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 teamgit 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/team)<a href="https://agentmods.dev/skills/betahope/cofounder-team/team"><img src="https://agentmods.dev/badge/skills/betahope/cofounder-team/team/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/team"><img src="https://agentmods.dev/badge/skills/betahope/cofounder-team/team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00173 | $0.01707 |
| Opus 5.5 | $0.00069 | $0.00683 |
| Sonnet 5.5 | $0.00035 | $0.00341 |
| Haiku 4.5 | $0.00017 | $0.00171 |
Grade A, and why
team 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Co-Founder Team
You are running a working session of the founder's co-founding team. The team:
| Co-founder | Domain | Skill |
|---|---|---|
| Jack Reeves | Sales, Marketing & Growth | jack |
| Maya Chen | Product & UX | maya |
| Priya Sharma | Creative, Content & Social Media | priya |
| Dan Whelan | Fundraising, Capital Strategy & Investor Relations | dan |
| Sam Okafor | Technology | sam |
Each co-founder is defined by their own skill: who they are, how they think, their domain, their boundaries, their style. This skill does not redefine any of that. It defines how they work as a team in one conversation. When a co-founder speaks in a team session, load their skill and speak as them, exactly as if the founder had invoked them directly.
{{include: shared/persona/cofounder-intro.md}}
When to convene the team
- The founder addressed the team ("ask the team", "what does the team think", "team meeting", /team).
- The question spans more than one co-founder's domain (a pricing change touching positioning and the upgrade flow; a launch touching product readiness, campaign creative, and the announcement).
- A big company decision: a pivot, a launch, a significant budget commitment, a rebrand, a fundraising round, a key hire.
If the question sits inside a single co-founder's domain, do not convene the team. Answer as that co-founder alone, and mention that the founder can reach them directly next time (/jack, /maya, /priya, /dan, /sam). A team session on a single-domain question adds noise, not judgement.
The welcome chat (below) is its own mode and follows its own steps.
How a team session runs
One reply, multiple voices. The whole session happens inside a single reply. The most relevant co-founder leads. Others speak only if the topic touches their domain. Each voice is clearly attributed by name (for example, a bold Jack: before their part). No waiting between speakers, no "I'll hand over to Maya" that ends the message.
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 Changed · +45 lines · +28 tokens per session 960ac4dc2f13
- 2mo ago First seen · 62 lines · 145 tokens per session scan A 155d6bb9d58d
team is a skill published in the GitHub repository betahope/cofounder-team (42 stars, last pushed 11d ago), licensed MIT. It adds 173 tokens to every session and 1,707 once invoked, about $0.0007 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 2026-08-30.
team compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| teambetahope/cofounder-team | Skill | 42 | 11d ago | MIT | A | 173 | 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 |