controls

controls is a skill for Claude Code, Codex from bromso/metapowers. It costs 8 tokens per session (486 once invoked), scanned A, original, MIT.

A process for designing checks that prevent or detect errors and fraud in business operations. Internal controls are rules and review steps that protect assets and improve record accuracy.

In plain words
What is it for?
Designing controls for cash, inventory, payroll, financial reporting, physical assets, user access, documentation, and audit reviews.
Why use it?
It exposes risky processes and assigns safeguards such as approvals, separated duties, restricted access, reconciliations, and reviews.

Skill for Claude CodeCodex

Part of the accounting plugin — 13 skills shipped together

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/bromso/metapowers/controls
Any agent
npx skills add bromso/metapowers --skill controls
Clone the repo
git clone --depth 1 https://github.com/bromso/metapowers

Made for: Claude Code, Codex.

Or install accounting, 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 controls

README.md
[![agentmods](https://agentmods.dev/badge/skills/bromso/metapowers/controls.svg)](https://agentmods.dev/skills/bromso/metapowers/controls)
Your own site
<a href="https://agentmods.dev/skills/bromso/metapowers/controls"><img src="https://agentmods.dev/badge/skills/bromso/metapowers/controls.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 486 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 $0.00008 $0.00486
Opus 5 $0.00004 $0.00243
Sonnet 5 $0.00002 $0.00097
Haiku 4.5 $0.00001 $0.00049

Measured 3d ago against content hash f1b730e13011, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

controls 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.

plugins/accounting/skills/controls/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Controls

Design internal controls for "$ARGUMENTS". Establish preventive and detective controls to safeguard assets, ensure accuracy, and maintain compliance.

Prerequisites

None — utility skill, run anytime. Most effective after Phase 1 (analyze) to understand the entity's operations and risk areas.

Process

  1. Assess control environment:

    • What processes handle cash, inventory, payroll, and financial reporting?
    • Where are the highest-risk areas for errors or fraud?
    • What controls currently exist (if any)?
    • What is the entity's size and complexity?
  2. Design preventive controls:

    • Segregation of duties — separate authorization, custody, and recording
    • Authorization controls — approval limits and signing authority
    • Physical controls — locks, safes, restricted access, inventory counts
    • IT controls — access permissions, password policies, audit logs
    • Documentation — standardized forms, sequential numbering, required fields
  3. Design detective controls:

    • Reconciliations — bank reconciliation, intercompany, sub-ledger to GL
    • Reviews — management review of reports, exception reports
    • Audits — internal audit schedule, surprise counts
    • Variance analysis — budget vs. actual monitoring
  4. Map controls to risks:

    • For each identified risk, assign one or more controls
    • Classify controls by type (preventive/detective) and frequency (daily/weekly/monthly/annual)
    • Identify any gaps where risks lack adequate controls
  5. Write the artifact to .metapowers/accounting/$ARGUMENTS/controls.md with sections:

    • Control Environment Assessment — current state and risk areas
    • Control Matrix — risks mapped to controls with type, frequency, and owner
    • Implementation Plan — priority order for implementing new or improved controls
    • Monitoring — how to verify controls are operating effectively

Output

The controls design written to .metapowers/accounting/$ARGUMENTS/controls.md. Present a summary highlighting:

  • Number of controls designed by type
  • Highest-risk areas and their mitigating controls
  • Implementation priorities

Read the full file on GitHub · 51 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 · 51 lines · 8 tokens per session scan A f1b730e13011

Subscribe to this mod's changes

controls is a skill published in the GitHub repository bromso/metapowers (1 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 486 once invoked, about $0.0000 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.

Related

Other skills, from other repositories

code-quality

Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture violations. Do NOT use for functional verification (run verification FIRST, then code-quality).

fusengine/agents · 41 tokens

researchers-legal

Researches court documents, indictments, plea agreements, and sentencing records. Use when the album subject involves legal proceedings or criminal cases.

bitwize-music-studio/claude-ai-music-skills · 32 tokens

ai-ml-governance

Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory…

cbrock84/headcount · 83 tokens

prior-art-search

Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments using BigQuery and CPC classification.

RobThePCGuy/Claude-Patent-Creator · 26 tokens

refactor

Refactors code toward project-guideline compliance and testability (so /optimus:unit-test can safely increase coverage) across four analysis lenses, fanned out to parallel agents when the scope warrants it. Supports "testability" or "guidelines" focus plus flexible scoping. Read-only until the user approves the plan…

oprogramadorreal/optimus-claude · 99 tokens

building

Implementation skill for writing production code with TDD. Covers the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns. Loaded by component-builder and bug-investigator.

romiluz13/cc10x · 53 tokens