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

@shapeshift-labs/frontier-tools

v0.1.0

Published

Serializable action and tool manifests for agent-operable Frontier apps.

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

shapeshift-labsshapeshift-labs

Keywords

frontiertoolsagentsactionsfunction-callingmcpautomationpatches

Readme

@shapeshift-labs/frontier-tools

Serializable action and tool manifests for agent-operable Frontier apps.

frontier-tools turns app affordances into data: what an action reads, writes, validates, requires, previews, rolls back, exposes to AI tools, and records after execution. It is not an agent runtime and it does not import MCP, OpenAI, LangChain, Vercel AI SDK, policy, route, view, trace, or mutation packages. Those systems can attach through structural adapters.

Related Packages

The published Frontier package family is generated from one shared package catalog so READMEs stay in sync across packages:

Package source repositories:

Install

npm install @shapeshift-labs/frontier-tools

Example

import {
  compileTools,
  createToolDescriptors,
  createToolsManifest,
  executeToolAction,
  planToolAction
} from '@shapeshift-labs/frontier-tools';

const tools = compileTools(createToolsManifest({
  id: 'todos.tools',
  actions: [{
    id: 'todos.complete',
    title: 'Complete todo',
    input: { todoId: 'string' },
    reads: ['entities.todos'],
    writes: ['entities.todos'],
    requires: ['todo.write'],
    dryRun: true,
    expectedPatch: [{ op: 'set', path: '/entities/todos/:id/done', value: true }],
    rollback: { action: 'todos.reopen' }
  }]
}));

const context = { capabilities: ['todo.write'] };

const descriptors = createToolDescriptors(tools, context, {
  format: 'openai',
  strict: true,
  includeFrontierMetadata: true
});

const plan = planToolAction(tools, {
  actionId: 'todos.complete',
  input: { todoId: 't1' },
  dryRun: true
}, context);

const record = executeToolAction(tools, {
  actionId: 'todos.complete',
  input: { todoId: 't1' },
  dryRun: true
}, { context });

Surface

  • createToolsManifest, defineTools, and defineToolAction normalize serializable action manifests.
  • compileTools indexes actions for repeated availability checks, descriptors, plans, and queries.
  • validateToolInput validates JSON-schema-shaped inputs without adding runtime validator dependencies.
  • planToolAction and planToolActionAsync return policy-aware dry-run plans with expected patch previews.
  • executeToolAction and executeToolActionAsync run structural handlers and produce replayable records.
  • createToolDescriptor and createToolDescriptors emit Frontier, OpenAI-style, MCP-style, Vercel-style, and LangChain-style tool descriptor data.
  • createToolsRegistryGraph and traceToolsImpact expose actions to Frontier registry and impact queries.
  • createToolsSession, encodeToolsJsonl, decodeToolsJsonl, redactToolsManifest, and createToolsProof support replay, audit, redaction, and evidence bundles.

Policy Bridge

Policy is structural. Pass a current policy decision or an evaluator:

const plan = await tools.planAsync(
  { actionId: 'todos.complete', input: { todoId: 't1' } },
  {
    capabilities: ['todo.write'],
    route: '/todos/inbox'
  },
  {
    policyEvaluator: async (request) => ({
      allowed: true,
      allowedTools: [request.tool],
      reasons: ['policy allowed tool']
    })
  }
);

The same decision can drive what descriptors an agent sees, whether a handler runs, which effects are blocked, and what proof is recorded.

Benchmarks

Package-local benchmark:

npm run bench

The package benchmark prints Frontier-only package measurements for manifest creation, compilation, availability, planning, descriptor generation, dry-run execution, registry graph output, JSONL, and proofs.

Research comparison harness:

npm run bench:competitors

Competitor results are intentionally kept in benchmark artifacts and research notes rather than README claims.