audit-support

An audit support skill for testing internal controls over financial reporting under Section 404 of the Sarbanes-Oxley Act, a US law known as SOX.

In plain words
What is it for?
Use it to prepare testing workpapers and support internal or external audit preparation. It is not a replacement for professional audit or legal advice.
Why use it?
It helps organize control tests, choose samples, document evidence, and classify control problems for audits.

Skill for Claude CodeCodex

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 skills/anthropics/knowledge-work-plugins/audit-support
Any agent
npx skills add anthropics/knowledge-work-plugins --skill audit-support
Clone the repo
git clone --depth 1 https://github.com/anthropics/knowledge-work-plugins

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,298 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 $0.00045 $0.03298
Opus 5 $0.00023 $0.01649
Sonnet 5 $0.00009 $0.00660
Haiku 4.5 $0.00005 $0.00330

Measured 3d ago against content hash 6e53c9529c42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-support 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 3d 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.

Origin

Copies of this mod

4 near-identical copies found in the catalogue:

finance/skills/audit-support/SKILL.md · 375 lines

How it starts

The opening of the file, as written. The whole thing — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Support

Important: This skill assists with SOX compliance workflows but does not provide audit or legal advice. All testing workpapers and assessments should be reviewed by qualified financial professionals. While "significance" and "materiality" are context-specific concepts that are ultimately assessed by auditors, this skill is intended to assist professionals in the creation and evaluation of effective internal controls and documentation for audits.

SOX 404 control testing methodology, sample selection approaches, testing documentation standards, control deficiency classification, and common control types.

SOX 404 Control Testing Methodology

Overview

SOX Section 404 requires management to assess the effectiveness of internal controls over financial reporting (ICFR). This involves:

  1. Scoping: Identify significant accounts and relevant assertions
  2. Risk assessment: Evaluate the risk of material misstatement for each significant account
  3. Control identification: Document the controls that address each risk
  4. Testing: Test the design and operating effectiveness of key controls
  5. Evaluation: Assess whether any deficiencies exist and their severity
  6. Reporting: Document the assessment and any material weaknesses

Scoping Significant Accounts

An account is significant if there is more than a remote likelihood that it could contain a misstatement that is material (individually or in aggregate).

Quantitative factors:

  • Account balance exceeds materiality threshold (typically 3-5% of a key benchmark)
  • Transaction volume is high, increasing the risk of error
  • Account is subject to significant estimates or judgment

Qualitative factors:

  • Account involves complex accounting (revenue recognition, derivatives, pensions)
  • Account is susceptible to fraud (cash, revenue, related-party transactions)
  • Account has had prior misstatements or audit adjustments
  • Account involves significant management judgment or estimates
  • New account or significantly changed process

Read the full file on GitHub · 375 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. 3d ago First seen · 375 lines · 45 tokens per session scan A 6e53c9529c42

Subscribe to this mod's changes

audit-support is a skill published in the GitHub repository anthropics/knowledge-work-plugins (23,791 stars, last pushed yesterday), licensed Apache-2.0. It adds 45 tokens to every session and 3,298 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 2026-08-30.

Related

Other skills, from other repositories

advogado-criminal

Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.

sickn33/agentic-awesome-skills · 42 tokens

matter-workspace

Manage matter workspaces — new, list, switch, close, or detach (practice-level). File-management logic for keeping one client or engagement's context separate from every other. Use when working across multiple clients or matters, when the user says "new matter", "switch matter", "list matters", "close matter", or when…

anthropics/claude-for-legal · 82 tokens

patent-novelty-check

Assess patent novelty and non-obviousness against prior art. Use when user says "专利查新", "patent novelty", "可专利性评估", "patentability check", or wants to evaluate if an invention is patentable.

wanshuiyin/Auto-claude-code-research-in-sleep · 59 tokens

mod-actions

Comprehensive moderation toolkit: user actions (ban/mute/DM), strike system, image moderation, report handling, generation moderation, content/training moderation, and NCMEC/CSAM reporting. All via Civitai tRPC API.

civitai/civitai · 52 tokens

auditing-part11-trails

Generates and verifies 21 CFR Part 11-style audit trails — who/what/when, electronic signatures, and tamper-evidence — for OpenMed pipelines in GxP and clinical-trial (GCP) settings. Use when the user runs OpenMed in a regulated/validated environment and needs an attributable, time-stamped, tamper-evident record of…

maziyarpanahi/openmed · 222 tokens

omh-legal-compliance-review

This is a Hermes-native legal-compliance-review workflow skill.

rlaope/oh-my-hermes · 64 tokens