accountant-controller

accountant-controller is a skill for Claude Code, Codex from wonsukchoi/domain-experts. It costs 66 tokens per session (2,455 once invoked), scanned A, original, MIT.

An accounting and financial-control guide for keeping a company's historical books accurate through each reporting period.

In plain words
What is it for?
Use it for period-end book closing, bank and account reconciliations, revenue-recognition questions, internal-control design or testing, and investigating financial discrepancies.
Why use it?
It helps trace reconciliation differences and apply accounting judgments consistently instead of hiding errors or leaving them unresolved.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it for period-end book closing, bank and account reconciliations, revenue-recognition questions, internal-control design or testing, and investigating financial discrepancies.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wonsukchoi/domain-experts/accountant-controller
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.

Any agent
npx skills add wonsukchoi/domain-experts --skill accountant-controller
Clone the repo
git clone --depth 1 https://github.com/wonsukchoi/domain-experts

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for accountant-controller

README.md
[![agentmods](https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/accountant-controller/github.svg)](https://agentmods.dev/skills/wonsukchoi/domain-experts/accountant-controller)
Your own site
<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/accountant-controller"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/accountant-controller/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.

agentmods 80×15 button for accountant-controller

Your own site · 80×15
<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/accountant-controller"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/accountant-controller.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,455 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00066 $0.02455
Opus 5 $0.00033 $0.01228
Sonnet 5 $0.00013 $0.00491
Haiku 4.5 $0.00007 $0.00246

Measured 9d ago against content hash e6170ae961e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

accountant-controller 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.

roles/accountant-controller/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Accountant / Financial Controller

Identity

Owns the accuracy of the historical financial record at a company doing its own GAAP-basis close — accountable for the books being right every period, not for predicting what happens next (that's the financial analyst's job, and this role feeds that one its source data). The defining tension: close fast enough that the business gets timely numbers, without cutting the reconciliation and documentation discipline that makes those numbers trustworthy under audit.

First-principles core

  1. The books have to tie, every period, or nothing built on them can be trusted. An account that doesn't reconcile isn't cosmetic — it means an error exists somewhere, and every downstream number (valuation, tax, forecast) inherits that uncertainty until the variance is traced to its cause, not plugged away.
  2. Substance over form. Treatment follows the actual economic reality of a transaction, not its legal label. A "sale" where the seller keeps all the risk and control isn't a sale for accounting purposes regardless of what the contract is titled.
  3. Controls exist because people and systems make mistakes under normal conditions, not because anyone is assumed dishonest. Segregation of duties and approval thresholds catch the honest error and the rare bad actor with the same mechanism — removing a control because "everyone here is trustworthy" removes the thing that would have caught the mistake nobody intended.
  4. Materiality is a calibrated judgment, not a fixed number, and both directions of error are costly. Chasing every discrepancy to zero burns close-cycle time that doesn't change any decision; waving off a large item as "probably fine" risks a real misstatement. The 5%-of-pretax-income rule of thumb is a starting anchor, not the answer — a $40K item is immaterial at $50M net income and a governance event at $500K.
  5. A number without traceable source documentation is a claim, not a fact. Every figure needs a path back to an invoice, contract, or bank statement — that traceability is what makes it auditable, not the assumption that it's probably right.

Read the full file on GitHub · 94 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 94 lines · 66 tokens per session scan A e6170ae961e1

Subscribe to this mod's changes

accountant-controller is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 2,455 once invoked, about $0.0003 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 skills, from other repositories

ledger-import-fixture-replay

Use when replaying Ledger import CSV fixtures to verify sourceRef preservation, cent normalization, and deterministic posting dates.

z3z1ma/10x · 29 tokens

fix-protocol-financial-trading

Master high-frequency FIX (Financial Information eXchange) protocol messaging (FIX 4.2/4.4/5.0 SP2), QuickFIX engine configuration, low-latency binary encoding (SBE), session state management, order routing, and market data parsing.

hamzabellouch/agent-skills · 65 tokens

payment-gateways-stripe-adyen-integration

Architect and implement secure, PCI-DSS compliant payment processing integrations with Stripe and Adyen, featuring idempotent webhook handling, tokenization, multi-currency processing, automatic retries, and ledger-based reconciliation.

hamzabellouch/agent-skills · 53 tokens

open-banking-iso20022-apis

Architect enterprise Open Banking platforms, PSD2/PSD3 compliant APIs, financial message modeling in ISO 20022 (pacs.008, camt.053, pain.001 XML/JSON), mTLS authentication with eIDAS certificates, and FAPI (Financial-grade API) OAuth2 profiles.

hamzabellouch/agent-skills · 71 tokens

justfix

Use this skill when the user asks for a quote, estimate, price, or "how much" for a UK trades job – electrical, plumbing, locksmith, glazing, carpentry, handyperson, heating, gas, roofing, drains, white goods, or boiler service. Calls the JustFix Estimator MCP server to return a cost breakdown, scope summary, and a…

Just-Fix/justfix-skill · 90 tokens

laravel-billing

Use when implementing subscriptions, invoices, payment methods, webhooks, or billing portals with Laravel Cashier (Stripe or Paddle).

fusengine/codex · 30 tokens