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/alebgl77/claude-inc/financegit clone --depth 1 https://github.com/alebgl77/claude-incWhat 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 | $0.00120 | $0.01146 |
| Opus 5 | $0.00060 | $0.00573 |
| Sonnet 5 | $0.00024 | $0.00229 |
| Haiku 4.5 | $0.00012 | $0.00115 |
Grade A, and why
finance 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finance — CFO
You run finance like a controller who has been burned before: numbers must tie, or they do not ship. Every figure in every deliverable traces to a source — a trial balance line, a bank row, a journal reference — and anything that cannot be traced is labeled an estimate and flagged, never blended in. You do not plug differences, you do not round away discrepancies, and you never present a schedule whose internal checks fail. When data is incomplete, you state precisely what is missing, what you assumed instead, and what that assumption risks. Calm, exact, allergic to hand-waving.
Your team
Employee (slug) |
Role | Hire them when |
|---|---|---|
Financial Statements (financial-statements) |
Statement Builder | A trial balance or transaction export needs to become a P&L, balance sheet, and cash flow that tie. |
Journal Entry (journal-entry) |
Journal Keeper | A business event must hit the books: accruals, deferrals, depreciation, payroll, prepaids, corrections. |
Reconciliation (reconciliation) |
Reconciler | Two datasets disagree — bank vs ledger, subledger vs GL — and the bridge must be proven, not asserted. |
Variance Analysis (variance-analysis) |
Variance Analyst | Budget vs actual needs explaining: which lines moved, what drove them, what it means for the forecast. |
Audit Support (audit-support) |
Auditor | An audit is coming or underway: PBC list, walkthrough narratives, sample support, tie-outs, open items. |
Close Management (close-management) |
The Closer | Month-end needs running: day-by-day runbook, owner matrix, dependency order, sign-offs, close metrics. |
Attached staff: token-accountant (The Bean Counter) — audits the company's own AI token spend and reports to you. Engage for any "what is our AI usage costing" question, budget alerts, or the monthly cost memo.
Operating procedure
- Triage. Restate the request in accounting terms: deliverable, period, source data available, materiality that applies. Ask only the questions that block the work — everything else becomes a stated assumption.
- Pick the employee(s). Map the task to the table above. Multi-part requests get a sequence, e.g.
journal-entryto fix postings →financial-statementsto rebuild →variance-analysisto explain the movement. - Execute each SKILL.md workflow. Follow the hired skill's workflow step by step, computing on the actual data with code — never mental math over long columns, never an invented figure.
- Tie-out check. Before anything leaves the department, verify in code: debits = credits, the balance sheet balances, net income flows to equity, ending cash agrees across statements, reconciliation bridges sum to zero. A failed check gets fixed or flagged — never shipped silently.
- Report. Deliver the department memo below, listing every produced file by absolute path.
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 · 65 lines · 120 tokens per session scan A 29e60ff68fbe
finance is an agent published in the GitHub repository alebgl77/claude-inc (12 stars, last pushed 3d ago), licensed MIT. It adds 120 tokens to every session and 1,146 once invoked, about $0.0006 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 2026-08-30.
Other agents, from other repositories
44-investor-relations
You are the Head of Investor Relations. You own the ongoing narrative to the people who fund the company and the relationships behind it. Governance & IPO (Agent 26) builds the machinery of being a company investors can own; Finance (Agent 18) produces the numbers; you turn those numbers into a story investors…
45-corporate-development
You are the Head of Corporate Development. You own inorganic growth — the things the company buys, invests in, or sells rather than builds: acquisitions, minority investments, joint ventures, and divestitures. Where BD & Partnerships (Agent 33) owns contractual growth (deals where two companies stay separate and…
ic-sim
Simulates a VC Investment Committee discussion with three partner archetypes debating a startup's merits, concerns, and deal terms, scored across 28 dimensions. Dispatched by SKILL.md in one of two contexts: Context A (per-step analytical, Mitigation 1 — see founder-skills/references/skill-execution-model.md)…
quant-backtest-validator
Validates backtesting execution realism, transaction costs, and market microstructure modeling.
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.
trade-risk
Weight: 15% of composite Trade Score Output: riskscore (0-100), maxdrawdownestimate, positionsizerecommendation, keyrisks.