npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

nominee-openai

v3.0.0

Published

Bridges OpenAI Agents' native approval into nominee's one-shot evidence: an approved call cannot change before the resumed token is minted.

Readme

nominee-openai

Decision-bound tools for the OpenAI Agents SDK.

import { Agent } from '@openai/agents'
import { Nominee, allow, ask } from 'nominee'
import { nomineeTool } from 'nominee-openai'
import { z } from 'zod'

const nominee = new Nominee({
  policy: {
    rules: [allow('github.issue.read'), ask('github.issue.close')],
    fallback: 'deny',
  },
})

const closeIssue = nomineeTool({
  name: 'close_issue',
  description: 'Close one GitHub issue',
  parameters: z.object({ repo: z.string(), issue: z.number() }),
  nominee,
  action: 'github.issue.close',
  user: ({ context }) => context.context.userId,
  resource: ({ input }) => `repo:${input.repo}#${input.issue}`,
  connection: 'github',
  scopes: ['issues:write'],
  execute: async ({ repo, issue }, { token }) => {
    // The credential is fetched only after the exact call is authorized.
    return closeGitHubIssue({ repo, issue, token })
  },
})

const agent = new Agent({ name: 'support-agent', tools: [closeIssue] })

Nominee ask rules are evaluated by the SDK's needsApproval hook. OpenAI pauses the run, and on resume the adapter verifies the approved tool-call id from RunContext before recording approval evidence and executing. Denials remain exceptions and never call the underlying tool.

What happens on ask

This adapter maps Nominee ask (and needsApproval) into the OpenAI Agents SDK's native, resumable approval flow: the run pauses for a human decision, and on resume the adapter verifies the approved tool-call id from RunContext and seals it as framework approval evidence on the action before execute runs. A denial remains an exception and never calls the tool. If execute runs without verifiable framework approval (e.g. a direct call that bypassed the SDK's pause), the portable path applies instead: the ask is settled inline when possible, or the call throws ActionPendingError with a durable actionId — persist that id and the original input, then resume with resolveActionApproval()resumeAction()executeCapability(). Full walkthrough: Approvals that outlive the request.

Observe before enforcing

Use the same tool with new Nominee({ mode: 'observe' }) to inventory the callbacks that actually run before writing a policy. The adapter's needsApproval hook returns false in this mode—including for an explicitly configured approval—while the original ask/deny verdict remains on the action and receipts. Observation reports do not retain raw string/boolean values or user IDs; numeric aggregates may be sensitive. Observe mode is not a security control and cannot be combined with production: true.