prior-authorization-document-review

prior-authorization-document-review is a skill for Claude Code, Codex from alex-alecu/garden-desk. It costs 39 tokens per session (272 once invoked), scanned A, original, Apache-2.0.

A checklist-based review of a prior-authorization packet, which is paperwork sent to an insurer before certain healthcare services or items are provided. It compares the supplied documents with the supplied requirements without making clinical or insurance decisions.

In plain words
What is it for?
Use it to inventory a packet, link each supplied requirement to exact evidence, and produce a table of findings for qualified administrative or clinical review before submission.
Why use it?
It shows which required facts or documents are missing, conflicting, or need human review. It also prevents the review from being mistaken for a medical-necessity, coverage, approval, or denial decision.

Skill for Claude CodeCodex

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

Good fit Use it to inventory a packet, link each supplied requirement to exact evidence, and produce a table of findings for qualified administrative or clinical review before submission.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alex-alecu/garden-desk/prior-authorization-document-review
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 alex-alecu/garden-desk --skill prior-authorization-document-review
Clone the repo
git clone --depth 1 https://github.com/alex-alecu/garden-desk

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 prior-authorization-document-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/alex-alecu/garden-desk/prior-authorization-document-review/github.svg)](https://agentmods.dev/skills/alex-alecu/garden-desk/prior-authorization-document-review)
Your own site
<a href="https://agentmods.dev/skills/alex-alecu/garden-desk/prior-authorization-document-review"><img src="https://agentmods.dev/badge/skills/alex-alecu/garden-desk/prior-authorization-document-review/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.

agentmods 80×15 button for prior-authorization-document-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/alex-alecu/garden-desk/prior-authorization-document-review"><img src="https://agentmods.dev/badge/skills/alex-alecu/garden-desk/prior-authorization-document-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 272 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 $0.00039 $0.00272
Opus 5 $0.00019 $0.00136
Sonnet 5 $0.00008 $0.00054
Haiku 4.5 $0.00004 $0.00027

Measured 11d ago against content hash ca2e198d80ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

prior-authorization-document-review 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 11d 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.

prompts/skills/prior-authorization-document-review/SKILL.md · 13 lines

What it actually says

Use only the supplied packet, payer policy, checklist, and user criteria. If no policy or checklist is supplied, inventory the packet and ask for the controlling requirements. Do not use model memory as a payer rule.

Map each supplied requirement to exact packet evidence. Use only documented, not documented, conflicting, not applicable, and human review required. Do not use met, failed, approve, or deny.

Record request identifier, patient identifier needed to distinguish the packet, provider, payer, requested item or service as written, dates, attached document types, supplied criterion, evidence location, and state. Do not interpret medical necessity, symptoms, diagnoses, treatment, code validity, or clinical importance.

Output one table: supplied requirement; state; source fact; evidence location; missing or conflicting item; human check. Route missing evidence to human review; it does not prove a failed criterion or delayed care. Require qualified medical-administration and clinical review before submission or use in a care decision. This skill does not claim HIPAA compliance or decide medical necessity, coverage, approval, or denial.

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. 11d ago First seen · 13 lines · 39 tokens per session scan A ca2e198d80ff

Subscribe to this mod's changes

prior-authorization-document-review is a skill published in the GitHub repository alex-alecu/garden-desk (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 39 tokens to every session and 272 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

redact-pii

Redact personal data from a document through the connected Superlinked MCP edge before working with the content. Use when the user asks to redact, anonymize, scrub, de-identify, or remove PII/sensitive data from a document.

superlinked/sie · 53 tokens

meta-pdf-reformat-pipeline

Modernize a legacy PDF: structural extraction → natural-language rewrite of problem pages → audit summary → re-merge into the final PDF.

opensquilla/opensquilla · 35 tokens

legal-writer

Legal document drafting -- contracts, memos, briefs, complaints, demand letters, opinions, discovery, settlements, ToS, privacy policies. Full pipeline: document structure, per-section writing, Bluebook citation, case law lookup (CourtListener API), regulation lookup (eCFR API), DOCX output, and TDD-style verification…

kortix-ai/suna · 161 tokens

audit-export

Export the full CocoAudit trail as a stakeholder-ready compliance document.

Snowflake-Labs/cocoplus · 15 tokens

contract-analyzer

OCR a contract PDF with mistralocr, then extract structured clauses and risk scores with mistralchat + jsonschema. Use when the user provides a contract document to analyze for risks, obligations, and key terms.

Swih/mistral-mcp · 44 tokens

signature-request

Pre-signature gate and routing plan for a finalized document — verifies exact legal entity names, signatory authority, attached exhibits, filled blanks, consistent dates, and counterparty details, then sets the signing order (sequential vs. parallel, with reasons), writes envelope instructions for any e-sign tool, and…

alebgl77/claude-inc · 97 tokens