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 skills/jgerton/brand-toolkit/startnpx skills add jgerton/brand-toolkit --skill startgit clone --depth 1 https://github.com/jgerton/brand-toolkitWrote 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/skills/jgerton/brand-toolkit/start)<a href="https://agentmods.dev/skills/jgerton/brand-toolkit/start"><img src="https://agentmods.dev/badge/skills/jgerton/brand-toolkit/start.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 | $0.00064 | $0.00978 |
| Opus 5 | $0.00032 | $0.00489 |
| Sonnet 5 | $0.00013 | $0.00196 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
start 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 4d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the brand-toolkit entry point. Your job is to assess where the user is in their brand journey and route them to the right skill.
Step 1: Find Existing Brand Brief
Run the discovery chain:
- Check the current working directory for
brand-brief.md - If a
codebasepath is known, check there too - If
vault_pathis set in an existing brief, check that location
Use Glob to search: **/brand-brief.md
Step 2: If Brand Brief Found
Read the brief. Summarize current state to the user:
- What stage they're at (seed/positioning/messaging/voice/visual/launch/growth)
- What's complete, what's in progress, what's missing
- Confidence levels on completed work
- Any inconsistencies or gaps
Then recommend the next action based on gaps. Present it as:
Your brand brief is at the [stage] stage.
- Positioning: [status] ([confidence summary])
- Messaging: [status]
- Voice: [status]
- Visual: [status]
Recommended next step: [skill name] because [reason]. Alternative: [other option] if [condition].
Step 3: If No Brand Brief Found
Assess readiness from what the user has told you. Look for signals:
Has research/validation (route to brand-positioning):
- Mentions customers, users, or audience specifics
- Has competitive knowledge
- Has done market research or customer interviews
- Has revenue or traction data
Has existing assets (route to brand-audit):
- Mentions existing website, app, or product
- Has a logo, colors, or brand guide
- Has scattered brand elements that need formalization
- Mentions inconsistency across channels
Has only an idea (seed stage):
- "I have an idea for..."
- "I'm thinking about building..."
- No mention of customers, market, or existing assets
- Vague problem description
For seed-stage users:
Explain honestly that brand positioning works best with a foundation. Don't gatekeep, but be transparent:
Brand positioning is strongest when built on real knowledge of your market and customers. Right now you're at the seed stage. Here are your options:
Option A: Validate first (recommended) Use
market-researcherto validate the problem and understand the competitive landscape. This gives brand-positioning real data to work with.Option B: Stress-test the idea Use
ideation-expertto pressure-test your concept before investing in brand work.Option C: Start a seed brief and build first I'll create a minimal brand-brief.md with what we know now, and you can come back for positioning after you've built something and talked to users. Sometimes the brand reveals itself through the work.
Which path feels right?
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.
- 4d ago First seen · 99 lines · 64 tokens per session scan A a717fd43fead
start is a skill published in the GitHub repository jgerton/brand-toolkit (59 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 978 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-cut
剪辑中文口播原素材：逐词转录、词典修字出修字表、五轮扫描找口误与重复、汇总表与重复句子表、打开 Studio 让用户复核、复盘沉淀用户偏好与词典。只产出一份已复核的删词账本，不切媒体、不做字幕、不做分镜动画。用户说剪口播、处理口误、生成口播基础素材、继续剪口播，或确认卡回传 action=returncutreview 时使用。不要用于执行物理剪切、导出剪后视频、单独安装、单独打开工作台或口播分镜成片。.
chengfeng-check-updates
剪辑环境的唯一管理者：就绪检查（skills 是否最新 → Runtime 是否配套）、Skills 更新激活、Runtime 安装与体检。用户说检查更新、安装剪辑环境、装播放器、检查剪辑环境、剪辑环境就绪了吗、配置转录凭证时使用；业务 Skill（剪口播/字幕/画面/导出）第 0 步也引用本 Skill 的就绪检查。不用于剪辑、字幕、画面、导出本身或项目数据迁移。.
infographic-template-updater
Update template catalogs and UI prompts after adding new infographic templates (src/templates/.ts), including SKILL.md template list, site gallery template mappings, and the AIPlayground prompt list.