document-verification

document-verification is a skill for Claude Code, Codex from microsoft/aibast-agents-library. It costs 18 tokens per session (207 once invoked), scanned A, original, MIT.

A checklist builder for checking whether fictional loan documents are ready for review. It organizes requirements for borrowers, properties, assets, identity, and loan programs.

In plain words
What is it for?
Use it to prepare document-readiness checklists for mortgage applications before an authorized person verifies them.
Why use it?
It turns a file review into a product-specific checklist and helps expose missing or incomplete documents.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one.

Good fit Use it to prepare document-readiness checklists for mortgage applications before an authorized person verifies them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/microsoft/aibast-agents-library/aibast_document-verification_03
About the project

AIBAST Agents Library is a collection of industry-focused AI agent templates accompanied by a local server that connects agents to GitHub Copilot for language-model inference. It helps developers create and run tool-using agents and isolated project environments, with an optional cloud-backed path for persistent memory. The catalogue entries provide the repository's agents, skills, commands, hooks, and instructions.

microsoft/aibast-agents-library · 7 stars · on GitHub

Install

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.

Any agent
npx skills add microsoft/aibast-agents-library --skill aibast_document-verification_03
Clone the repo
git clone --depth 1 https://github.com/microsoft/aibast-agents-library

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for document-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/microsoft/aibast-agents-library/aibast_document-verification_03.svg)](https://agentmods.dev/skills/microsoft/aibast-agents-library/aibast_document-verification_03)
Your own site
<a href="https://agentmods.dev/skills/microsoft/aibast-agents-library/aibast_document-verification_03"><img src="https://agentmods.dev/badge/skills/microsoft/aibast-agents-library/aibast_document-verification_03.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 207 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.00207
Opus 5 $0.00009 $0.00103
Sonnet 5 $0.00004 $0.00041
Haiku 4.5 $0.00002 $0.00021

Measured 4d ago against content hash e74d48f34086, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

document-verification 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.

solutions/loan-origination-assistant/manual/skills/aibast_document-verification_03/SKILL.md · 26 lines

What it actually says

Document readiness

Builds product-specific borrower, asset, property, identity, and program checklists.

Procedure

  1. Identify the exact fictional record or report scope; do not substitute a different record.
  2. Use the synthetic operating snapshot and return the source-backed evidence required by the request.
  3. Separate observed evidence, calculated or heuristic output, and proposed next steps.
  4. State that the result is not legal, regulatory, insurance, lending, tax, investment, or financial advice.
  5. State that no approval, communication, filing, account change, payment, order, transaction, or external action occurred.
  6. Name the authorized human review required before action.

Locked example

Persona: Processor

Prompt: Build the VA document checklist for Sandra so I can verify the file.

Expected synthetic evidence: LA-2025-4004, Certificate of Eligibility.

Changes

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.

  1. 4d ago First seen · 26 lines · 18 tokens per session scan A e74d48f34086

Subscribe to this mod's changes

document-verification is a skill published in the GitHub repository microsoft/aibast-agents-library (7 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 207 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 2026-09-03.