Saucebox Registry
← Browse

@pipecrew-ai/siteview-list

A

List every PipeCrew site-view server currently running on localhost. Probes ports 5173-5195 via the /state endpoint and reports port, PID, workspace, run-id, character count, and whether any server is awaiting user input. Use when you've started multiple runs and need to see what's alive, or before killing a stale server.

skillclaude

Install

agr install @pipecrew-ai/siteview-list --target claude

Writes 2 files into .claude/skills/, pinned to git-06de2fcb.

  • .claude/skills/siteview-list/SKILL.md
  • .claude/skills/siteview-list/scan.js

Document

name: siteview-list description: List every PipeCrew site-view server currently running on localhost. Probes ports 5173-5195 via the /state endpoint and reports port, PID, workspace, run-id, character count, and whether any server is awaiting user input. Use when you've started multiple runs and need to see what's alive, or before killing a stale server.

/siteview-list

Quick inventory of every PipeCrew site-view server currently running.

Useful when:

  • You've started multiple runs and lost track of which port hosts which.
  • Old servers from prior sessions may still be running — this shows them.
  • Before killing a process, verify by port + run-id what it's serving.

Usage

/pipecrew:siteview-list

No arguments. Scans localhost ports 5173–5195; any server responding to /state with a PipeCrew-shaped payload is reported.

Instructions

When the user invokes /siteview-list:

  1. Run the scan script via Bash: 
    node {plugin_dir}/skills/siteview-list/scan.js
  2. Relay the output to the user verbatim — it's a pre-formatted table.
  3. If no servers are running, suggest /pipecrew:site-view to start one.
  4. If stale servers are found (run-ids that don't match the user's current active run), offer to kill them by PID.

Output example

3 site-view server(s) running:

PORT  PID     WORKSPACE  RUN ID                                           CHARS  INPUT  FEATURE
----  ------  ---------  ------------------------------------------------  -----  -----  -------
5173  20828   dal        2026-04-16-114907-simulated-demo                  10     no     simulated-demo
5177  16352   dal        2026-04-16-122519-book-content-upload             16     no     book-content-upload
5178  13252   dal        2026-04-17-024620-simulated-demo                  15     no     simulated-demo

Full reference

Scan range + probe details documented in {plugin_dir}/skills/siteview-list/scan.js header.

Trustgrade A

  • passBody integrity

    Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.

  • passType matchnot applicable to this artifact type

    Whether the artifact is really the kind of thing its metadata claims it is.

  • passFreshness

    How long since the source repository was last pushed to.

  • passPrompt injection

    Scans the artifact's own text for instructions aimed at your agent rather than at you.

  • passLicense

    Whether the source repository declares an SPDX license permissive enough to redistribute.

How the grade is calculated

Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:

  • Aevery check passed
  • Bone warning
  • Ctwo warnings
  • Dprompt injection or body integrity failed, or three warnings
  • Fone of those failed, and something else is wrong

These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.

Versions

  • git-06de2fcbfe842026-07-31