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 Nolpak14/getregdata --skill world-bank-contractsgit 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/skills/nolpak14/getregdata/world-bank-contracts)<a href="https://agentmods.dev/skills/nolpak14/getregdata/world-bank-contracts"><img src="https://agentmods.dev/badge/skills/nolpak14/getregdata/world-bank-contracts/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/nolpak14/getregdata/world-bank-contracts"><img src="https://agentmods.dev/badge/skills/nolpak14/getregdata/world-bank-contracts.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 | $0.00185 | $0.02653 |
| Opus 5 | $0.00093 | $0.01326 |
| Sonnet 5 | $0.00037 | $0.00531 |
| Haiku 4.5 | $0.00018 | $0.00265 |
Grade A, and why
world-bank-contracts scanned grade A with 1 finding 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.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl "https://search.worldbank.org/api/contractdata?format=json&qterm=Siemens&rows=20" How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
world-bank-contracts
Free, official World Bank data from the World Bank Search API - the public search layer over the Bank's operations, covering every IBRD/IDA project and the contract awards financed under them. This skill needs no paid actor, no Apify token, and no API key: the Projects and Contract-awards endpoints are fully open. Use it to see which World Bank-financed contracts a company has won (a due-diligence credibility signal) and to mine development-finance suppliers for lead generation, then route to the registry skills to resolve the winning company.
Persona
You are a KYB / due-diligence analyst and lead-gen researcher working the development-finance angle. You search the World Bank data to answer two questions: which World Bank-financed contracts has this company won (a legitimacy and track-record signal), and which suppliers are winning awards under projects in this country or sector (a warm development-finance supplier list). You read contract-award records, not just project records, because the award carries the winning supplier and the money.
What this gives you (for free)
- Contract-award search by supplier - the money endpoint: free-text supplier match plus filters on supplier country and project, each award carrying the winning supplier's name, the awarded amount, the procurement method, and the parent project.
- Project search - World Bank projects filtered by country, sector, and status, each with the project name, commitment amount, board-approval date, and status.
- The join key - awards carry a
projectidthat links each contract back to the project that financed it, so you can go from a supplier's win to the operation behind it. - Multi-supplier detail - contracts split across several suppliers return the per-supplier breakdown, so a shared award is not misread as one company's whole.
Licence: CC BY 4.0 (attribution). Read-only.
Authentication
None - no key, no registration. Both endpoints return clean 200s over plain GET. There is no per-request key or log API; the service is fair-use with per-IP throttling only, so keep request rates reasonable and paginate rather than hammering.
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.
- 9d ago First seen · 142 lines · 185 tokens per session scan A b75b0b7e102c
world-bank-contracts is a skill published in the GitHub repository Nolpak14/getregdata (6 stars, last pushed 1mo ago), licensed MIT. It adds 185 tokens to every session and 2,653 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
apify-x402-agentic-wallet
Discover, pay for, and run any Apify Actor by paying USDC on Base over the x402 protocol with a Coinbase Agentic Wallet (awal) — no Apify account or API key. You buy one small, spend-capped prepaid Apify token, then run as many Actors as the request needs with it. Use when the user wants to use Apify tools without…
regtech-expert
Expert in regulatory technology, compliance automation, KYC/AML, transaction monitoring, risk assessment, and automated reporting. Use when the user mentions compliance, KYC, AML, transaction monitoring, risk assessment, or regulatory reporting, or when the task involves KYC/AML Compliance, KYC/AML Program, Regulatory…
risk-assessment
Deterministic heuristic risk scoring using a four-factor weighted model (Geographic 30%, Customer 35%, Product 25%, Channel 10%) aligned with Basel III, EBA Guidelines, FATF standards, and FinCEN guidance. Bands: LOW (0-20), MEDIUM (21-60), HIGH (61-80), CRITICAL (81-100).
Transaction Monitoring Alert Triage
Use when triaging a transaction-monitoring alert or small alert batch on an existing customer to inventory the alert and the rule that fired, compare the customer's expected-activity baseline against observed activity, structure the escalate / close / request-more-information analysis, and package a…
transaction-monitoring
AML transaction monitoring for ongoing customer relationships. Identifies suspicious patterns including structuring, layering, and unusual activity. Assesses against regulatory thresholds and prepares Suspicious Activity Reports (SARs) with HITL decision gates.
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.