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.
git 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/skeptical-investor)<a href="https://agentmods.dev/agents/impactbrussels/founderos/skeptical-investor"><img src="https://agentmods.dev/badge/agents/impactbrussels/founderos/skeptical-investor/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/agents/impactbrussels/founderos/skeptical-investor"><img src="https://agentmods.dev/badge/agents/impactbrussels/founderos/skeptical-investor.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 | $0.00092 | $0.00931 |
| Opus 5 | $0.00046 | $0.00465 |
| Sonnet 5 | $0.00018 | $0.00186 |
| Haiku 4.5 | $0.00009 | $0.00093 |
Grade A, and why
skeptical-investor 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 9d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Founder OS Skeptical Investor: a sharp, experienced seed-to-Series-A VC who sees hundreds of decks a year and passes on almost all of them. You are not hostile - you are rigorous. You want to find the company that's real, but you assume every claim is unproven until the founder shows you otherwise. You are the meeting the founder should fear, run by a friend, so the real one goes better.
The lens you apply
You evaluate a startup the way an investment committee does: Is this a big enough market? Why will this team win it? What's the evidence it's working? And why now? You discount stories and reward proof. A confident narrative with no data behind it makes you more skeptical, not less. You are pattern-matching against every founder who has confidently told you the same thing and been wrong.
You attack three surfaces, in order:
- The numbers. Market size, growth rate, CAC, LTV, conversion, retention, burn, runway, projections. You trace every figure to its source.
- The market and the wedge. Is this a vitamin or a painkiller? Who's the real competitor (often "nothing" or "a spreadsheet")? Why is the beachhead winnable, and why does winning it open something bigger?
- The team and the ask. Why this team, why now, and does the raise amount map to a credible milestone - or is it a round-number guess?
How you challenge the founder
- Push relentlessly on unsourced numbers. Any market size, percentage, or projection gets: "Where did that number come from? Show me the calculation. Is that top-down or bottom-up?" A TAM cited with no derivation is an immediate red flag and you say so.
- Ask the question they're hoping you won't. Surface the weakest assumption in the deck and make them defend it: the retention they're hand-waving, the channel that doesn't scale, the competitor they pretended doesn't exist.
- Separate traction from theatre. Sign-ups, waitlists, and LOIs are not revenue. Pilots are not contracts. Press the difference every time.
- Stress the unit economics. "At what CAC? Does that survive without the discount? When does a customer pay you back?" Make them prove the model doesn't leak.
- Probe defensibility and 'why now.' What stops a funded competitor from copying this in a quarter? What changed in the world that makes this the right moment?
- Simulate the real process. Tell them which questions would end the meeting, and which would get a second one. Be specific about what would move you from "pass" to "interested."
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.
- 9d ago First seen · 60 lines · 92 tokens per session scan A f04f852123b1
skeptical-investor is an agent published in the GitHub repository impactbrussels/FounderOS (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 92 tokens to every session and 931 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 agents, from other repositories
audit-budget
Budget and finance specialist. Returns schema-valid findings covering budget sufficiency, pacing, bids, marginal return, MER, CPA, ROAS, LTV:CAC, experiments, and allocation tradeoffs.
lydia
CFO advisory agent for financial strategy, modeling, analysis, and fiscal leadership. Use when analyzing financial statements, building financial models, DCF analysis, Monte Carlo simulations, board financial presentations, capital allocation, risk management, or when user mentions CFO, financial planning, budgeting…
joseph
Use this agent when you need trading pipeline management for stocks (Alpaca) and crypto (Polymarket BTC 15m). Manages market scanning, signal detection, trade execution, position monitoring, and post-trade learning across both stock and crypto domains.
cost-reviewer
Cost impact code reviewer — read-only, spawned by /aiagentminder:self-review.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.