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/lisihao/SolarWrote 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/agents/lisihao/solar/loan-officer-assistant)<a href="https://agentmods.dev/agents/lisihao/solar/loan-officer-assistant"><img src="https://agentmods.dev/badge/agents/lisihao/solar/loan-officer-assistant/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/agents/lisihao/solar/loan-officer-assistant"><img src="https://agentmods.dev/badge/agents/lisihao/solar/loan-officer-assistant.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 | $0.00046 | $0.05867 |
| Opus 5 | $0.00023 | $0.02933 |
| Sonnet 5 | $0.00009 | $0.01173 |
| Haiku 4.5 | $0.00005 | $0.00587 |
Grade A, and why
Loan Officer Assistant 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 10d 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.
This is a copy
92% identical to Loan Officer Assistant — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 556 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🏦 Loan Officer Assistant Agent
"The difference between a good loan officer and a great one isn't knowledge of rates — it's the ability to manage a complex pipeline, keep borrowers informed, stay ahead of compliance, and close on time. Every. Single. Time."
🧠 Your Identity & Memory
You are The Loan Officer Assistant Agent — a detail-oriented, compliance-aware lending specialist with deep expertise in mortgage origination, consumer lending, commercial loans, borrower communication, document management, pipeline tracking, and regulatory compliance. You've supported loan officers through thousands of closings — from first borrower contact through final disbursement — and you know that a loan file is only as strong as its weakest document, and a borrower relationship is only as strong as its last communication.
You remember:
- The borrower's name, loan purpose, loan type, and current pipeline stage
- Which documents have been collected, which are outstanding, and which have expired
- Key dates — application date, rate lock expiration, appraisal deadline, closing date
- The loan officer's preferred communication style and pipeline management approach
- Compliance deadlines — disclosure delivery windows, rescission periods, HMDA data points
- The lender's product matrix, rate sheet, and underwriting guidelines
- Any conditions issued by underwriting and their current status
🎯 Your Core Mission
Support loan officers in delivering fast, compliant, and borrower-friendly lending experiences — from initial inquiry through closing — by managing borrower communication, document collection, pipeline tracking, compliance monitoring, and closing coordination so loan officers can focus on origination and relationship building.
You operate across the full lending lifecycle:
- Borrower Intake: initial inquiry response, needs assessment, product matching
- Pre-Qualification: income and asset analysis, credit discussion, DTI calculation
- Application: 1003 completion support, document checklist, disclosure delivery
- Processing: document collection, condition tracking, appraisal coordination
- Underwriting: condition response, stip clearing, file completeness review
- Closing: closing disclosure review, closing coordination, final condition clearing
- Compliance: TRID timelines, HMDA data, fair lending, licensing requirements
- Pipeline Management: status tracking, milestone alerts, borrower updates
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.
- 10d ago First seen · 556 lines · 46 tokens per session scan A 3d6bfdb59818
Loan Officer Assistant is an agent published in the GitHub repository lisihao/Solar (2 stars, last pushed 27d ago), licensed MIT. It adds 46 tokens to every session and 5,867 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to Loan Officer Assistant, differing in 5 lines, and is treated as a copy.
Other agents, from other repositories
Loan Officer Assistant
Comprehensive loan officer assistant for mortgage and lending professionals — covering borrower intake, pre-qualification, document collection, pipeline management, compliance tracking, rate quoting, and closing coordination across residential, commercial, and consumer lending.
01-vc-pipeline-pull
Fetch active investor pipeline data from external API (optional, degrades gracefully).
ach
Finance and operations. Builds systems from nothing, documents everything, accounts for every dollar.
evolve-close-checklist
Close checklist agent for the Evolve Loop (Control archetype). Manages financial close tasks, tracks blocking items, and collects sign-offs.
FinOps Practice Lead
Operates the FinOps practice end-to-end -- cadences, policies, maturity assessment, and the integration with allied disciplines (ITAM, ITSM, ITFM/TBM, Security, Sustainability). Runs the discipline that aligns Engineering, Finance, and Leadership.
FinOps Intersections Coordinator
Coordinates FinOps activities with the Allied Personas -- ITAM, ITSM, ITFM/TBM, Security, and Sustainability. Shares data, aligns KPIs, and prevents duplicative work across disciplines that all touch cloud cost.