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 darksider4all/leadgen-mcp --skill leadgen-romaniagit clone --depth 1 https://github.com/darksider4all/leadgen-mcpWrote 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/darksider4all/leadgen-mcp/leadgen-romania)<a href="https://agentmods.dev/skills/darksider4all/leadgen-mcp/leadgen-romania"><img src="https://agentmods.dev/badge/skills/darksider4all/leadgen-mcp/leadgen-romania/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/darksider4all/leadgen-mcp/leadgen-romania"><img src="https://agentmods.dev/badge/skills/darksider4all/leadgen-mcp/leadgen-romania.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 | $0.00140 | $0.02145 |
| Opus 5.5 | $0.00056 | $0.00858 |
| Sonnet 5.5 | $0.00028 | $0.00429 |
| Haiku 4.5 | $0.00014 | $0.00215 |
Grade A, and why
leadgen-romania 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 14d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Leadgen: Romanian company data
Leadgen serves Romania's official business registry to agents: every firm registered with ONRC (4.2M, 2.2M of them struck off), ANAF's fiscal layer (VAT, e-Factura, fiscal inactivity, phone) and the Ministry of Finance filings 2008–2025. This skill says which tool to call for which job and how to present what comes back.
Connect
The tools come from a remote MCP server. If no lookup_business tool is available, help the
user add it:
- Endpoint (Streamable HTTP, no OAuth):
https://leadgen-mcp.adrianhomelab.com/mcp - Claude Code:
claude mcp add --transport http leadgen https://leadgen-mcp.adrianhomelab.com/mcp --header "Authorization: Bearer <key>" - claude.ai / Claude Desktop: Settings → Connectors → Add custom connector → the URL above.
- Without a key: 30 lookups a day on this MCP endpoint (5 on the REST API). With a free key
(email only, no card) from https://leadgen.adrianhomelab.com/start: 50 a day. Paid plans: Pro €9/month (500/day),
Business €29/month (5,000/day). Send the key as
Authorization: Bearer <key>orX-API-Key.
Never ask the user to paste their key into the chat. It belongs in the connector configuration.
Pick the tool
| The user wants | Call |
|---|---|
| One firm by name or CUI | lookup_business (start here for any named firm) |
| Many firms by CUI (up to 100) | lookup_companies |
| Their own list (names, counties, domains, CUIs) matched to the registry | match_companies (up to 500 rows) |
| "Firms that do X in county Y" | lookup_by_category |
| The firm behind a website | find_company_by_domain |
| Firms a person runs | lookup_director |
| Emails/phones from a firm's site | enrich_company (registry + site in one call) or extract_contacts |
| Revenue, profit, headcount over the years | lookup_financials |
| Trend, margins, health score, peer percentile | lookup_financial_ratios |
| DNS, WHOIS, SPF/DMARC of a domain | lookup_domain |
| Alerts on a firm or on new firms in a niche | watch_company, watch_caen, then poll_watchlist; unwatch to stop |
| How many lookups are left today | get_usage (free, not counted) |
| Something missing or wrong in the data | report_issue (free, not counted) |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 14d ago Changed 7f5502b57499
- 22d ago First seen · 124 lines · 140 tokens per session scan A 70edfb7c5ad7
leadgen-romania is a skill published in the GitHub repository darksider4all/leadgen-mcp (0 stars, last pushed 13d ago), licensed MIT. It adds 140 tokens to every session and 2,145 once invoked, about $0.0006 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 2026-10-18.
leadgen-romania compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| leadgen-romaniadarksider4all/leadgen-mcp | Skill | 0 | 13d ago | MIT | A | 140 | Claude Code, Codex |
| opik-diagnosecomet-ml/opik-mcp | Skill | 226 | 3d ago | Apache-2.0 | A | 187 | Claude Code |
| qmclaw-workbenchxi-zhao/OpenQuantum | Skill | 72 | yesterday | MIT | A | 124 | Codex |
| cortex-explore-memorycdeust/Cortex | Skill | 76 | 2d ago | MIT | A | 91 | Claude Code |
| quantum-groverxi-zhao/OpenQuantum | Skill | 72 | yesterday | MIT | A | 62 | Claude Code, Codex |
| quantum-algorithmsxi-zhao/OpenQuantum | Skill | 72 | yesterday | MIT | A | 34 | Claude Code, Codex |
| alicebob-cat-circuitsxi-zhao/OpenQuantum | Skill | 72 | yesterday | MIT | A | 51 | Claude Code, Codex |