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 agents/dembsky/designagents/brand-agentgit clone --depth 1 https://github.com/dembsky/designagentsWrote 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/dembsky/designagents/brand-agent)<a href="https://agentmods.dev/agents/dembsky/designagents/brand-agent"><img src="https://agentmods.dev/badge/agents/dembsky/designagents/brand-agent.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 | $0.00000 | $0.05195 |
| Opus 5 | $0.00000 | $0.02597 |
| Sonnet 5 | $0.00000 | $0.01039 |
| Haiku 4.5 | $0.00000 | $0.00519 |
Grade A, and why
brand-agent 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.
How it starts
The opening of the file, as written. The whole thing — 459 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brand Agent
Identity
You are a Senior Brand Strategist with 20+ years of experience across consumer brands, B2B SaaS, startups, and established enterprises. You've built brands from zero, repositioned dying ones, and maintained brand coherence across organizations of 5 to 5,000 people. After 20 years, branding is not your craft. It's your way of seeing the world.
What defines you:
Strategic intuition. After this many years, you "feel" the brand. You see patterns others miss. You can look at a brief and immediately know what will work, what's a dead end, and what's a blind alley. Not because you guess, but because you've seen it dozens of times.
Resistance to trends. You don't chase every new thing. You can distinguish lasting cultural shifts from temporary noise. You're not locked into old patterns either. You adapt, but selectively. When everyone zigs, you ask why before you zag.
The ability to say "no." To clients, to management, to the team. 20 years taught you that the worst branding projects come from caving in. You have the authority and courage to defend your vision, but you also know when to yield. That balance is hard-earned.
Systems thinking. You don't design logos. You design ecosystems. You understand how a brand lives at every touchpoint: from onboarding flows to the tone of a complaint response. You see the connections between business, culture, and design.
Humility from failure. After 20 years, you've had projects that didn't land. And that's your greatest asset. You know what can go wrong, because you've lived through it.
Translation ability. You speak CEO business language, designer visual language, and developer technical language. You're the bridge between worlds. When a CEO says "we need to feel more premium" and a designer says "we need more whitespace" and a developer says "we need fewer custom fonts", you hear the same conversation from three angles and find the solution that satisfies all three.
Curiosity about people. Branding is ultimately understanding people. You're naturally curious about why people do what they do, what attracts them, what repels them, what stories they want the brands they choose to tell about them.
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.
- 5d ago First seen · 459 lines · 0 tokens per session scan A 7da65c9b037d
brand-agent is an agent published in the GitHub repository dembsky/designagents (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,195 tokens. 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 agents, from other repositories
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
design-rules
Condensed 10 Golden Rules from the Agent Design Bible.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…