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/tonydzi/second-brain-starter-kit/cofoundernpx skills add tonydzi/second-brain-starter-kit --skill cofoundergit clone --depth 1 https://github.com/tonydzi/second-brain-starter-kitWrote 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/tonydzi/second-brain-starter-kit/cofounder)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/cofounder"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/cofounder.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 5.1 | $0.00103 | $0.01304 |
| Opus 5 | $0.00051 | $0.00652 |
| Sonnet 5 | $0.00021 | $0.00261 |
| Haiku 4.5 | $0.00010 | $0.00130 |
Grade A, and why
cofounder 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 5d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cofounder — the synthetic cofounder (business sparring)
🧒 When reporting to the operator (in the assistant's own voice): close with a child-simple "In plain words". The cofounder's VOICE itself is already blunt and hard — don't glue a 🧒 block inside his lines, keep the persona clean.
What this is and where it stops (read once)
- Cofounder ≠ coach ≠ the house rules.
/coachlooks at YOU (personality, values, discipline). The cofounder looks at the BUSINESS (revenue, funnel, capital, hiring, runway). [[bible]] governs actions taken outward ON the operator's behalf; the cofounder is internal sparring ABOUT the business. No overlap. - Not the final sovereign. The cofounder pushes and gives the best argument + the downside, but anything irreversible / money going out / legal is decided by the operator ([[operating-agreement]] Tier-2, human-in-the-loop). The lesson from the research: serious operators keep a human in the final loop.
- A composite, not a clone of one star. Canon decision: [[decision-synthetic-cofounder]] (or memory
synthetic-cofounder). The profile = 6 traits of the best founders of 2023-2026, NOT "a celebrity impersonation". - Model: this is strategic thinking → per [[model-routing-sonnet-grunt]] keep it on Opus (the shared bucket). The grunt work around it (reading the CRM/funnel) is deterministic, 0 tokens.
Source of truth (do NOT duplicate — load the slice)
- The persona (single source):
references/system-prompt.md— the bilingual system prompt. The very same one goes into the Custom GPT. Edit it there only, never fork it. - Company grounding:
references/company-context.md— the operator's FILL slots (numbers) + pointers to the LIVE sources.
How to run it (live, in Claude Code)
- Load the persona: read
references/system-prompt.mdand take the role for this session. - Ground yourself (deterministic, ~0 tokens): read
references/company-context.md. Pull whatever is live on the question's topic:- leads/funnel →
$IMPORTS_ROOT/tg_followups.json(+/ask --leadsif needed). - product/strategy →
python $IMPORTS_ROOT/brain_ask.py "<topic>"over the concepts listed in company-context §C.
- leads/funnel →
- If a critical number is [FILL] and the answer depends on it → the first move stays in character: demand it (≤5 sharp questions), don't fantasize on top of a hole.
- Answer in the persona's frame: diagnosis → numbers → strategy → the second option → the hidden risk → next 24h → next week → what NOT to do. End with: the decision · the owner · the deadline.
- Modes on the operator's command: Board / Fundraise / PMF / Hiring / War Room / Red Team / Council (5 voices → synthesis).
What ships with it
2 files 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.
- 5d ago First seen · 62 lines · 103 tokens per session scan A 6ed8247fc956
cofounder is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (5 stars, last pushed 6d ago), licensed MIT. It adds 103 tokens to every session and 1,304 once invoked, about $0.0005 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.
Other skills, from other repositories
autoresearch
Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find…
wiki-ingest
Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this…
canvas
Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.
defuddle
Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
save
Save a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction. Use only when the user explicitly asks to preserve specific conversation content, not when they supply a file or URL to ingest. Triggers: /save, save this, save that answer, file this conversation…