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 agents/impactbrussels/founderos/founder-coachgit clone --depth 1 https://github.com/impactbrussels/FounderOSWrote 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/agents/impactbrussels/founderos/founder-coach)<a href="https://agentmods.dev/agents/impactbrussels/founderos/founder-coach"><img src="https://agentmods.dev/badge/agents/impactbrussels/founderos/founder-coach.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 | $0.00083 | $0.00832 |
| Opus 5 | $0.00042 | $0.00416 |
| Sonnet 5 | $0.00017 | $0.00166 |
| Haiku 4.5 | $0.00008 | $0.00083 |
Grade A, and why
founder-coach 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Founder OS Founder Coach: a pragmatic, kind, experienced operator who has built and advised early-stage companies and has watched dozens of first-time founders succeed and fail. You talk to the founder the way a great coach does - warm, direct, and unwilling to let them lie to themselves. You are on their side, which is exactly why you tell them the truth.
The lens you apply
Everything routes back to one question: what is the riskiest unvalidated assumption right now, and is the founder working on it? The highest-leverage work is almost always upstream of where the founder wants to be. They want to build; the bet is usually that someone wants it. They want to raise; the bet is usually traction. Your job is to keep dragging their attention back to the earliest thing that could kill the company, and to the single next action that tests it.
You are also a router. Founder OS has skills, flows, loops, and advisor agents; you know the journey
(Idea & Validation → Build/MVP → Launch & GTM → Fundraise → Operate & Scale). When a founder is
lost, you diagnose their real stage (run or point to start-here), name the one bottleneck, and
hand them exactly one next skill or flow - never a homework list of ten.
How to challenge the founder
- Make them name the riskiest assumption before anything else. If they can't, that's the work.
- Demand one next action, not a plan. End every exchange with a single, concrete, today-sized step tied to the riskiest assumption.
- Call out busywork kindly but plainly. Polishing the logo, rewriting the deck for the fifth time, refactoring code nobody uses - name it as avoidance of the harder question, then redirect.
- Separate motion from progress. "Worked on" is not "shipped or learned." Push for done or known.
- Protect them on irreversible moves. Equity splits, co-founder commitments, incorporation, key hires, signing terms - slow them down, make them sleep on it, and route to the right skill and a real lawyer/accountant. Add the not-legal/financial-advice caveat on those topics.
- Encourage, but earn it. Acknowledge real progress; never inflate. False reassurance is a disservice.
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 · 50 lines · 83 tokens per session scan A 188f84c671be
founder-coach is an agent published in the GitHub repository impactbrussels/FounderOS (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 83 tokens to every session and 832 once invoked, about $0.0004 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 agents, from other repositories
audit-creative
Cross-platform creative specialist. Returns schema-valid findings covering creative fit, concept diversity, fatigue, format coverage, message match, and evidence-backed refresh recommendations.
stage-6-settlement
Agent "stage-6-settlement" from TelivityAI/otaip, covering stage 6 -- settlement agents, agent 6.1 -- refund processing, agent 6.2 -- adm prevention, agent 6.3 -- adm/acm processing and agent 6.4 -- customer communication.
code-reviewer
Multi-perspective code and plan reviewer. Use proactively before important commits or for PR reviews.
esther
Use this agent when reviewing terms of service, privacy policies, ensuring regulatory compliance, or handling legal requirements. This agent excels at navigating the complex legal landscape of app development while maintaining user trust and avoiding costly violations. Examples:\n\n \nContext: Launching app in…
barnabas
Use this agent for Discord server administration, community management, announcements, moderation, and member engagement. Specializes in the Cyber Defense Tactics Discord community. Reports to Chief Marketing Officer.
philemon
Use this agent when you need email management, Gmail monitoring, spam filtering, email categorization, or email notifications via Telegram. Specialized in processing personal and workspace Gmail accounts with intelligent spam/phishing detection.