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 agentmods add commands/sophymarine/openregistry/ddgit clone --depth 1 https://github.com/sophymarine/openregistryWrote 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/commands/sophymarine/openregistry/dd)<a href="https://agentmods.dev/commands/sophymarine/openregistry/dd"><img src="https://agentmods.dev/badge/commands/sophymarine/openregistry/dd.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.00517 |
| Opus 5 | $0.00020 | $0.00259 |
| Sonnet 5 | $0.00008 | $0.00103 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
dd 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 4d 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.
What it actually says
Run a full Company Due Diligence workflow on "$1" in jurisdiction $2 using the OpenRegistry MCP tools. Every call below is a live, direct-to-government query. Every response is unmodified — field names, status codes, raw filing bytes preserved exactly as the registry emits them.
Step 1 — Resolve the entity
If "$1" looks like a registry identifier, use it directly as company_id. Otherwise call search_companies({ jurisdiction: "$2", query: "$1" }). Pick the entity whose status is "active" and whose company_name most closely matches. If multiple near-matches, ask me which one before proceeding.
Step 2 — Profile
get_company_profile({ jurisdiction: "$2", company_id: <resolved_id> }). Report: legal name, status, incorporation date, registered address, company type / legal form, SIC/NACE codes, last/next accounts dates, flags (has_charges, has_insolvency_history, in_liquidation, redaction markers).
Step 3 — People (directors + UBO + shareholders)
get_officers({ jurisdiction: "$2", company_id, include_resigned: false })
get_persons_with_significant_control({ jurisdiction: "$2", company_id })
get_shareholders({ jurisdiction: "$2", company_id })
If PSC returns 501 with alternative_url, surface it — UBO is AML-gated in most EU post CJEU C-37/20.
Step 4 — Charges
get_charges({ jurisdiction: "$2", company_id }) — flag outstanding charges with lender + creation date.
Step 5 — Latest accounts
list_filings({ jurisdiction: "$2", company_id, category: "accounts", limit: 1 })
fetch_document({ jurisdiction: "$2", document_id: <latest> })
Extract: turnover, operating profit, net income, total assets, liabilities, equity, cash, employees.
Step 6 — Structured report Entity status · Governance · Ownership · Financial health · Encumbrances · Red flags. Cite every claim with the registry's own identifier so I can click through to the government record for verification.
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.
- 4d ago First seen · 35 lines · 41 tokens per session scan A 37f829bb3b9c
dd is a command published in the GitHub repository sophymarine/openregistry (17 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 517 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
onboard
Customer onboarding with Step 0 verification (HITL consent required).
onboard-interactive
Interactive customer onboarding with Step 0 independent verification (dialog-based, 17 stagegates).
monitor
AML transaction monitoring and suspicious activity reporting.
refresh
Periodic customer review with independent verification.
risk
Risk reassessment with updated due diligence.
screen
Comprehensive sanctions and PEP screening.