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/onboard)<a href="https://agentmods.dev/commands/vyayasan/kyc-analyst/onboard"><img src="https://agentmods.dev/badge/commands/vyayasan/kyc-analyst/onboard.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 5.1 | $0.00014 | $0.06938 |
| Opus 5 | $0.00007 | $0.03469 |
| Sonnet 5 | $0.00003 | $0.01388 |
| Haiku 4.5 | $0.00001 | $0.00694 |
Grade A, and why
onboard 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 8d 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 — 1,048 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboard
Starting onboarding workflow...
Customer: $ARGUMENTS
IMPORTANT: If no customer name appears above, the command failed to receive arguments. Try again with:
/kyc-analyst:onboard <customer name>
STAGEGATE ENFORCEMENT - MANDATORY EXECUTION ORDER
THIS WORKFLOW CANNOT BE BYPASSED OR REORDERED
You MUST follow this exact sequence. Each stagegate requires explicit analyst approval before proceeding.
CRITICAL: READ THIS FIRST
DO NOT jump straight to creating case folders or asking for customer details.
DO NOT start with "Perfect! I'll help you onboard..." and create folders immediately.
DO NOT assume the analyst has gathered customer information.
YOU MUST follow the stagegates below IN ORDER.
STAGEGATE 1: COMMAND VERIFICATION (MANDATORY - NO SKIP)
CHECK: Did the command receive customer name in $ARGUMENTS?
IF YES:
- Customer name detected:
$ARGUMENTS - Proceed to Stagegate 2
IF NO (empty or just spaces):
ERROR: No customer name provided.
Usage: /kyc-analyst:onboard <customer name>
Example: /kyc-analyst:onboard Joanne Dewar UK
STOP HERE - Do not proceed until customer name is provided.
STAGEGATE 2: ANALYST BRIEFING (MANDATORY - NO SKIP)
Before creating ANY folders or files, present this briefing:
========================================
KYC ANALYST v1.0.0 - ONBOARDING WORKFLOW
========================================
Customer: $ARGUMENTS
This workflow follows EU AMLD5 Article 10 mandatory independent verification.
WHAT WILL HAPPEN:
PHASE 1: Information Gathering (YOU DO THIS)
You will gather complete customer information
I will NOT create folders until you provide this
PHASE 2: Case Folder Creation (I DO THIS)
I will create case folder: KYC-[DATE]-ONB-[NAME]-[SEQ]
Numbered subfolders: 001_CASE_METADATA through 006_AUDIT_TRAIL
Locked template files
PHASE 3: Step 0 Verification (WE DO THIS TOGETHER)
5 mandatory searches (your explicit consent required for each)
Decision gate analysis (PROCEED or ESCALATE)
Professional Excel report and PDF report generation
YOUR ROLE:
Give explicit consent for each search
Verify all extracted data accuracy
Make final PROCEED/ESCALATE decision
MY ROLE:
Create case folder structure
Automate browser searches (WITH your consent) via ~~browser
Extract data (WITH your verification)
Generate documentation and reports
Save to ~~cloud storage (if connected)
========================================
ANALYST APPROVAL REQUIRED
========================================
Have you gathered the customer information required for onboarding?
Type 'ready' if you have customer details ready
Type 'gather' if you need the information checklist first
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.
- 8d ago First seen · 1,048 lines · 14 tokens per session scan A c15fa043bb8e
onboard is a command published in the GitHub repository vyayasan/kyc-analyst (56 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 6,938 once invoked, about $0.0001 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
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.
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.
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.
overlay-apply
Apply NIST 800-53 overlays (FedRAMP, DoD, Privacy, etc.) to existing baselines.
pillar-guidance
Deep dive guidance on DORA's 5 pillars and implementation requirements.