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

@clawdbot/lobster

v2026.1.24

Published

Workflow runtime for AI agents - deterministic pipelines with approval gates

Readme

Lobster

A Clawdbot-native workflow shell: typed (JSON-first) pipelines, jobs, and approval gates.

Example of lobster at work

Clawdbot or any other AI agent can use lobster as a workflow engine and not construct a query every time - thus saving tokens, providing room for determinism, and resumability.

Watching a PR that hasn't had changes

node bin/lobster.js "workflows.run --name github.pr.monitor --args-json '{\"repo\":\"clawdbot/clawdbot\",\"pr\":1152}'"
[
  {
    "kind": "github.pr.monitor",
    "repo": "clawdbot/clawdbot",
    "prNumber": 1152,
    "key": "github.pr:clawdbot/clawdbot#1152",
    "changed": false,
    "summary": {
      "changedFields": [],
      "changes": {}
    },
    "prSnapshot": {
      "author": {
        "id": "MDQ6VXNlcjE0MzY4NTM=",
        "is_bot": false,
        "login": "vignesh07",
        "name": "Vignesh"
      },
      "baseRefName": "main",
      "headRefName": "feat/lobster-plugin",
      "isDraft": false,
      "mergeable": "MERGEABLE",
      "number": 1152,
      "reviewDecision": "",
      "state": "OPEN",
      "title": "feat: Add optional lobster plugin tool (typed workflows, approvals/resume)",
      "updatedAt": "2026-01-18T20:16:56Z",
      "url": "https://github.com/clawdbot/clawdbot/pull/1152"
    }
  }
]

And a PR that has a state change (in this case an approved PR)

 node bin/lobster.js "workflows.run --name github.pr.monitor --args-json '{\"repo\":\"clawdbot/clawdbot\",\"pr\":1200}'"
[
  {
    "kind": "github.pr.monitor",
    "repo": "clawdbot/clawdbot",
    "prNumber": 1200,
    "key": "github.pr:clawdbot/clawdbot#1200",
    "changed": true,
    "summary": {
      "changedFields": [
        "number",
        "title",
        "url",
        "state",
        "isDraft",
        "mergeable",
        "reviewDecision",
        "updatedAt",
        "baseRefName",
        "headRefName"
      ],
      "changes": {
        "number": {
          "from": null,
          "to": 1200
        },
        "title": {
          "from": null,
          "to": "feat(tui): add syntax highlighting for code blocks"
        },
        "url": {
          "from": null,
          "to": "https://github.com/clawdbot/clawdbot/pull/1200"
        },
        "state": {
          "from": null,
          "to": "MERGED"
        },
        "isDraft": {
          "from": null,
          "to": false
        },
        "mergeable": {
          "from": null,
          "to": "UNKNOWN"
        },
        "reviewDecision": {
          "from": null,
          "to": ""
        },
        "updatedAt": {
          "from": null,
          "to": "2026-01-19T05:06:09Z"
        },
        "baseRefName": {
          "from": null,
          "to": "main"
        },
        "headRefName": {
          "from": null,
          "to": "feat/tui-syntax-highlighting"
        }
      }
    },
    "prSnapshot": {
      "author": {
        "id": "MDQ6VXNlcjE0MzY4NTM=",
        "is_bot": false,
        "login": "vignesh07",
        "name": "Vignesh"
      },
      "baseRefName": "main",
      "headRefName": "feat/tui-syntax-highlighting",
      "isDraft": false,
      "mergeable": "UNKNOWN",
      "number": 1200,
      "reviewDecision": "",
      "state": "MERGED",
      "title": "feat(tui): add syntax highlighting for code blocks",
      "updatedAt": "2026-01-19T05:06:09Z",
      "url": "https://github.com/clawdbot/clawdbot/pull/1200"
    }
  }
]

Goals

  • Typed pipelines (objects/arrays), not text pipes.
  • Local-first execution.
  • No new auth surface: Lobster must not own OAuth/tokens.
  • Composable macros that Clawdbot can invoke in one step to save tokens.

Quick start

From this folder:

  • pnpm install
  • pnpm test
  • pnpm lint
  • node ./bin/lobster.js --help
  • node ./bin/lobster.js doctor
  • node ./bin/lobster.js "exec --json --shell 'echo [1,2,3]' | where '0>=0' | json"

Notes

  • pnpm test runs tsc and then executes tests against dist/.
  • bin/lobster.js prefers the compiled entrypoint in dist/ when present.

Commands

  • exec: run OS commands
  • exec --stdin raw|json|jsonl: feed pipeline input into subprocess stdin
  • where, pick, head: data shaping
  • json, table: renderers
  • approve: approval gate (TTY prompt or --emit for Clawdbot integration)

Next steps

  • Clawdbot integration: ship as an optional Clawdbot plugin tool.

Workflow files

Lobster can run YAML/JSON workflow files with steps, env, condition, and approval gates.

lobster run path/to/workflow.lobster
lobster run --file path/to/workflow.lobster --args-json '{"tag":"family"}'

Example file:

name: inbox-triage
steps:
  - id: collect
    command: inbox list --json
  - id: categorize
    command: inbox categorize --json
    stdin: $collect.stdout
  - id: approve
    command: inbox apply --approve
    stdin: $categorize.stdout
    approval: required
  - id: execute
    command: inbox apply --execute
    stdin: $categorize.stdout
    condition: $approve.approved