finance

A finance lead that coordinates specialists for accounting and financial planning work. Its team prepares financial statements, records journal entries, reconciles mismatched records, analyzes differences, supports audits, and manages closing the books.

In plain words
What is it for?
Use it for income statements, balance sheets, cash-flow reports, accounting entries, reconciliations, budget or actual comparisons, audit support, and period-end close work.
Why use it?
It keeps financial results traceable to source records and flags missing information instead of hiding gaps with unsupported estimates. It is designed for figures that must agree across reports.

Agent

Install

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.

agentmods
npx agentmods add agents/alebgl77/claude-inc/finance
Clone the repo
git clone --depth 1 https://github.com/alebgl77/claude-inc
Per session 120 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,146 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 29e60ff68fbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

agents/finance.md · 65 lines

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

  1. 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.
  2. Pick the employee(s). Map the task to the table above. Multi-part requests get a sequence, e.g. journal-entry to fix postings → financial-statements to rebuild → variance-analysis to explain the movement.
  3. 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.
  4. 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.
  5. Report. Deliver the department memo below, listing every produced file by absolute path.

Read the full file on GitHub · 65 lines

Changes

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.

  1. 2d ago First seen · 65 lines · 120 tokens per session scan A 29e60ff68fbe

Subscribe to this mod's changes

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.

Related

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…

ankitjha67/product-architect · 0 tokens

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…

ankitjha67/product-architect · 0 tokens

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)…

lool-ventures/founder-skills · 247 tokens

quant-backtest-validator

Validates backtesting execution realism, transaction costs, and market microstructure modeling.

stefan-jansen/claude-code-toolkit · 15 tokens

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.

TelivityAI/otaip · 0 tokens

trade-risk

Weight: 15% of composite Trade Score Output: riskscore (0-100), maxdrawdownestimate, positionsizerecommendation, keyrisks.

zubair-trabzada/ai-trading-claude · 0 tokens