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.
git clone --depth 1 https://github.com/vyayasan/kyc-analystWrote 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/vyayasan/kyc-analyst/refresh)<a href="https://agentmods.dev/commands/vyayasan/kyc-analyst/refresh"><img src="https://agentmods.dev/badge/commands/vyayasan/kyc-analyst/refresh/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/commands/vyayasan/kyc-analyst/refresh"><img src="https://agentmods.dev/badge/commands/vyayasan/kyc-analyst/refresh.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 | $0.00006 | $0.00307 |
| Opus 5.5 | $0.00002 | $0.00123 |
| Sonnet 5.5 | $0.00001 | $0.00061 |
| Haiku 4.5 | $0.00001 | $0.00031 |
Grade A, and why
refresh 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.
What it actually says
Refresh
Periodic customer review with independent verification searches to ensure ongoing due diligence compliance and identify any changes in customer risk profile or undisclosed relationships.
Usage
/kyc:refresh <customer name>
Process
- Initiate - Verify last refresh date, confirm trigger (time-based, risk-based, event-based)
- Re-run Step 0 - Execute all 5 independent verification searches
- Compare - Identify changes since last review (new directorships, adverse media, PEP status)
- Assess - Classify changes as material or non-material
- Decide - Update risk rating or escalate if material changes detected
- Document - Generate refresh report, update case file, schedule next refresh
Refresh Intervals
- HIGH risk: Annual (12 months)
- MEDIUM risk: 24 months (UK/EU), 6 months (MENA)
- LOW risk: 36 months (UK/EU), 12 months (MENA/US)
HITL Checkpoints
- Analyst confirms trigger and timing before proceeding
- Manager approves search completeness
- Analyst classifies material vs non-material changes
- Manager reviews risk reassessment
- MLRO notified for immediate escalation cases
Version: 1.0.0 Author: Vyayasan
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 First seen · 43 lines · 6 tokens per session scan A 5b35101aacb6
refresh is a command published in the GitHub repository vyayasan/kyc-analyst (58 stars, last pushed 3mo ago), licensed MIT. It adds 6 tokens to every session and 307 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
ai-marked-asset-anchored
Validate a C2PA manifest and AI Act Art. 50 marking in the page, replay the content-credential chain remotely, and anchor the disclosure manifest to Bitcoin.
air-gapped-helm-handover
Run a CECL workflow on a loopback-only Helm daemon, hit the consent-tier boundary at evidence export, and cross-check the kernel against the public worker.
same-law-three-doorways
Run one tool in the page, on the hosted MCP worker, and against its signed receipt, then compare the executionhash character by character.
zero-egress-emir-proof
Run four EMIR Refit validators inside the browser tab, pack and anchor only the hashes, and hand a supervisor the re-verification recipe.
filings
Scan recent filings on a company and surface material events (director changes, new charges, capital events, insolvency markers). Works on GB / IE / CA / IS / FI / IM / LI / MX / KR.
signed-policy-agentic-commerce
Run an agentic commerce chain under a signed Work Mandate, trip the escalation gate on purpose, and replay the gates on the ledger.