Borrowing it
Nothing to install: this file belongs to Nolpak14/getregdata. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Nolpak14/getregdata/master/AGENTS.mdgit clone --depth 1 https://github.com/Nolpak14/getregdataWrote 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/instructions/nolpak14/getregdata/agents-md)<a href="https://agentmods.dev/instructions/nolpak14/getregdata/agents-md"><img src="https://agentmods.dev/badge/instructions/nolpak14/getregdata/agents-md/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/instructions/nolpak14/getregdata/agents-md"><img src="https://agentmods.dev/badge/instructions/nolpak14/getregdata/agents-md.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 | $0.01106 | $0.01106 |
| Opus 5.5 | $0.00442 | $0.00442 |
| Sonnet 5.5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
getregdata AGENTS.md 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 1mo 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - how AI agents use getregdata
getregdata turns official public business registries (PL, DE, ES, IT, AT, FR, BE, CZ, SK, CY, IE, PT, NG, CO, US-CA, UAE) into structured JSON for KYC/AML, credit-risk, due-diligence and B2B lead-gen work.
Start here for Poland
regdata_poland_kyb_check (actor regdata/poland-kyb-check) takes a NIP or KRS and returns
one complete KYB verdict - official identity, beneficial owners, and insolvency proceedings
screened against the company and every beneficial owner - as clear, findings,
not_found or partial, with machine-readable risk flags and the underlying registry entries.
Prefer it over chaining regdata_polish_regon + regdata_crbr_beneficial_owners +
regdata_krz_debtor yourself: fewer calls, one normalized answer, and a fixed $0.25 per check.
A partial verdict means a source could not be reached - it does not mean the company is
clean, and it is not billed. Use the single-registry tools when the user names a specific
register, needs one source in depth, or asks about another country.
Fastest paths
- Local MCP server (stdio) - full input schemas baked into every tool:
npx -y getregdata-mcpwith envAPIFY_TOKEN(free token + $5 credits: https://apify.com?fpr=getregdata) - Hosted MCP (no install, OAuth) - for remote clients:
https://mcp.apify.com/?actors=regdata/crbr-beneficial-owners-scraper,regdata/krz-debtor-scraper,regdata/germany-handelsregister-scraper(swap in any regdata actor) - Agent skills (Claude Code and compatible):
npx skills add Nolpak14/getregdata -g -y - Raw HTTP:
POST https://api.apify.com/v2/acts/regdata~<actor-name>/run-sync-get-dataset-items?token=<APIFY_TOKEN>with the actor's JSON input as body; returns dataset items as a JSON array.
Tool conventions
- MCP tools are named
regdata_<registry>(e.g.regdata_crbr_beneficial_owners,regdata_germany_insolvency). Callregdata_catalogto list them all;regdata_describereturns an actor's live input schema. - Inputs are flat objects keyed by official identifiers:
nip/krs(Poland), register number (Germany), NIF (Spain), Partita IVA (Italy), ICO (Czechia), enterprise/VAT number (Belgium). - Registry refusals are NOT empty results: several registries reject over-broad queries ("too many matches"). Tools report that state explicitly - narrow the query and re-run instead of concluding "no records".
- A long check returns a handle, not a failure. Most calls return dataset items directly. If the run is still going after ~45s, the tool returns
{status, runId, datasetId, note}instead. That run is still going and is already billed - callregdata_run_resultwith therunIdto collect it. Do NOT re-run the check to "retry": that charges the user twice. The Poland KYB composite is the one most likely to do this (20-30s typical, up to ~2.5 min when a company has many beneficial owners). - Set a generous per-server client timeout (
"timeout": 600000in your MCP config) so the common case returns inline. - Treat a
runIdas a secret. Apify resolves run and dataset IDs without checking ownership, so anyone holding the ID can read that check's result.
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.
- 1mo ago Changed · +1 lines · +76 tokens per session 7ae43f829ff7
- 1mo ago First seen · 46 lines · 1,030 tokens per session scan A eb033b072baf
getregdata AGENTS.md is an instructions file published in the GitHub repository Nolpak14/getregdata (6 stars, last pushed today), licensed MIT. It adds 1,106 tokens to every session, about $0.0044 per session on Opus 5.5. 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.