prior-auth-packet-builder

A workflow for assembling a concise prior-authorization packet from case files and insurer policy documents. Prior authorization is an insurer’s approval required before some treatments or services are covered.

In plain words
What is it for?
Use it to review a case, find matching rules about authorization, referrals, imaging, or billing, create two review documents, and finalize the packet.
Why use it?
It brings the relevant case facts and policy requirements together and highlights missing information before a human reviewer makes a decision.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/openai/openai-agents-python/prior-auth-packet-builder
Any agent
npx skills add openai/openai-agents-python --skill prior-auth-packet-builder
Clone the repo
git clone --depth 1 https://github.com/openai/openai-agents-python

Made for: Claude Code, Codex.

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 396 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00021 $0.00396
Opus 5 $0.00010 $0.00198
Sonnet 5 $0.00004 $0.00079
Haiku 4.5 $0.00002 $0.00040

Measured 3d ago against content hash a4c0f07d18d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prior-auth-packet-builder 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 3d 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.

examples/sandbox/healthcare_support/skills/prior-auth-packet-builder/SKILL.md · 40 lines

What it actually says

Prior Auth Packet Builder

Use this skill when a case requires prior authorization review, referral validation, imaging review, or payer-specific policy checks.

Workflow

  1. Inspect case/scenario.json and case/transcript.txt.
  2. Search policies/ for payer, prior auth, referral, imaging, and PPO guidance:
    • Run the preferred search and fallback as one shell command: rg -n -i 'prior authorization|prior-auth|imaging|referral|billing|PPO|Blue Cross' policies || grep -RniE 'prior authorization|prior-auth|imaging|referral|billing|PPO|Blue Cross' policies.
    • An rg launcher or bootstrap failure is not evidence that there are no policy matches.
  3. Read only the most relevant policy files.
  4. Create output/policy_findings.md with these exact headings:
    • ## Case summary
    • ## Matched policy files
    • ## Prior authorization
    • ## Referral
    • ## Missing information Cite each matched policy by its filename.
  5. Create output/human_review_checklist.md with:
    • what a human reviewer should verify
    • what to tell the patient
    • what queue should own the case
  6. Call finalize_policy_packet only after both artifacts exist.

Rules

  • Use targeted searches over broad file reads.
  • Use the targeted grep -RniE fallback only when rg cannot complete the search.
  • Only cite policy files you actually inspected.
  • Keep outputs concise and operational.
  • The workflow is complete only when finalize_policy_packet succeeds.
  • If referral status is pending and prior auth is unclear, recommend human review.
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. 3d ago First seen · 40 lines · 21 tokens per session scan A a4c0f07d18d1

Subscribe to this mod's changes

prior-auth-packet-builder is a skill published in the GitHub repository openai/openai-agents-python (29,123 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 396 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.

Related

Other skills, from other repositories

pdf-processing

Process and extract information from PDF documents. Use this skill when the user asks to read, analyze, or extract data from PDF files.

MervinPraison/PraisonAI · 30 tokens

document-parsing

Extract readable Markdown from local Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and text-based PDF files using the preinstalled AnyDoc runtime.

Cloudgeni-ai/opengeni · 39 tokens

opengeni-documents

Create, inspect, edit, review, import, and export durable OpenGeni document artifacts and explicit DOCX file boundaries. Use for reports, briefs, proposals, forms, tables, sections, headers, footers, comments, tracked changes, and Word-compatible delivery.

Cloudgeni-ai/opengeni · 60 tokens

opengeni-presentations

Create, inspect, edit, import, and export durable OpenGeni presentation artifacts and explicit PPTX file boundaries. Use for decks, slides, masters, layouts, rich text, tables, charts, imported media, groups, notes, and visual presentation QA.

Cloudgeni-ai/opengeni · 58 tokens

opengeni-spreadsheets

Create, inspect, calculate, edit, import, and export durable OpenGeni spreadsheet artifacts and explicit XLSX/CSV file boundaries. Use for workbooks, formulas, analyses, tables, calculations, and spreadsheet visual QA. Do not use for controlling a live Excel application.

Cloudgeni-ai/opengeni · 62 tokens

document-writer

专业文档编写技能。用于撰写技术文档、README、API文档、用户手册等。当用户需要编写或改进文档时使用此技能。.

RTGS2017/NagaAgent · 44 tokens