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.
npx skills add nordio-ai/brreg-mcp-server --skill brreggit clone --depth 1 https://github.com/nordio-ai/brreg-mcp-serverWrote 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.
[](https://agentmods.dev/skills/nordio-ai/brreg-mcp-server/brreg)<a href="https://agentmods.dev/skills/nordio-ai/brreg-mcp-server/brreg"><img src="https://agentmods.dev/badge/skills/nordio-ai/brreg-mcp-server/brreg/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.
<a href="https://agentmods.dev/skills/nordio-ai/brreg-mcp-server/brreg"><img src="https://agentmods.dev/badge/skills/nordio-ai/brreg-mcp-server/brreg.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.01798 |
| Opus 5 | $0.00026 | $0.00899 |
| Sonnet 5 | $0.00010 | $0.00360 |
| Haiku 4.5 | $0.00005 | $0.00180 |
Grade A, and why
brreg 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brønnøysundregistrene — reading the register without being lied to
The API is open, keyless and unauthenticated. Fetching is not the problem. The problem is that every trap below returns a plausible number with HTTP 200 instead of an error, so a wrong answer looks exactly like a right one.
This skill is for the agent driving brreg-mcp-server (or its CLI). The tools carry these guards and
fire them automatically — this file is why they exist and what to do when one speaks.
Surfaces
| You are | Use |
|---|---|
| Claude Desktop | the .mcpb — four tools, guards always on |
| Claude Code / a script | brreg <verb> — the same handlers over argv |
brreg get_units --orgnrs 923609016
brreg search_units --nace 96.210 --kommune 0301 --employees-min 1 --employees-max 4
brreg get_financials --orgnrs 918035443
brreg reference # field glossary with statutory sources, retired NACE, role codes
brreg self-test --mock # proves the install works offline
Always parse the JSON. stdout is one object per invocation (elapsed_sec included); diagnostics go
to stderr; usage errors exit 2. Everything reproduces offline with --mock — the mock swaps the socket,
not the code path, and its dataset is the trap set.
The rule that matters most
Never conclude from a zero, an absence, or a null without reading
hintsfirst.
The tools return hints precisely when the register is being quiet in a misleading way. A total: 0
with a retired_nace hint means "the code moved", not "no such businesses". If you report the zero,
you have reported the trap's output as a finding.
What each silence actually means
| You see | It does NOT mean | It means |
|---|---|---|
total: 0 |
"none exist" | possibly a retired NACE code — SN2007 expired 2025-01-01, brreg serves SN2025. Read hints. |
driftsinntekter: null + filed_no_revenue_line |
zero revenue | a holding company — accounts filed, income sits in subsidiaries as financial income. |
status: not_applicable |
dormant / a red flag | an ENK (sole proprietorship). They never file. ~74% of the register. |
antallAnsatte: null |
headcount unknown | withheld — brreg never shows a value below 5 but holds the number. |
gone (410) |
not found | removed on legal grounds — brreg asks that caches drop it too. |
deleted + slettedato |
an error | dissolved — arrives as HTTP 200 with a reduced payload, straight into your success branch. |
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.
- 10d ago First seen · 123 lines · 51 tokens per session scan A db38b1042e5a
brreg is a skill published in the GitHub repository nordio-ai/brreg-mcp-server (0 stars, last pushed 17d ago), licensed MIT. It adds 51 tokens to every session and 1,798 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…