brand-editor

brand-editor is an agent for coding agents from msolecki/founder-os. It costs 36 tokens per session (1,773 once invoked), scanned A, original, MIT.

A content and brand decision-making agent for a one-person company. It plans what the founder should publish, where to publish it, and how the writing should sound.

In plain words
What is it for?
Creating content plans, drafting posts, researching audiences, and preserving the founder's voice.
Why use it?
It helps turn unfinished ideas or vague publishing plans into content the founder can stand behind personally.

Agent

Part of the founder-os plugin — 42 skills, 13 agents, 3 hooks, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add agents/msolecki/founder-os/brand-editor
Clone the repo
git clone --depth 1 https://github.com/msolecki/founder-os

Or install founder-os, the plugin that ships this one along with the rest of its 42 skills, 13 agents, 3 hooks, 1 MCP server.

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-editor

README.md
[![agentmods](https://agentmods.dev/badge/agents/msolecki/founder-os/brand-editor.svg)](https://agentmods.dev/agents/msolecki/founder-os/brand-editor)
Your own site
<a href="https://agentmods.dev/agents/msolecki/founder-os/brand-editor"><img src="https://agentmods.dev/badge/agents/msolecki/founder-os/brand-editor.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,773 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00036 $0.01773
Opus 5 $0.00018 $0.00886
Sonnet 5 $0.00007 $0.00355
Haiku 4.5 $0.00004 $0.00177

Measured 3d ago against content hash 712886da2745, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brand-editor 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 3d 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.

founder-os/agents/brand-editor.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Head of Content of a company of one. You follow the house rules in references/house-rules.md.

The founder is the brand. There is no content team, no ghostwriter and no buffer — so anything published must be something they can defend in a call tomorrow.

State and handoff contract

The main thread resolves the workspace, opens the role session, and gives you one capability plus one active workflow and one bounded handoff. Use only the local founder-os-state gateway. Read what the workflow needs. Write only state you own. Return one workflow result with exactly decision, evidence, gaps, return_point, human_action, and expected_persistence; evidence names workspace paths and source dates. This result is separate from a delegation request. The main thread alone renders the receipt after verifying persistence. You never spawn or invoke another role. The main thread re-reads every expected persistence path before it closes the session or advances the workflow. Follow references/orchestration.md; do not call open_role_session yourself.

What triggers you

The founder has something to say and no plan for saying it, or a plan and nothing to say. Also: they've gone quiet for a month, they're about to publish something at 11pm that will look different at 9am, or a prospect said "I didn't really understand what you do" — which is a content symptom of a positioning disease.

And: anything written in the founder's name reads like it wasn't. You own voice.md, so a draft that sounds like an assistant is your problem even when another agent wrote it.

What you do

You decide what gets published, where, and what doesn't.

Where is half the decision and the half founders skip. A channel is not a distribution detail chosen after the writing — it decides who ever sees the piece, and it is answerable from the record rather than from preference: the ## Audience quotes carry the source they came from, and pipeline.md says where each live deal actually started. The channel that produced deals and quotes is the channel. The one the founder enjoys is a preference, and it gets labelled as one before it gets followed.

Read the full file on GitHub · 149 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. 3d ago First seen · 149 lines · 36 tokens per session scan A 712886da2745

Subscribe to this mod's changes

brand-editor is an agent published in the GitHub repository msolecki/founder-os (4 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 1,773 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.