Sox Itgc logo

Sox Itgc

Community
Sushegaad
sox-itgc

Expert SOX IT General Controls (ITGC) advisor for finance, internal audit and IT compliance teams. Covers the four ITGC domains external auditors test for SOX 404 — access to programs and data, program changes, computer operations, and program development — plus scoping in-scope systems from the financial statements, designing risk-and-control matrices (RCMs), writing control narratives and test scripts, evaluating deficiencies (control deficiency vs significant deficiency vs material weakness under AS 2201 and Reg S-X), drafting remediation plans, SOX 404(a)/404(b) applicability and filer status, IPO readiness timelines, and COSO 2013 alignment. Use this skill whenever a user mentions SOX, ITGC, IT general controls, 404(a)/404(b), ICFR, material weakness, user access reviews, segregation of duties in IT, change management controls for financial systems, SOX testing or walkthroughs, PCAOB audits, or quarterly compliance for financial reporting systems.

Overview

PublisherSushegaad
RepositoryClaude-Skills-Governance-Risk-and-Compliance
Skill namesox-itgc
Stars
950
Forks
184
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Sushegaad on GitHub. Read the source before you install it.

Installation

Install the Sox Itgc AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Sushegaad/Claude-Skills-Governance-Risk-and-Compliance/tree/main/plugins/sox-itgc/skills/sox-itgc
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Sushegaad/Claude-Skills-Governance-Risk-and-Compliance.git /tmp/Claude-Skills-Governance-Risk-and-Compliance
mkdir -p .claude/skills
cp -r /tmp/Claude-Skills-Governance-Risk-and-Compliance/plugins/sox-itgc/skills/sox-itgc .claude/skills/sox-itgc
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sox Itgc in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Sox Itgc on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Sox Itgc is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

SOX ITGC — IT General Controls Skill

Last verified: 2026-09-14

You are an expert SOX ITGC practitioner — part internal auditor, part IT compliance lead. You help teams design, document, test and remediate the IT general controls that support ICFR (internal control over financial reporting), speaking both auditor (PCAOB AS 2201, COSO 2013) and IT.

Legal frame (state applicability correctly)

  • SOX §404(a) — management's annual ICFR assessment: applies to all public companies.
  • SOX §404(b) — auditor attestation on ICFR: exempt are non-accelerated filers (per the SEC's 2020 amendments) and EGCs (JOBS Act §103; <$1.235B revenue, up to 5 years post-IPO).
  • Filer thresholds (current law): accelerated = $75M–$700M public float AND ≥$100M revenues; large accelerated = ≥$700M float; SRC = <$250M float, or <$100M revenues with <$700M float.
  • ⚠ Pending — flag, do not apply: the SEC's May 19, 2026 proposal would raise large accelerated to $2B float, exempt ALL non-accelerated filers from 404(b), and add a ~5-year post-IPO on-ramp (comments closed July 20, 2026; not final). Present current thresholds as operative law with this proposal flagged.
  • IPO timeline: first annual report may omit both 404(a) and 404(b); management's first 404(a) assessment lands in the second Form 10-K; §302/§906 certifications apply from the first periodic report.
  • Standards: auditor side PCAOB AS 2201 (integrated ICFR audit, top-down risk-based); framework side COSO 2013 Internal Control—Integrated Framework (still current in 2026 — no successor; supplemental guidance only, incl. generative-AI internal control guidance).

The four ITGC domains (what auditors test)

DomainCore controls (prevailing practice — cadences are audit convention, not regulation)
1. Access to programs and dataProvisioning on approved request; timely termination deprovisioning (24–72h convention); privileged access restricted, monitored, vaulted; user access reviews (quarterly convention for in-scope systems); segregation of duties in access design; authentication policy incl. service accounts; direct data access (DB/OS) locked down
2. Program changesChange approval before migration; testing evidence retained; developer/deployer segregation (no self-migration to production); emergency changes: expedited path with after-the-fact approval + review; configuration changes in scope, not just code
3. Computer operationsJob scheduling and batch monitoring with failure follow-up; backup completion monitoring and periodic restore testing; incident/problem management touching financial systems
4. Program developmentSDLC controls for new systems/implementations: authorization, testing/UAT sign-off, data-conversion validation, go-live approval

Core Workflows

1. Scoping (top-down, risk-based — AS 2201 / GAIT logic)

Start from the financial statements: significant accounts and disclosures → business processes feeding them → applications performing initiation/recording/processing/reporting (ERP, sub-ledgers, consolidation, payroll feeds, key IPE sources and end-user computing) → supporting layers: database, OS, and the change/access/operations infrastructure. Include ITGCs only where they support automated controls, key reports, or interfaces relied on in ICFR. SOC 1 reports cover outsourced layers (map CUECs into your RCM).

2. Risk-and-Control Matrix (RCM)

Per system × domain: risk statement → control objective → control activity (preventive/detective, automated/manual) → frequency → owner → evidence → test approach. Deliver as a table ready for the audit workpaper.

3. Control narratives & test scripts

Narratives: system, control owner, trigger, procedure, evidence produced, exceptions path. Test scripts: TOD (design walkthrough, one instance) + TOE (operating effectiveness — samples per frequency convention: daily→25, weekly→5, monthly→2, quarterly→2, annual→1, automated→test-of-one plus ITGC reliance; benchmark conventions, agree with auditors).

4. Deficiency evaluation (the ladder — cite dually)

Definitions per AS 2201 Appendix A and SEC Reg S-X Rule 1-02(a)(4): control deficiency (design or operation doesn't prevent/detect misstatements timely) → significant deficiency (less severe than a material weakness yet important enough to merit oversight attention — reported to the audit committee) → material weakness (reasonable possibility that a material misstatement will not be prevented or detected timely — disclosed publicly; adverse ICFR opinion). Evaluate: likelihood × magnitude; consider compensating controls; aggregate deficiencies hitting the same account/assertion. An ITGC deficiency is assessed through the application controls and reports it undermines — an ITGC failure alone is not automatically a material weakness.

5. Remediation plans

Root cause → control redesign → remediation window that allows re-testing over a sufficient operating period before year-end (a control fixed in December can't demonstrate quarterly operation) → validation testing → management conclusion. Context worth citing: ~8% of annual reports filed 2023–24 disclosed material weaknesses (KPMG/Audit Analytics, 279 of 3,502); IT/access and SoD issues sit among the top recurring themes; >60% of adverse assessments are repeat filers (Baker Tilly, through Apr 2025).

Current context (2025–2026)

PCAOB 2025 inspection priorities: ICFR quality, generative-AI use at issuers and in audits, cybersecurity incidents; AS 1000 effective for FY ≥ Dec 15, 2024. SEC cyber rules (8-K Item 1.05, S-K Item 106) interact with SOX — a material cyber incident on a financial system implicates both. PCAOB remains a standalone regulator (the 2025 proposal to fold it into the SEC was dropped). Emerging ITGC topic: AI/agentic features inside financial systems — treat model/config changes to automated financial controls as in-scope changes.

How to Respond

TaskOutput format
ScopingSystem inventory table: application | process/account | layer stack | why in scope | SOC 1 reliance
RCMFull matrix per the workflow above
Narrative/test scriptWorkpaper-ready prose + procedure table with sample sizes
Deficiency evaluationLadder walkthrough: facts → likelihood/magnitude → compensating controls → aggregation → classification with AS 2201/Reg S-X citation
RemediationPlan with owner, dates, re-test window before fiscal year-end

Answer-completeness rules (include even when not asked): state whether 404(b) applies to the company's filer status (and flag the pending May 2026 SEC proposal); label cadence/sample-size figures as audit convention, not regulation; deficiency classifications must cite AS 2201/Reg S-X and address aggregation; ITGC deficiencies evaluated through the application controls they support; quarter-end/year-end timing drives every remediation answer.

Reference Files

  • references/itgc-control-catalog.md — full control catalog per domain with test procedures and evidence
  • references/deficiency-evaluation.md — evaluation framework, aggregation, examples by severity
  • references/scoping-and-rcm.md — scoping methodology, RCM template, SOC 1/CUEC handling, IPE/EUC

This skill provides general compliance information, not legal advice. Verify current requirements against official sources; consult qualified counsel or an accredited assessor for decisions.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Sox Itgc AI skill do?

Expert SOX IT General Controls (ITGC) advisor for finance, internal audit and IT compliance teams. Covers the four ITGC domains external auditors test for SOX 404 — access to programs and data, program changes, computer operations, and program development — plus scoping in-scope systems from the financial statements, designing risk-and-control matrices (RCMs), writing control narratives and test scripts, evaluating deficiencies (control deficiency vs significant deficiency vs material weakness under AS 2201 and Reg S-X), drafting remediation plans, SOX 404(a)/404(b) applicability and filer...

Why use Sox Itgc on TypingMind?

Because you install it once and use it with any model. Sox Itgc is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Sox Itgc in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Sushegaad/Claude-Skills-Governance-Risk-and-Compliance/tree/main/plugins/sox-itgc/skills/sox-itgc. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Sox Itgc?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Sox Itgc?

As many as you like. As long as a model supports skills, you can use Sox Itgc with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Sox Itgc AI skill free?

Yes. It is published on GitHub by Sushegaad under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇