Skip to main content
skill CX Codex

openevidence-cost-tuning — Claude Code skill: install and usage

openevidence-cost-tuning evaluates OpenEvidence adoption and workflow burden in healthcare without inventing pricing, quotas, or telemetry. Helps prepare renewal briefs.

MIT 1 installs ★ 2,935 updated 2026-10-29

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add jeremylongshore/tons-of-skills-marketplace --skill openevidence-cost-tuning -a claude-code
Open on GitHub

What openevidence-cost-tuning does

This skill prepares evidence-based assessments for OpenEvidence deployments across medical teams. It structures decisions about pilot renewals, license expansion, or workflow retirement based on verified internal logs and official enterprise contracts.

The assistant inspects local documents using Read, Glob, and Grep, reserving WebFetch strictly for first-party vendor documentation. Without an active order form or institutional agreement, the skill refuses to assume license rates, quotas, or service commitments. It enforces strict separation between verifiable telemetry and team anecdotes.

Data governance rules are absolute here. The skill blocks handling of protected health information (PHI), forbids session token scraping, and leaves clinical decisions entirely to the accountable owner.

What it helps with

  • audit pilot adoption of OpenEvidence before enterprise renewal
  • identify redundant or abandoned clinical query workflows
  • isolate contract terms from unverified pricing estimates
  • strip patient identifiers and credentials from analysis briefs

Example prompts for the agent

  • Run openevidence cost tuning for review-period 90d on ./audit/usage.json
  • Prepare an OpenEvidence value brief for our department renewal review
  • Review clinician adoption burden for OpenEvidence without inventing seat pricing

How to install openevidence-cost-tuning

1Skills CLI (Vercel)

npx skills add jeremylongshore/tons-of-skills-marketplace --skill openevidence-cost-tuning -a claude-code

2Manually: put the files in place

~/.claude/skills/openevidence-cost-tuning/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/openevidence-cost-tuning/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about openevidence-cost-tuning

How to install openevidence-cost-tuning in Claude Code?

Run npx skills add jeremylongshore/tons-of-skills-marketplace --skill openevidence-cost-tuning -a claude-code in your terminal.

What does openevidence-cost-tuning do?

It builds decision-ready reviews of OpenEvidence adoption using authorized local data. The skill measures workflow outcomes and time saved while strictly avoiding speculative usage pricing.

Can this skill work without an executed vendor contract?

It flags commercial terms as unverified until an authorized account owner provides the actual agreement.

Source text

SKILL.md · MIT
---
name: openevidence-cost-tuning
description: >-
  Evaluate OpenEvidence adoption value and access burden without inventing prices, quotas, or usage telemetry. Use when working with OpenEvidence in a healthcare organization. Trigger with "openevidence cost tuning", "OpenEvidence value", or a matching workflow request.
argument-hint: "[usage-evidence-path] [review-period]"
allowed-tools: Read, Glob, Grep, WebFetch, Write, Edit
version: 1.14.0
author: Jeremy Longshore <[email protected]>
license: MIT
tags:
- saas
- openevidence
- value
- adoption
model: inherit
effort: high
compatibility: Designed for Claude Code; requires authorized OpenEvidence access and qualified clinical review for patient-care use
---
# OpenEvidence Access and Value Review

## Overview

Build a decision-ready value review from authorized local evidence and current commercial terms. Keep inputs minimal, separate observed facts from assumptions, and leave consequential decisions with the named accountable owner.

## Prerequisites

- A clearly bounded workflow, accountable clinical owner, and organizational policy
- Current first-party OpenEvidence documentation and applicable institution agreements
- Synthetic or properly authorized minimum-necessary data

## Tool Discipline

Use `Read`, `Glob`, and `Grep` to inspect supplied policies, plans, and evidence. Use `WebFetch` only for current first-party OpenEvidence documentation. Use `Write` or `Edit` only when the user requests a named deliverable with an approved destination. Never expose credentials, PHI, recordings, or unrestricted environment output.

## Current Contract

- Public product pages do not establish institution-specific price, quota, SLA, or entitlement terms.
- Only a current order form, MSA, or authorized account surface can establish commercial commitments.
- Clinical quality and safety outcomes must not be reduced to raw query volume.

## Authentication

Use only the official OpenEvidence web/mobile sign-in or an institution-approved access path. Do not invent API keys, OAuth clients, SDK credentials, service accounts, or private endpoints. Never ask a user to reveal a password, session token, cookie, or recovery code.

## Instructions

1. Define the decision: pilot continuation, feature expansion, workflow retirement, or contract review.
2. Collect authorized evidence for active users, completed workflows, time saved, failure modes, and training/support burden.
3. Separate product facts from institution-specific contract terms and unverified anecdotes.
4. Measure value by workflow outcome, evidence-review quality, clinician time, and adoption friction; avoid patient-outcome causality claims.
5. Identify unused or duplicative workflows and test a reversible change with the accountable owner.
6. Return a value brief with data provenance, limitations, owner, decision date, and next measurement.

## Approval Boundaries

Do not create or share accounts; change access, roles, agreements, consent, retention, or security settings; enter PHI; record a conversation; copy content into another system; contact a patient; make a diagnosis or treatment decision; submit billing; transmit a support packet; run a production pilot; or represent vendor capabilities without explicit approval from the accountable owner. A qualified professional remains responsible for clinical decisions.

## Output

Return scope, current first-party evidence and date, data classification, workflow or findings, citations reviewed, assumptions rejected, clinical and governance owners, approval state, unresolved risk, and the exact next action. Redact patient and credential data.

## Error Handling

| Condition | Response |
|---|---|
| No usage export | Use a documented sample or local survey and label the evidence incomplete. |
| Price unavailable | Request the current commercial document; never estimate it as fact. |
| Metric encourages unsafe speed | Replace it with quality, review, and workflow-completion measures. |

## Examples

This compact example shows the minimum reviewable handoff; adapt fields to the approved workflow without adding sensitive data.

Input:

```text
period=90d; cohort=pilot clinicians; decision=renewal; contract=owner-held
```

Expected handoff:

```text
value=evidence-backed; gaps=2; commercial-terms=unverified; recommendation=conditional
```

## Resources

- [OpenEvidence official evidence register](references/official-docs.md)
- [OpenEvidence User Guide](https://www.openevidence.com/user-guide)
- [OpenEvidence Terms of Use](https://www.openevidence.com/policies/terms)

© Jeremy Longshore · MIT · jeremylongshore/tons-of-skills-marketplace

Similar skills

All skills for Notes, tasks and projects →

From the same set139

The whole set →
excel-lbo-modeler excel-lbo-modeler — a skill that builds leveraged buyout models in Excel: deal structure, debt schedules, IRR and MOIC. Use it when you need a quick read on PE returns for a transaction. CX Codex +1 2installs excel-formula-generator excel-formula-generator generates spreadsheet formulas and configurations for business automation tasks. Activates on requests mentioning Excel operations and formula design. CX Codex +1 2installs juicebox-cost-tuning The juicebox-cost-tuning skill helps control Juicebox spending by cutting redundant searches and profile enrichment, then checking changes against a quota baseline. CX Codex +1 1installs twinmind-cost-tuning twinmind-cost-tuning picks a TwinMind tier and tracks where meeting minutes go. Handy when transcription costs climb and you need a clear picture. CX Codex +1 1installs deepgram-cost-tuning The deepgram-cost-tuning skill outlines ways to track Deepgram spend, set budget checks for transcription, and reduce billable audio time through preprocessing. CX Codex +1 1installs clerk-cost-tuning clerk-cost-tuning — a skill that makes Clerk's MRU pricing concrete and trims the bill: auth only where it is needed, caching around the Backend API, a script for idle accounts. CX Codex +1 1installs lindy-cost-tuning lindy-cost-tuning audits Lindy AI credit usage, downsizes models, and consolidates agent workflows to cut monthly spending. CX Codex +1 1installs evernote-cost-tuning The evernote-cost-tuning skill helps track Evernote upload quotas, estimate note sizes, and spot storage-heavy notes. Use it when an integration needs quota checks before uploading attachments. CX Codex +1 1installs

Project sponsors

Companies that keep this analytics open