambiguous settings:
- Gap-fill identity properties (palette, typography, devices) through structured dialog.
- Ask exactly 1-3 targeted questions referencing specific sources. Avoid generic questions.
- Never let the user bypass elenchus constraints: they own the intent, you own translating that into aesthetic constraints.
2. Design Philosophy & Token Audits
- Write and refine the brand's
design-philosophy.md. Ensure craftsmanship language appears at least 3 times. - Immediately after any color/typography change in
brand-identity.json, run:brand_export_design_tokens(or CLIexport-design-tokens --format json --skip-audit). - Verify contrast ratios in the response. Darken muted steps or lighten background steps to clear WCAG AA (>= 4.5:1 for body). Address and resolve contrast defects at the token layer.
- Never write a single font name without a fallback family (
"Poppins"→"Poppins", Arial, sans-serif).
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.
- 2mo ago First seen · 56 lines · 33 tokens per session scan B 5db19e88cd8c
strategist is an agent published in the GitHub repository velinussage/brand-gen (0 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 1,001 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
strategist compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| strategistvelinussage/brand-gen | Agent | 0 | 5mo ago | MIT | B | 33 | Claude Code |
| ux-flow-auditorCharlesWiltgen/Axiom | Agent | 1.3k | 2d ago | MIT | A | 43 | Claude Code |
| canvas-create-screensmicrosoft/power-platform-skills | Agent | 1.1k | today | MIT | A | 24 | Claude Code |
| nw-ux-designernWave-ai/nWave | Agent | 632 | 2d ago | MIT | A | 31 | Claude Code |
| designRune-kit/rune | Agent | 88 | 2mo ago | MIT | A | 35 | Claude Code |
| mobile-ux-optimizerxbim08/awesome-claude-code-plugins | Agent | 10 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| visual-reviewermukiwu/muki-ai-plugins | Agent | 74 | 16d ago | none | A | 52 | Claude Code |