company-check

company-check is a skill for Claude Code from paulieb89/bouch-plugins. It costs 121 tokens per session (3,180 once invoked), scanned A, original, no licence file.

A due-diligence checker for UK companies and directors. Due diligence means checking public records before making a business, lending, hiring, or compliance decision.

In plain words
What is it for?
It checks Companies House, the Gazette insolvency records, HMRC VAT information, and the Disqualified Directors register, then gives a CLEAR, WATCH, or FLAG result using a chosen risk profile.
Why use it?
It brings together several UK records so risks such as insolvency, unpaid VAT, or director bans are easier to review in one assessment.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the foundations plugin — 10 skills, 1 MCP server shipped together

Good fit It checks Companies House, the Gazette insolvency records, HMRC VAT information, and the Disqualified Directors register, then gives a CLEAR, WATCH, or FLAG result using a chosen risk profile.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/paulieb89/bouch-plugins/company-check
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 paulieb89/bouch-plugins --skill company-check
Clone the repo
git clone --depth 1 https://github.com/paulieb89/bouch-plugins

Made for: Claude Code.

Or install foundations, the plugin that ships this one along with the rest of its 10 skills, 1 MCP server.

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 company-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/paulieb89/bouch-plugins/company-check/github.svg)](https://agentmods.dev/skills/paulieb89/bouch-plugins/company-check)
Your own site
<a href="https://agentmods.dev/skills/paulieb89/bouch-plugins/company-check"><img src="https://agentmods.dev/badge/skills/paulieb89/bouch-plugins/company-check/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for company-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/paulieb89/bouch-plugins/company-check"><img src="https://agentmods.dev/badge/skills/paulieb89/bouch-plugins/company-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,180 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.
Origin unknown 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 $0.00121 $0.03180
Opus 5 $0.00060 $0.01590
Sonnet 5 $0.00024 $0.00636
Haiku 4.5 $0.00012 $0.00318

Measured 9d ago against content hash b42399aa828b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

company-check 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 9d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/cross_reference.py, scripts/render_check.py, scripts/risk_score.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/foundations/skills/company-check/SKILL.md · 252 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 9d ago First seen · 252 lines · 121 tokens per session scan A b42399aa828b

Subscribe to this mod's changes

company-check is a skill published in the GitHub repository paulieb89/bouch-plugins (2 stars, last pushed 4mo ago), with no licence file. It adds 121 tokens to every session and 3,180 once invoked, about $0.0006 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

especialista-em-acreditacao-jci

Especialista em Acreditação JCI (Joint Commission International). Use para preparar acreditação JCI: padrões, IPSG (metas de segurança), tracer methodology e cultura de qualidade. Palavras-chave: JCI, Joint Commission, acreditação, padrões, IPSG, tracer, segurança, internacional.

euwebertdefreitas/ai-skills-for-claude-code · 0 tokens

especialista-em-acreditacao-qmentum

Especialista em Acreditação Qmentum International (Accreditation Canada). Use para preparar acreditação Qmentum: padrões, ROPs (práticas organizacionais requeridas), níveis e melhoria contínua. Palavras-chave: Qmentum, Accreditation Canada, acreditação, ROP, padrões, níveis, qualidade, saúde.

euwebertdefreitas/ai-skills-for-claude-code · 0 tokens

especialista-em-base-legal-sus

Especialista em Base Legal do SUS e Ordenamento Normativo. Use para entender a base legal do SUS: Constituição, Lei 8.080/8.142, princípios, pactos e normas operacionais. Palavras-chave: SUS, Lei 8080, 8142, base legal, princípios, normas operacionais, Constituição, saúde pública.

euwebertdefreitas/ai-skills-for-claude-code · 0 tokens

especialista-em-etica-em-saude

Especialista em Ética em Saúde e Responsabilidade Profissional. Use para princípios bioéticos, códigos de ética, consentimento, sigilo e responsabilidade profissional. Palavras-chave: ética, bioética, consentimento, sigilo, código de ética, responsabilidade profissional, autonomia.

euwebertdefreitas/ai-skills-for-claude-code · 65 tokens

especialista-em-gestao-de-saude

Especialista em Gestão de Saúde. Use para gestão de saúde e serviços assistenciais: indicadores de saúde, qualidade assistencial, regulação, saúde populacional e conformidade. Palavras-chave: gestão de saúde, assistencial, indicadores, qualidade, regulação, saúde populacional, LGPD/HIPAA.

euwebertdefreitas/ai-skills-for-claude-code · 73 tokens

especialista-em-governanca-corporativa

Especialista em Governança Corporativa. Use para estrutura de governança: conselho, transparência, prestação de contas, equidade, compliance e gestão de riscos. Palavras-chave: governança corporativa, conselho, transparência, accountability, compliance, riscos, IBGC.

euwebertdefreitas/ai-skills-for-claude-code · 66 tokens