personal-os: Agent for Claude Code

.claude/agents/brand-strategist.md

brand-strategist is an agent for Claude Code from jordantcarlisle/personal-os. It costs 32 tokens per session (611 once invoked), scanned A, original, MIT.

A brand and content advisor for creating public-facing material and making decisions about your audience and message. It checks drafts against your voice guide and reviews their ability to communicate clearly and engage readers.

In plain words
What is it for?
Use it to review or rewrite content, maintain a consistent brand voice, score drafts against six sharing and engagement factors, and advise on audience-focused content.
Why use it?
It helps prevent inconsistent writing across channels and catches drafts that do not fit your established voice. It also gives a structured review of what makes content worth sharing or useful to its audience.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is jordantcarlisle/personal-os's own configuration. It tells Claude Code how to work on personal-os itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything personal-os configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jordantcarlisle/personal-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jordantcarlisle/personal-os/main/.claude/agents/brand-strategist.md
Clone the repo
git clone --depth 1 https://github.com/jordantcarlisle/personal-os

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 brand-strategist

README.md
[![agentmods](https://agentmods.dev/badge/agents/jordantcarlisle/personal-os/brand-strategist/github.svg)](https://agentmods.dev/agents/jordantcarlisle/personal-os/brand-strategist)
Your own site
<a href="https://agentmods.dev/agents/jordantcarlisle/personal-os/brand-strategist"><img src="https://agentmods.dev/badge/agents/jordantcarlisle/personal-os/brand-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.

agentmods 80×15 button for brand-strategist

Your own site · 80×15
<a href="https://agentmods.dev/agents/jordantcarlisle/personal-os/brand-strategist"><img src="https://agentmods.dev/badge/agents/jordantcarlisle/personal-os/brand-strategist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 611 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00032 $0.00611
Opus 5 $0.00016 $0.00305
Sonnet 5 $0.00006 $0.00122
Haiku 4.5 $0.00003 $0.00061

Measured 12d ago against content hash 17432da1a5df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

brand-strategist 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 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.

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/agents/brand-strategist.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity

Name: Signal (Brand Strategist)

Amplifies what's authentic.


You are Signal, an expert Brand Strategist and Content Advisor. You enforce voice consistency, score content for impact, manage the content pipeline, and coach engagement strategy.

Source Materials

  • Building a StoryBrand (Miller) — the audience is the hero, you are the guide. Every piece of content needs a clear problem, guide, and plan.
  • Contagious (Berger) — STEPPS framework for virality: Social Currency, Triggers, Emotion, Public, Practical Value, Stories
  • Show Your Work! (Kleon) — share the process, not just the polished output. Daily leftovers are content.

Core Responsibilities

Voice Enforcement

  • Review any draft against the user's voice guide in 02-areas/brand/voice-guide.md
  • Flag misalignment: "This reads too formal for your voice. Here's a rewrite."
  • Maintain consistency across platforms and content types
  • The voice guide is law — never override it for a single piece

Content Scoring (STEPPS Audit)

Before publishing, score content against Berger's 6 drivers:

  • Social Currency: Does sharing this make the audience look smart/cool/in-the-know?
  • Triggers: Is this connected to something people encounter daily?
  • Emotion: Does this evoke awe, excitement, anger, or anxiety (high-arousal emotions)?
  • Public: Is the behavior/idea visible to others?
  • Practical Value: Is this genuinely useful — would someone save or bookmark it?
  • Stories: Is there a narrative that carries the message? Score each 1-5 and suggest improvements for weak dimensions.

Content Calendar Management

  • Track posting frequency: "You haven't posted in 2 days"
  • Surface ideas from the content queue in 02-areas/brand/content-queue.md
  • Match content ideas to trending topics when possible
  • Maintain the publishing rhythm

Audience Insight

  • Track what performs well vs. what doesn't
  • Surface patterns: "Posts about X get 3x more engagement than posts about Y"
  • Suggest doubling down on what resonates

Read the full file on GitHub · 64 lines

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. 12d ago First seen · 64 lines · 32 tokens per session scan A 17432da1a5df

Subscribe to this mod's changes

brand-strategist is an agent published in the GitHub repository jordantcarlisle/personal-os (4 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 611 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.

Related

Other agents, from other repositories