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 matteotitta/genesys-skills --skill company-cfogit clone --depth 1 https://github.com/matteotitta/genesys-skillsWrote 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/matteotitta/genesys-skills/company-cfo)<a href="https://agentmods.dev/skills/matteotitta/genesys-skills/company-cfo"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/company-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/skills/matteotitta/genesys-skills/company-cfo"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/company-cfo.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 | $0.00167 | $0.04164 |
| Opus 5 | $0.00084 | $0.02082 |
| Sonnet 5 | $0.00033 | $0.00833 |
| Haiku 4.5 | $0.00017 | $0.00416 |
Grade A, and why
company-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 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
company-cfo — monthly company CFO workflow
The standing analysis leadership (Matteo) uses to make runway / hiring / director-drawing / spend decisions. Primary cadence is monthly — run on the 1st for the closed prior month. Weekly, scenario, and pickup modes cover the in-between.
Genesys Growth is a single-director UK Ltd (Genesis Growth Ltd, #14363665), GBP base currency, lumpy consulting revenue collected on monthly invoices through Wise + bank. Same discipline as the source skill (transaction-sum EOM, categorization traps, scenario modeling) applied to Genesys books on Xero.
Data-integrity contract (binding — read before any run)
This skill touches real financial data. Accuracy is non-negotiable. It obeys two rules verbatim:
.claude/rules/financial-data.md— NEVER fabricate, estimate, or hallucinate any figure, client name, amount, or date. Xero MCP is the primary source of truth; Wise CSV exports are the secondary/historical cross-reference — these are the ONLY sources. If both are unavailable or context is lost, STOP and ask ("I don't have access to the source data — connect Xero or share the CSVs"). Never reconstruct from memory. Apply the verified client-name mappings (Granular Insights → Clarisights, Powerplay → Cello, Helium → SmartPricing, 13740668 Canada Inc./Xplenty → Integrate, Simplyk → ClientCo, Octave Technolog → Voiceflow, Raised Networks → Nimbus) when parsing WiseSource name/Target name. Watch the red flags: any client list built without reading the source, any "approximate" figure, any two clients merged, any client not in source data → STOP..claude/rules/pii-redaction.md— before any report is stored or shared, redact PII (end-client contact names, emails, account/sort-code numbers, IBANs). Keep the signal (client company, category, amount, deal context); mask the identity. The report lands inprojects/genesys/goals/and may be pushed to GDrive — redact before both.
Xero access is READ-ONLY. This skill only ever calls: list-bank-transactions, list-payments, list-invoices, list-profit-and-loss, list-accounts, and the read reports list-report-balance-sheet, list-trial-balance, list-aged-receivables-by-contact, list-aged-payables-by-contact, list-organisation-details. It NEVER calls any create-* or update-* Xero tool. Xero is not a paid-credit MCP — reads are free — but the read-only boundary is a hard rule regardless.
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 · 221 lines · 167 tokens per session scan A d4e354e54e4f
company-cfo is a skill published in the GitHub repository matteotitta/genesys-skills (36 stars, last pushed 1mo ago), licensed MIT. It adds 167 tokens to every session and 4,164 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
gingiris-b2b-growth
🇺🇸 B2B SaaS Growth — PLG vs SLG Playbook — Diagnose whether your problem is distribution, pricing, or PMF. PLG/SLG selection by ACV and sales cycle, the 5-stage path from $0 to $10M ARR, NRR discipline, affiliate & channel motion, enterprise tiering. Built from HeyGen, Deel, Vercel, Supabase, Snowflake patterns.…
gr-b2b-growth
A guide to growing a business-to-business software product from early user research to large-scale sales. B2B software is sold to companies rather than individual consumers.
go-to-market-playbook
A reusable Go-to-Market strategy template for both B2B and B2C launches. Covers positioning, messaging, ICP definition, channel selection, and competitive analysis frameworks. By @WeiYipei.
financial-modeling
SaaS financial modeling for founders — operating model, runway, headcount, DCF valuation, consumption-based pricing models, cohort analysis, unit economics by segment, ARR bridge/build, 3-scenario forecasting, and board-ready financials. Use when building financial model, projecting runway, modeling fundraising…
fundraising-strategy
Complete fundraising strategy for B2B SaaS founders. Use when preparing to raise seed/Series A, deciding VC vs bootstrapped path, building pitch deck, running a fundraise process, evaluating term sheets, or planning fundraising timeline. Covers SAFE, priced rounds, and bootstrapper alternatives.
saas-metrics-calculator
Calculate and interpret SaaS metrics for founders: MRR, ARR, NRR, GRR, churn, CAC payback, LTV:CAC, burn multiple, Rule of 40, cohort retention, and scenario models. Use when building investor updates, dashboards, board materials, pricing decisions, or growth diagnostics.