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

@chief-clancy/dev

v0.12.0

Published

Autonomous Ralph Wiggum execution surface for Claude Code — pick up tickets and execute them with judgment

Readme

@chief-clancy/dev

Autonomous ticket executor for Claude Code.

npm License: MIT

npx @chief-clancy/dev

[!WARNING] Clancy is in early development. Expect breaking changes and rough edges.

Pick up tickets from your board and execute them autonomously — branch, implement, create PR. Works standalone with board credentials, or as part of the full Clancy pipeline.

What it does

The /clancy:dev slash command fetches a ticket from your board, grades it through a 5-check readiness gate, and runs the full pipeline (branch setup, implementation, PR creation). The /clancy:dev-loop command processes multiple tickets in sequence with quiet hours, halt conditions, and structured artifact reporting.

How it works

  1. Install: npx @chief-clancy/dev — choose global or local
  2. Configure: /clancy:board-setup — enter your board credentials
  3. Run one ticket: /clancy:dev PROJ-123 — grade and execute
  4. Or go AFK: /clancy:dev-loop --afk — autonomous batch execution

Modes

| Mode | Command | Behaviour | | ------------- | ------------------------------------- | --------------------------------------------------- | | Single ticket | /clancy:dev PROJ-123 | Grade one ticket, execute if green | | AFK loop | /clancy:dev-loop --afk | Pre-flight grade all tickets, halt if any non-green | | AFK strict | /clancy:dev-loop --afk --afk-strict | Execute greens, defer yellows, halt on reds |

Flags

| Flag | Description | | -------------------- | ------------------------------------------------------------------------- | | --afk | Enable AFK mode (pre-flight grading, no prompts) | | --afk-strict | Execute only green tickets, defer yellows | | --max=N | Cap the number of tickets to process | | --max-batch=N | Cap the pre-flight batch size | | --bypass-readiness | Skip the readiness gate (requires --reason="...", rejected in AFK mode) | | --resume | Resume from a partial pre-flight checkpoint | | --yes | Skip interactive cost confirmation |

Local plan execution (--from)

The pipeline supports executing local plan files without board credentials. This capability is surfaced via /clancy:implement (installed by chief-clancy or @chief-clancy/terminal):

# Single plan
/clancy:implement --from .clancy/plans/add-dark-mode-1.md

# Batch mode — implement all approved plans in a directory
/clancy:implement --from .clancy/plans/ --afk

How it works: The --from flag bypasses the board entirely — no credentials, no ticket fetch. The pipeline parses the plan file for ticket key (slug), title, and implementation details, creates a synthetic ticket, and runs with a no-op board. In single-file mode, no approval check is performed. In batch mode, unapproved plans (no .approved marker) are skipped with a warning.

Batch mode (--from {directory} --afk) lists .md plan files in the directory, naturally sorted by filename, skips unapproved plans with a warning, and implements each approved plan sequentially. Stops on first failure and reports an implemented/skipped/remaining summary.

PR creation works in two tiers: if .clancy/.env contains a GITHUB_TOKEN (or equivalent), PRs are created automatically. Without tokens, the branch is pushed and you create the PR manually.

Readiness gate

Every ticket is graded against a 5-check rubric before execution:

| Check | Question | | ----------------- | -------------------------------------- | | Clear | Is the ticket unambiguous? | | Testable | Can success be verified with tests? | | Small | Is it a single deliverable unit? | | Locatable | Can the subagent find the right files? | | Touch-bounded | Is the set of files to modify bounded? |

Green tickets execute. Yellow tickets prompt for clarification (or are deferred in --afk-strict mode). Red tickets halt.

Artifacts

AFK loop runs produce structured artifacts in .clancy/dev/:

| Artifact | Written when | Description | | --------------------- | --------------------------- | ----------------------------------------------- | | readiness-report.md | Pre-flight runs | Colour-bucketed verdicts for all graded tickets | | run-summary.md | After execution | Per-ticket status, timing, halt reason | | deferred.json | --afk-strict with yellows | Deferred ticket ids and reasons | | drift.json | After execution (AFK modes) | Predicted vs actual changed files |

Reports are rotated (last 3 kept). All writes are atomic (write-temp-rename).

Board setup

To execute tickets from your board without the full pipeline:

  1. Run /clancy:board-setup in Claude Code
  2. Follow the prompts to configure your board credentials
  3. Run /clancy:dev PROJ-123 (or your board's ticket format)

Credentials are stored in .clancy/.env and are per-project (not global).

Supported boards: Jira, GitHub Issues, Linear, Shortcut, Notion, Azure DevOps.

Updating

Run /clancy:update-dev in Claude Code. It checks npm for the latest version, shows what's new from the GitHub release, and re-runs the installer to overwrite commands, workflows, agents, and runtime bundles (clancy-dev.js, clancy-dev-autopilot.js). Supports --afk to skip the confirmation prompt.

Uninstalling

Run /clancy:uninstall-dev in Claude Code. It removes dev-exclusive commands and workflows from the selected scope. For project-scoped uninstalls, it also removes runtime bundles (.clancy/clancy-dev.js, .clancy/clancy-dev-autopilot.js) and the VERSION marker. Checks for other installed Clancy packages before removing shared files (board-setup, scan agents, map-codebase, update-docs). Leaves .clancy/.env untouched.

Full pipeline

@chief-clancy/dev covers autonomous ticket execution. For strategic briefing, planning, and the full development lifecycle, install the complete Clancy package:

npx chief-clancy

Also included

Installing @chief-clancy/dev also installs codebase scanning commands from @chief-clancy/scan:

  • /clancy:map-codebase — scan your codebase with 5 parallel agents and generate .clancy/docs/
  • /clancy:update-docs — incrementally refresh docs affected by recent changes

Running /clancy:map-codebase before executing tickets enriches the readiness grading with real codebase context.

Part of the Clancy monorepo

Credits

Built on the Ralph technique by Geoffrey Huntley. See CREDITS.md.

License

MIT — see LICENSE.