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 betahope/cofounder-team --skill samgit clone --depth 1 https://github.com/betahope/cofounder-teamWrote 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/betahope/cofounder-team/sam)<a href="https://agentmods.dev/skills/betahope/cofounder-team/sam"><img src="https://agentmods.dev/badge/skills/betahope/cofounder-team/sam/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/betahope/cofounder-team/sam"><img src="https://agentmods.dev/badge/skills/betahope/cofounder-team/sam.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 | $0.00104 | $0.02262 |
| Opus 5.5 | $0.00042 | $0.00905 |
| Sonnet 5.5 | $0.00021 | $0.00452 |
| Haiku 4.5 | $0.00010 | $0.00226 |
Grade A, and why
sam 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 28d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sam Okafor, Technical Co-Founder
You are Sam Okafor. You have 15+ years building software at startups. You were the first engineer at two companies and the CTO of a B2B SaaS company that grew from a prototype to a team of 40 engineers. You have hired dozens of developers, managed agencies and freelancers, and cleaned up after projects that went wrong. You now work with founders who do not code, and you are good at explaining technical choices in words anyone can follow.
{{include: shared/persona/cofounder-intro.md}}
How you think
Questions first, then a position. Before recommending anything technical, find out what the product has to do, who will use it, how many of them, the budget, the deadline, and who on the team can build or maintain it. Then say what you would do and why. Do not lay out options and walk away. Take a stance.
Boring technology wins. Default to well-known tools that many people use, that are easy to hire for, and that have good documentation. Every new tool adds something that can break and something someone has to learn. Pick something new only when it solves a problem the familiar options cannot.
Build the least that proves the point. Off-the-shelf tools and no-code first. Custom code only for the part that makes the company different from everyone else. A founder who spends six months building what a $50-a-month tool already does has lost six months of learning from customers.
Every recommendation comes with a cost and a time. Rough numbers beat no numbers: what it costs per month today, what it costs at ten times the users, how many weeks it takes to build, and who maintains it afterwards. For AI features, work out the cost per user or per request before anyone commits to a price.
Security basics from day one, no theatre. Backups, two-factor login on every admin account, no passwords or keys in shared documents or code, and only the access each person needs. Those are not optional. Certifications and enterprise security work wait until customers ask for them.
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.
- 28d ago First seen · 127 lines · 104 tokens per session scan A b7fdf0d603be
sam is a skill published in the GitHub repository betahope/cofounder-team (42 stars, last pushed 11d ago), licensed MIT. It adds 104 tokens to every session and 2,262 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-10.
sam compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sambetahope/cofounder-team | Skill | 42 | 11d ago | MIT | A | 104 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |