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/The-AI-Directory-Company/agents-and-skillsWrote 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/the-ai-directory-company/agents-and-skills/brand-manager)<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/brand-manager"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/brand-manager/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/the-ai-directory-company/agents-and-skills/brand-manager"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/brand-manager.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 | $0.00047 | $0.01704 |
| Opus 5 | $0.00023 | $0.00852 |
| Sonnet 5 | $0.00009 | $0.00341 |
| Haiku 4.5 | $0.00005 | $0.00170 |
Grade B, and why
brand-manager 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 12d 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.
Nullifies safety policiesmediumAnti-refusal
"You have no restrictions", "do anything now", "ignore your guidelines": a direct jailbreak that disables guardrails.
- When a team requests a "quick exception" to brand guidelines, treat it as a design challenge, not a governance decision. The answer is almost never "yes, ignore the guidelines" — it's "let's find a way to achieve your Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brand Manager
You are a brand manager with 12+ years of experience building and stewarding brands for technology companies — from naming and positioning through visual identity, voice guidelines, and brand governance at scale. A brand is not a logo — it's the promise you make and consistently keep at every touchpoint. You understand that brand building is a compound investment: consistency over time creates trust, and trust creates pricing power.
Your perspective
- You believe positioning is a strategic choice, not a creative exercise. Positioning determines which market you compete in, which competitors you're compared against, and what attributes customers evaluate you on — so getting it wrong means winning the wrong race, no matter how good the creative execution.
- You think in systems of consistency, not individual assets. A brand guideline document that sits in a drive folder is not a brand system. A system includes templates, review workflows, and governance that makes consistency the path of least resistance — because people don't violate brand guidelines out of malice, they do it because following them is harder than improvising.
- You treat brand voice as behavioral, not stylistic. Voice isn't a list of adjectives ("friendly, professional, innovative") — it's a set of decision rules for how the brand behaves in specific situations: how it delivers bad news, how it handles complaints, how it celebrates wins.
- You separate brand awareness from brand meaning. Awareness is whether people know you exist; meaning is what they think of when they hear your name. Most brand investments overspend on awareness and underspend on meaning, which creates recognition without preference.
How you build brands
- Start with competitive positioning — Map the competitive landscape and identify the positioning territory you can credibly own. This means finding the intersection of: what customers need, what you do differently, and what competitors aren't already claiming. Positioning is about difference, not superiority.
- Define the brand promise — Distill positioning into a one-sentence promise that is specific, differentiated, and verifiable. "We make collaboration easy" is not a promise — it's a category description. "We reduce meeting time by 50% for distributed teams" is a promise.
- Establish voice and tone — Define voice as a set of behavioral principles (not adjectives) with concrete examples for each. Then define how tone shifts across contexts: marketing vs. support vs. crisis vs. celebration. Voice is constant; tone adapts.
- Build the visual identity system — Design visual elements that reinforce the positioning: logo, color, typography, imagery style, and spatial principles. Every visual choice should be traceable back to a positioning rationale. "We chose bold colors" is a preference; "we chose high-contrast colors because our positioning emphasizes clarity and confidence" is a brand decision.
- Create governance infrastructure — Build templates, approval workflows, and a brand asset library that makes on-brand creation easier than off-brand improvisation. Include do/don't examples for every guideline.
- Instrument brand health — Define 3-5 brand health metrics: aided/unaided awareness, attribute association, consideration rate, Net Promoter Score. Measure quarterly and track trends, not snapshots.
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.
- 12d ago First seen · 63 lines · 47 tokens per session scan B 5c98d8de9942
brand-manager is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 1,704 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (nullifies safety policies). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
accessibility-expert
WCAG compliance, screen reader compatibility, and inclusive design patterns. Use when auditing accessibility, fixing a11y issues, or designing inclusive UIs.
ux-researcher
UX research, usability testing, user interviews, wireframing, and information architecture specialist. Use when planning user research, designing interfaces, conducting heuristic evaluations, or creating wireframes. Trigger phrases: UX research, user research, usability, wireframe, user interview, persona, journey…
graphic-designer
Expert graphic designer for digital and print design, color theory, typography, and visual identity.
motion-designer
Expert motion designer for UI animations, micro-interactions, and motion systems.
experience-reviewer
Use when reviewing the experience dimension of a written plan (UX + DX). Dispatched primarily by plan-review-experience (via plan-review). Scores 5 sub-dimensions 0-10 (information hierarchy, state coverage, accessibility, DX ergonomics, AI-slop avoidance). Context: A plan with both UI and API changes needs review.…
amby-ux
UX Designer — AmbyKit role for design; use for that perspective.