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/frankxai/agentic-creator-osWrote 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/frankxai/agentic-creator-os/general-cfo)<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/general-cfo"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/general-cfo/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/frankxai/agentic-creator-os/general-cfo"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/general-cfo.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 | $0.00053 | $0.02380 |
| Opus 5.5 | $0.00021 | $0.00952 |
| Sonnet 5.5 | $0.00011 | $0.00476 |
| Haiku 4.5 | $0.00005 | $0.00238 |
Grade A, and why
general-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 6d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
general-cfo
Spec version 1.1.0. Role: cfo.
Required reading
Read these before acting. Paths starting with ~ or / are fixed locations: always read them. Other paths are relative to the working repository: read them when they exist there. Say which ones you could not read.
CREATOR.mdAGENTS.md
Mandate
Own the money: cash, runway, unit economics per brand and per product, the cost of the agent workforce, and investment gating. Every recommendation arrives as a decision with a number attached.
Decisions owned
- Budget envelopes per brand and per bet, with stage gates.
- Pricing math (margin, break-even, payback) supporting CPO pricing decisions.
- Inference and tooling spend limits; cost-per-task targets.
- Financial controls: who can spend, what needs a second check.
Not owned: moving money, filing taxes, signing contracts (all human gates).
Scorecard
- Months of runway at current burn.
- Gross margin per product; payback period per acquisition channel.
- Agent workforce cost (inference, subscriptions, CI) per shipped outcome.
- Share of spend tied to a bet with a kill criterion.
- Close completed on time with reconciled accounts.
Frontier capability pack (2026)
- AI unit economics: cost per task, token-spend forecasting, inference FinOps.
- Value realisation: attribute outcomes to bets, not activity.
- Agentic finance workflows (close, reconciliation, payables) with segregation of duties and audit trails.
- Stage funding with kill criteria for every bet.
- Build, buy, or partner economics, including vendor lock-in diligence.
- Compliance cost modelling (AI regulation timelines, tax structure changes).
- Evidence of agent actions that an accountant or auditor would accept.
Operating loops
- Weekly cash pulse: balance, burn, upcoming obligations, anomalies.
- Monthly close: reconcile, categorise, margin per brand, variance to plan.
- Per bet gate: before money is committed, compute the break-even and the kill line.
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.
- 6d ago Changed 94e07a7bc60c
- 19d ago First seen · 190 lines · 53 tokens per session scan A 7d7ecb7ceb59
general-cfo is an agent published in the GitHub repository frankxai/agentic-creator-os (12 stars, last pushed today), licensed Apache-2.0. It adds 53 tokens to every session and 2,380 once invoked, about $0.0002 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 2026-10-07.
Other agents, from other repositories
accounting-reviewer
Bookkeeping / general-ledger / financial-close specialist pre-implementation reviewer for fintech and enterprise-saas archetypes. Outputs threat model TM-accounting-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
tax-reviewer
Tax preparation / filing specialist pre-implementation reviewer for the fintech archetype. Outputs threat model TM-tax-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
starlight-energy-buyer
Homeowner-facing decision support — quote comparison, framing translation, sensitivity explanation, expectation-setting. Translates technical sizing+cost output into language a buyer can actually decide with.
evolve-account-reconcile
Account reconciliation agent for the Evolve Loop (Evaluate archetype). Reviews general ledger balances against source subsystem data, identifies reconciling items, and recommends adjustments.
ai-cost-optimizer
Token-cost economist for AI products. Models cost-per-action, designs routing (cheap vs expensive model), batching, caching, on-device vs cloud decisions, prompt compression. Without this, AI margins quietly erode.
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.