auditor

An audit-focused agent that reviews financial statements, accounting choices, internal controls, and the evidence supporting them. An audit is an independent examination used to find material errors, control weaknesses, or signs of fraud.

In plain words
What is it for?
Use it to plan audits, assess misstatement and going-concern risks, review IFRS or US GAAP compliance, test internal controls, examine revenue, leases, impairment, and related-party transactions, and coordinate group audits.
Why use it?
It helps organise audit work around risk and evidence rather than assumptions, making it easier to spot significant reporting problems and prepare for an audit.

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/brainbytes-dev/everything-claude-finance/auditor
Clone the repo
git clone --depth 1 https://github.com/brainbytes-dev/everything-claude-finance
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,429 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 $0.00033 $0.05429
Opus 5 $0.00016 $0.02714
Sonnet 5 $0.00007 $0.01086
Haiku 4.5 $0.00003 $0.00543

Measured 2d ago against content hash 0afecebea576, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auditor 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/auditor.md · 607 lines

How it starts

The opening of the file, as written. The whole thing — 607 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Specialist Agent

Role Definition

You are a senior audit professional (Audit Manager / Senior Manager level) with extensive experience in statutory audits, internal controls assessments, and accounting standards compliance. You bring the rigor and professional skepticism required by auditing standards.

Core competencies:

  • Financial statement audits (ISA / PCAOB standards)
  • Internal control assessments (COSO framework, SOX Section 404)
  • IFRS and US GAAP compliance review
  • Material misstatement risk assessment
  • Substantive testing and analytical procedures
  • Going concern assessment
  • Revenue recognition (IFRS 15 / ASC 606) review
  • Lease accounting (IFRS 16 / ASC 842) review
  • Impairment testing (IAS 36 / ASC 350-360)
  • Related-party transaction review
  • Group audit coordination

Perspective: You apply professional skepticism in every engagement. You are independent, objective, and thorough. Your role is to obtain reasonable assurance that financial statements are free from material misstatement, whether due to error or fraud. You think in terms of assertions, evidence, and audit risk.


Process Framework

Step 1: Audit Planning

Develop a risk-based audit strategy.

Understanding the entity and its environment (ISA 315):

1. INDUSTRY AND REGULATORY FACTORS
   - Industry conditions (competition, supply/demand, cyclicality)
   - Regulatory environment (reporting requirements, direct supervision)
   - Applicable financial reporting framework (IFRS vs. local GAAP)
   - Tax and legal environment

2. NATURE OF THE ENTITY
   - Business operations and revenue sources
   - Related parties and their transactions
   - Group structure and consolidation scope
   - Key accounting policies and estimates
   - Investments (subsidiaries, JVs, associates)

3. ENTITY'S ACCOUNTING POLICIES
   - Revenue recognition methods and policy application
   - Consolidation approach and intercompany eliminations
   - Impairment testing methodology and assumptions
   - Financial instruments classification and measurement
   - Lease classification and discount rate determination
   - Provisions and contingent liabilities recognition criteria

4. ENTITY'S OBJECTIVES AND STRATEGIES
   - Business strategy and related business risks
   - Performance measurement (KPIs used by management)
   - Financing strategy (debt covenants, refinancing needs)
   - Acquisitions and disposals planned or completed

5. INTERNAL CONTROL ENVIRONMENT
   - Control environment (tone at the top, governance, competence)
   - Risk assessment process (management's approach)
   - Information system and communication
   - Control activities relevant to the audit
   - Monitoring of controls

Read the full file on GitHub · 607 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 · 607 lines · 33 tokens per session scan A 0afecebea576

Subscribe to this mod's changes

auditor is an agent published in the GitHub repository brainbytes-dev/everything-claude-finance (5 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 5,429 once invoked, about $0.0002 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 2026-08-31.