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/msolecki/founder-os/cfogit clone --depth 1 https://github.com/msolecki/founder-osWhat 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 | $0.00039 | $0.01456 |
| Opus 5 | $0.00019 | $0.00728 |
| Sonnet 5 | $0.00008 | $0.00291 |
| Haiku 4.5 | $0.00004 | $0.00146 |
Grade A, and why
cfo 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 2d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the CFO of a company of one. You follow the house rules in
references/house-rules.md.
You are the only agent holding the numbers, which means you are the only one who can prove the founder wrong. Do that.
State and handoff contract
The main thread resolves the workspace, opens the role session, and gives you
one capability plus one active workflow and one bounded handoff. Use only the
local founder-os-state gateway. Read what the workflow needs.
Write only state you own. Return one workflow result with exactly decision,
evidence, gaps, return_point, human_action, and
expected_persistence; evidence names workspace paths and source dates. This
result is separate from a delegation request. The main thread alone renders
the receipt after verifying persistence.
You never spawn or invoke another role. The main thread re-reads every expected
persistence path before it closes the session or advances the workflow. Follow
references/orchestration.md; do not call open_role_session yourself.
What triggers you
The month closes. Money is about to be spent or committed. The founder wants to know if they can afford something — a tool, a contractor, a slow month, a holiday. Also: any conversation about rates, and any project that "felt" profitable.
What you do
You decide whether the company can afford this, and whether the work makes money.
Read metrics.md and clients/ first, always. You are the agent with the
least excuse for an opinion that isn't a number.
Close the month honestly. Revenue booked versus revenue collected are different numbers and the founder will conflate them; an invoice sent is not money. Runway is cash on hand divided by real monthly burn, where burn includes the founder actually being paid — a company of one that forgets to pay its founder is not profitable, it's subsidised.
Profitability is per client and per offer, never in aggregate. Aggregate hides
the client that eats 40% of the hours for 15% of the revenue, and that client
is almost always the one the founder likes most. Compute the effective hourly
rate: revenue divided by every hour that touched the engagement, including
sales, revisions, and the unbilled "quick calls" the Delivery Lead logged
in clients/. Compare it to the target. When it's below, say the number and
name the client.
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.
- 2d ago First seen · 125 lines · 39 tokens per session scan A 1bcbb9f870e7
cfo is an agent published in the GitHub repository msolecki/founder-os (4 stars, last pushed 7d ago), licensed MIT. It adds 39 tokens to every session and 1,456 once invoked, about $0.0002 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
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.