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 cyanheads/sanctions-screening-mcp-server --skill sanctions-screening-guidegit clone --depth 1 https://github.com/cyanheads/sanctions-screening-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/cyanheads/sanctions-screening-mcp-server/sanctions-screening-guide)<a href="https://agentmods.dev/skills/cyanheads/sanctions-screening-mcp-server/sanctions-screening-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/sanctions-screening-mcp-server/sanctions-screening-guide/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/cyanheads/sanctions-screening-mcp-server/sanctions-screening-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/sanctions-screening-mcp-server/sanctions-screening-guide.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 | $0.00055 | $0.00765 |
| Opus 5.5 | $0.00022 | $0.00306 |
| Sonnet 5.5 | $0.00011 | $0.00153 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
sanctions-screening-guide 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 5d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gates
Before attributing an ownership graph to a counterparty, compare the candidate GLEIF record with the identity evidence supplied: jurisdiction, registration authority and number, and addresses. A ranked name match alone does not choose the legal entity. If competing records remain plausible, retain the alternatives and ask for identifying evidence; do not merge their ownership chains into one counterparty.
Before treating a search as exhausted, distinguish an empty page from an empty result set and a finished result set from a bounded candidate search. Drain available pages; where the search reports a lower bound, narrow with another identifying name word or a known jurisdiction. If an entity is absent under the default registration-status filter, broaden the status search before concluding it was not found. An unavailable alternate-name index is a coverage gap, not evidence that a trading or former name has no LEI.
Before using a designation to identify a person or organization, compare the published identifiers and corroborating details. Preserve partial or approximate birth dates; do not pair separate dates and birthplaces unless the record pairs them. Descriptive features can corroborate a candidate but are not searchable identifiers. Keep source-specific labels and units: similar feature names do not establish equivalent measurements. A CSL record with unknown entity type remains unknown; neither its list membership nor an end date establishes its current legal effect. Verify export-control restrictions against the named agency list and Federal Register material, using the published provenance when available.
Workflows
Finish an ownership investigation
Drain continuation pages for the same ownership segment before following its boundary records. Assemble nodes by LEI and edges by child LEI, parent LEI, and relationship type; an edge may refer to a node returned on another page. For each omitted branch, start a new trace at the boundary LEI on its specified walk side. Track already-processed LEI/side pairs to avoid cycles and overlapping work. Segment depth restarts at the new root; retain the original segment's node placement rather than treating the new depth as distance from the original counterparty.
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.
- 5d ago First seen · 31 lines · 55 tokens per session scan A e17a09c8128d
sanctions-screening-guide is a skill published in the GitHub repository cyanheads/sanctions-screening-mcp-server (3 stars, last pushed 6d ago), licensed Apache-2.0. It adds 55 tokens to every session and 765 once invoked, about $0.0002 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 2026-11-02.
sanctions-screening-guide compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sanctions-screening-guidecyanheads/sanctions-screening-mcp-server | Skill | 3 | 6d ago | Apache-2.0 | A | 55 | Claude Code |
| regtech-expertpersonamanagmentlayer/pcl | Skill | 44 | 12d ago | Apache-2.0 | A | 73 | Claude Code |
| risk-assessmentvyayasan/kyc-analyst | Skill | 61 | 4mo ago | MIT | A | 81 | Claude Code |
| transaction-monitoringvyayasan/kyc-analyst | Skill | 61 | 4mo ago | MIT | A | 47 | Claude Code |
| onboardingvyayasan/kyc-analyst | Skill | 61 | 4mo ago | MIT | A | 83 | Claude Code |
| screeningvyayasan/kyc-analyst | Skill | 61 | 4mo ago | MIT | A | 44 | Claude Code |
| refreshvyayasan/kyc-analyst | Skill | 61 | 4mo ago | MIT | A | 74 | Claude Code |