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 skills add danielpaulai/Purely-Personal-Run-a-business-by-itself --skill build-my-business-braingit clone --depth 1 https://github.com/danielpaulai/Purely-Personal-Run-a-business-by-itselfWrote 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/danielpaulai/purely-personal-run-a-business-by-itself/build-my-business-brain)<a href="https://agentmods.dev/skills/danielpaulai/purely-personal-run-a-business-by-itself/build-my-business-brain"><img src="https://agentmods.dev/badge/skills/danielpaulai/purely-personal-run-a-business-by-itself/build-my-business-brain/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/skills/danielpaulai/purely-personal-run-a-business-by-itself/build-my-business-brain"><img src="https://agentmods.dev/badge/skills/danielpaulai/purely-personal-run-a-business-by-itself/build-my-business-brain.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 | $0.00163 | $0.02627 |
| Opus 5 | $0.00081 | $0.01314 |
| Sonnet 5 | $0.00033 | $0.00525 |
| Haiku 4.5 | $0.00016 | $0.00263 |
Grade C, and why
build-my-business-brain scanned grade C 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
gap interview in Step 3. Never refuse to run because the folder is empty. How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build My Business Brain · Purely Personal
by Daniel Paul · Purely Personal
Read the reference file before writing a single section:
references/business-brain-template.md: the 8-section canonical Business Brain template this skill fills
One job: produce a BUSINESS-BRAIN.md so specific that every downstream skill sounds like this participant on its first run.
The brain is the single source of truth for the whole system. A vague brain makes every skill vague at once. A specific brain fixes them all at once. One real number beats three vague claims, every time.
WHERE THIS SKILL SITS
Reads from: every foundation document in the project or workspace folder Writes: BUSINESS-BRAIN.md, the one file every other skill reads FIRST Hands off to: /matchmaker to fit the first skill against the finished brain Tell the user the next step in one line after delivering.
STEP 0 · CONTEXT CHECK (always first, never skipped)
Find every source before writing anything. Check, in this order:
-
An existing BUSINESS-BRAIN.md (also accept
business-brain.mdandbrain.md) in Project Knowledge, attached to the chat, or in the workspace folder. If one exists, this run becomes an UPDATE: keep every filled section exactly as it is, fill only the gaps, and never overwrite a real value with a guess. -
The 7-file bootcamp convention. In claude.ai: the Project files. In Cowork or Claude Code: the connected workspace folder, its root, or a
/docsor/foundationsubfolder. The filenames:File Feeds template section icp-[name].md§2 ICP voice-dna-[name].md§5 Voice DNA positioning-[name].md§1 Identity, §7 Design Tokens messaging-[name].md§6 Messaging, §4 Proof rule1-[name].md§6 Messaging (Rule of 1) personal-story-[name].md§1 Identity (unique angle) business-inbox-[name].md(aliasinbox-[name].md)§3 Offer, §8 Standing Facts -
Any recognizable foundation document regardless of filename: a Voice DNA, ICP profile, Brand Positioning, Messaging House, offer doc, about page, sales page, pitch deck notes, testimonial list. If it holds real facts about this business, it is a source. Read it.
-
Nothing found: say so plainly, then build the brain entirely through the gap interview in Step 3. Never refuse to run because the folder is empty.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 240 lines · 163 tokens per session scan C 1b5c0c50047d
build-my-business-brain is a skill published in the GitHub repository danielpaulai/Purely-Personal-Run-a-business-by-itself (2 stars, last pushed 29d ago), licensed MIT. It adds 163 tokens to every session and 2,627 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
obsidian
Obsidian vault: search/read/write notes, backlinks, Bases, Canvas.
loopx-doc-registry
Use when a connected LoopX project is asked to read, remember, record, index, register, or use a durable project material such as a Lark/wiki/design doc, research note, SOP, owner packet, migration report, benchmark paper, or external material source. Use even when the user does not mention LoopX or doc registry.
mindos-zh
A local knowledge-base assistant for storing and finding decisions, meeting notes, procedures, troubleshooting lessons, and preferences across conversations and coding agents. It works only with the MindOS knowledge base.
excel-author
Create and edit Excel (.xlsx) workbooks with openpyxl. Supports formulas, charts, formatting, and data analysis.
ppt-author
Create and edit PowerPoint (.pptx) presentations programmatically. Requires python-pptx.
ocr-document
Extract text from PDFs, images, and scanned documents. Uses pymupdf (local) or optional cloud OCR APIs.