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.
npx skills add tylergibbs1/backwork-mcp --skill prior-auth-researchgit clone --depth 1 https://github.com/tylergibbs1/backwork-mcpWrote 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/skills/tylergibbs1/backwork-mcp/prior-auth-research)<a href="https://agentmods.dev/skills/tylergibbs1/backwork-mcp/prior-auth-research"><img src="https://agentmods.dev/badge/skills/tylergibbs1/backwork-mcp/prior-auth-research/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/skills/tylergibbs1/backwork-mcp/prior-auth-research"><img src="https://agentmods.dev/badge/skills/tylergibbs1/backwork-mcp/prior-auth-research.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 | $0.00038 | $0.01417 |
| Opus 5.5 | $0.00015 | $0.00567 |
| Sonnet 5.5 | $0.00008 | $0.00283 |
| Haiku 4.5 | $0.00004 | $0.00142 |
Grade A, and why
prior-auth-research 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 15d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prior authorization research
Given a payer and CPT/HCPCS codes (and optionally diagnosis codes and a state), find out whether the payer's policy requires prior authorization, list the documentation criteria with citations, flag gaps, and produce a submission checklist.
The tools come from the Backwork MCP server. Their names start with backwork_. Some clients add a prefix, for example mcp__plugin_backwork_backwork__backwork_prior_auth_research. If no Backwork tool is available, tell the user to connect Backwork (https://backworkhealth.com/mcp) and stop. Do not answer from general knowledge.
Ground rules
- Research support, not a determination. Report what the policy says. Never say PA "will be approved" or that a service "is medically necessary". End every answer with: "Confirm with the payer before you submit or schedule."
- No PHI. Never ask for or accept patient names, member IDs, dates of birth, MRNs, addresses, or chart notes. If the user pastes any, do not repeat it. Ask them to remove it, and continue with codes, payer, state, plan type, and policy as-of date only. Send only those values to the tools.
- Cite from tool output only. Each policy citation needs: policy number (
policy_id), title, payer or authority, effective date, and source URL. Add the last-verified date when the tool returns it. A field the tool did not return is written "not returned". Never fill it in from memory. - Inferred codes are not document-backed. A code with
source: inferred_title_matchis attached because the policy title names the drug. The document does not list the code. Label it "Inferred from policy title. Confirm in the document." A code withsource: document(or nosource) is listed in the document. - Say when you don't know. If the tools return no PA rule or policy, write "Not determinable from Backwork data" and say what is missing. Do not guess.
Steps
- Get the inputs: payer and codes (required). Optional: diagnosis codes, state, plan type. Ask for payer or code if missing.
- Get the PA signal.
- Traditional Medicare: call
backwork_prior_auth_researchwithaction: "check",procedure_codes, andstate. - Any other payer (commercial, Medicare Advantage, Medicaid): call
backwork_prior_auth_researchwithaction: "start_research",procedure_codes,payer,state, anddiagnosis_codes. If the result has aresearch_idand is not complete, callaction: "get_research"with thatresearch_idup to three times. If it is still running, give theresearch_idto the user and continue with the policy evidence.
- Traditional Medicare: call
- Get the policy evidence. Call
backwork_coverage_lookupwithprocedure_codes,payer,state,diagnosis_codes,include: ["code_details", "prior_auth"], andcode_include: ["policies"]. - For each policy that matches the payer (at most three), call
backwork_policy_researchwithaction: "get",policy_id, andinclude: ["criteria", "codes"]. Read the code'ssourceand the criteria sections. - If the criteria are thin, call
backwork_policy_researchwithaction: "criteria",queryset to the code or service name, andsection: "documentation". - If diagnosis codes were given, call
backwork_claim_validationwithprocedure_codes,diagnosis_codes,payer, andstateto get documentation requirements and denial-risk notes. - Write the answer in the format below.
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.
- 15d ago First seen · 76 lines · 38 tokens per session scan A 7f0fef4e4629
prior-auth-research is a skill published in the GitHub repository tylergibbs1/backwork-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 1,417 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-02.
Other skills, from other repositories
fto-triage
Freedom-to-operate triage — a structured first look at potentially blocking patents, not an FTO opinion. Use when a product, process, or feature is being evaluated for blocking patents, when asked whether anything stops a launch, or to build a claim-chart first pass against the most plausible patents before patent…
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.