Skip to main content
skill CX Codex

ping — Claude Code skill: verify the Mycelium plugin loaded

A smoke test that answers with one marker line when the Mycelium plugin is packaged and wired up correctly. Not meant for everyday use.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add haabe/mycelium --skill ping -a claude-code
Open on GitHub

What ping does

Call it and you get a single line back: MYCELIUM_PLUGIN_LOAD_OK. Nothing else. The string is a plugin-shape marker, not a version claim — it proves the whole path works, from manifest through the marketplace and install to a namespaced invocation. To see which version is actually running, check /plugin list or the version field in plugin.json.

The marker used to carry a version suffix, and that drifted: it sat at _v0.20.0 while plugin.json moved through 10 patches. It came up during dogfood on 2026-05-09, so the suffix is gone.

Metadata sets disable-model-invocation: true, so the model will not pick this skill up on its own. It also assumes it runs inside the Mycelium framework — standalone, you lose the canvas state, theory gates and harness behavior it expects. Real Mycelium skills live in the parent skills/ directory.

What it helps with

  • confirm the Mycelium plugin installed and responds to a namespaced call
  • check packaging after edits to the manifest or marketplace entry
  • tell an install problem apart from a skill problem
  • get a predictable answer to assert on in a script

Example prompts for the agent

  • Run the ping skill and show me the output verbatim
  • Check that the Mycelium plugin loaded — invoke ping
  • ping should return one line; what did it return?

How to install ping

1Skills CLI (Vercel)

npx skills add haabe/mycelium --skill ping -a claude-code

2Manually: put the files in place

~/.claude/skills/ping/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/ping/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about ping

How do I install ping in Claude Code?

Use the skills installer: npx skills add haabe/mycelium --skill ping -a claude-code. The skill file then sits at ~/.claude/skills/ping/SKILL.md.

What does the ping skill do?

It replies with the single line MYCELIUM_PLUGIN_LOAD_OK, which confirms the Mycelium plugin is packaged and reachable by a namespaced call.

Why doesn't the model invoke ping by itself?

The skill metadata sets disable-model-invocation: true, so there is no automatic pickup — you call it yourself.

Source text

SKILL.md · MIT
---
name: ping
description: Smoke-test skill that confirms the Mycelium plugin loaded correctly. Returns a deterministic marker string for plugin-shape validation. Not for end-user invocation in normal use.
disable-model-invocation: true
metadata:
  framework_dependency: "mycelium"
  framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin install mycelium@haabe-mycelium."
---

# Ping (smoke-test only)

When invoked, respond with exactly this single line and nothing else:

```
MYCELIUM_PLUGIN_LOAD_OK
```

This is a plugin-shape marker, not a version assertion — it confirms the plugin packaging works end-to-end (manifest → marketplace → install → namespaced invocation). The version a user is actually running comes from `/plugin list` or `plugin.json#version`, not this marker. (The marker was previously version-suffixed, which created drift: it stayed pinned at `_v0.20.0` while plugin.json moved through 10 patches. Detected during 2026-05-09 dogfood.)

For real Mycelium skills, see the parent `skills/` directory once migration completes.

© haabe · MIT · haabe/mycelium

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set18

team-shape Checks your teams against Team Topologies: types, cognitive load, interaction modes and whether the architecture follows Conway's Law on purpose. CX Codex +1 ★ 47repo stars retrospective Logs a completed cycle to the canvas: what you predicted, what actually happened, where the estimate missed. Keeps retros on data instead of memory. CX Codex +1 ★ 47repo stars reflexion A skill that runs implement, validate, self-critique and retry up to three times, then escalates with a written list of what is still broken. CX Codex +1 ★ 47repo stars prompt-optimizer Runs your CLAUDE.md edits against two eval splits and shows whether the gain is real or just fitting the test set. CX Codex +1 ★ 47repo stars mocked-persona-interview For solo and hobby projects where real user interviews are off the table: the skill runs interviews with invented personas and keeps them from becoming a rubber stamp for your own assumptions. CX Codex +1 ★ 47repo stars metrics-detect Scans the repo and sets up adapters for the metric sources your product actually uses, from GitHub to Stripe. Handy when the project predates this setup. CX Codex +1 ★ 47repo stars jtbd-map Splits customer work into functional, emotional and social jobs, then saves the map to a canvas file. CX Codex +1 ★ 47repo stars harms-check A skill that scans a user-facing product for deceptive patterns and foreseeable misuse before release, the harms that security and privacy gates don't look for. CX Codex +1 ★ 47repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor