internal-controls-and-audit

internal-controls-and-audit is a skill for Claude Code from cbrock84/headcount. It costs 67 tokens per session (978 once invoked), scanned A, original, MIT.

A guide to controls that keep financial processes accurate and prevent one person from initiating, approving, and hiding a transaction. It also explains how to prepare evidence for an audit, an independent review of financial records and controls.

In plain words
What is it for?
Use it to design approval limits, separate duties, test controls, prepare for an audit, and respond to audit findings.
Why use it?
It exposes weak approvals, unclear responsibilities, missing evidence, and other gaps before an auditor finds them.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the finance plugin — 13 skills shipped together

Good fit Use it to design approval limits, separate duties, test controls, prepare for an audit, and respond to audit findings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cbrock84/headcount/internal-controls-and-audit
About the project

headcount is an organization of independently installable Claude Code plugins, each grouping skills for a department such as finance, security, or demand generation. Claude Code users install the departments they need and invoke their skills for specialized work; the catalogue entries are skills and related agent tooling from that organization.

cbrock84/headcount · 1,320 stars · on GitHub · cbrock84.github.io

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 cbrock84/headcount --skill internal-controls-and-audit
Clone the repo
git clone --depth 1 https://github.com/cbrock84/headcount

Made for: Claude Code.

Or install finance, the plugin that ships this one along with the rest of its 13 skills.

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 internal-controls-and-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/cbrock84/headcount/internal-controls-and-audit.svg)](https://agentmods.dev/skills/cbrock84/headcount/internal-controls-and-audit)
Your own site
<a href="https://agentmods.dev/skills/cbrock84/headcount/internal-controls-and-audit"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/internal-controls-and-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 978 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00067 $0.00978
Opus 5 $0.00034 $0.00489
Sonnet 5 $0.00013 $0.00196
Haiku 4.5 $0.00007 $0.00098

Measured 4d ago against content hash a7827252e24e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

internal-controls-and-audit 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 4d 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.

plugins/finance/skills/internal-controls-and-audit/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Internal controls and audit

Controls exist because a single person who can initiate, approve and record a transaction can also conceal one. Everything else is elaboration on that.

This structures control design and audit readiness. Statutory audit requirements, and regimes such as SOX where they apply, are matters for your auditors and qualified advisers.

The five components an auditor will assess

Segregation of duties is one control activity inside a much larger structure, and a team that has only built control activities will still be told its control environment is weak. Auditors assess five components, and a deficiency in any one undermines the others:

  • Control environment — integrity and ethical values, oversight by whoever plays the board role, a structure with defined responsibility and authority, competence for the work assigned, and accountability actually enforced. This is the component small organizations skip and the one that determines whether every other control holds.
  • Risk assessment — objectives defined clearly enough to have risks, risks identified and responded to, fraud risk assessed explicitly rather than assumed away, and change identified as it happens. New systems, new people, and rapid growth all invalidate control designs quietly.
  • Control activities — the controls themselves, including those over the information systems the records depend on, and evidence that they were performed rather than merely designed.
  • Information and communication — quality information available to the people who need it, communicated internally to those who act on it and externally to those who rely on it. A control nobody was told about does not operate.
  • Monitoring — someone checks that controls still work, and identified deficiencies get remediated on a timetable rather than carried forward year after year.

Two of these are consistently the weak ones in organizations under a few hundred people: fraud risk is never assessed on the reasoning that everyone is trusted, and monitoring never happens because the people who would monitor are the people who perform the controls.

Read the full file on GitHub · 88 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. 4d ago First seen · 88 lines · 67 tokens per session scan A a7827252e24e

Subscribe to this mod's changes

internal-controls-and-audit is a skill published in the GitHub repository cbrock84/headcount (1,320 stars, last pushed 5d ago), licensed MIT. It adds 67 tokens to every session and 978 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 2026-09-03.

Related

Other skills, from other repositories

bank-partnership

Assess partner bank compliance requirements — OCC/FDIC expectations, regulatory pass-through.

bromso/metapowers · 15 tokens

mortgage-compliance

You are operating under strict mortgage regulatory compliance rules. Every response you generate that touches on lending, rates, fees, qualifications, or loan terms MUST comply with the following regulations. Violations of these rules expose Lendtrain powered by Atlantic Home Mortgage and its borrowers to legal and…

lendtrain/mortgage · 0 tokens

invest

First-time fork users: run the invest-setup skill first to initialize. The main flow lives in this skill (the AI agent uses the CLI/MCP to view the portfolio / run the committee / replay decision history). The Web GUI has been retired (2026-07) — every capability is exposed via CLI subcommands / MCP tools. The backend…

longsizhuo/openInvest · 261 tokens

antinet-four-color-cards

A document-analysis skill that organises findings into four card types: facts, explanations, risks, and actions. It is intended for financial reports and legal documents.

anbeime/skill · 97 tokens

stockbit-auth

Log in to Stockbit and capture the session for this server — opens the browser login flow and verifies the token was stored. Use when the user asks to log in or re-authenticate to Stockbit, or after a status check reports the session expired, HTTP 401, or logged out.

INo-xious/stockbit-mcp · 63 tokens

phase-preview

Preview a signed-off design one release phase at a time — cut it down into a series of phase screens, each showing only what exists by that phase with the layout untouched, then put them on a scrubber you drag to watch the screen fill in release by release. Use when the user wants a Phase 1 / MVP version of an…

Cavalry-Collective/visual-stack · 107 tokens