Clubhouse-Workshop: Skill for Claude Code

.claude/skills/prepare-beta/SKILL.md

prepare-beta is a skill for Claude Code from Agent-Clubhouse/Clubhouse-Workshop. It costs 43 tokens per session (1,698 once invoked), scanned A, original, MIT.

A release-preparation workflow for publishing a beta version of one Workshop plugin, a software add-on. It reviews that plugin’s commits, suggests a version change, and prepares a pull request (PR).

In plain words
What is it for?
Use it to prepare a plugin beta release from recent Git commits, create the release PR, and route the beta to the preview registry.
Why use it?
It removes the manual work of figuring out what changed and which beta version to publish. It also gives instructions for adding the release tag through the project’s automated checks.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is Agent-Clubhouse/Clubhouse-Workshop's own configuration. It tells Claude Code how to work on Clubhouse-Workshop itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Clubhouse-Workshop configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Agent-Clubhouse/Clubhouse-Workshop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Agent-Clubhouse/Clubhouse-Workshop/main/.claude/skills/prepare-beta/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Agent-Clubhouse/Clubhouse-Workshop

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for prepare-beta

README.md
[![agentmods](https://agentmods.dev/badge/skills/agent-clubhouse/clubhouse-workshop/prepare-beta/github.svg)](https://agentmods.dev/skills/agent-clubhouse/clubhouse-workshop/prepare-beta)
Your own site
<a href="https://agentmods.dev/skills/agent-clubhouse/clubhouse-workshop/prepare-beta"><img src="https://agentmods.dev/badge/skills/agent-clubhouse/clubhouse-workshop/prepare-beta/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prepare-beta

Your own site · 80×15
<a href="https://agentmods.dev/skills/agent-clubhouse/clubhouse-workshop/prepare-beta"><img src="https://agentmods.dev/badge/skills/agent-clubhouse/clubhouse-workshop/prepare-beta.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,698 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.01698
Opus 5 $0.00022 $0.00849
Sonnet 5 $0.00009 $0.00340
Haiku 4.5 $0.00004 $0.00170

Measured 11d ago against content hash b7fc55eadade, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

prepare-beta scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/prepare-beta/SKILL.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prepare a Plugin Beta Release

This skill prepares a beta release for a single Workshop plugin using a 6-phase flow. The user provides the plugin ID as $ARGUMENTS. If omitted, list available plugins and ask.

Scope: All work is filtered to plugins/<plugin-id>/ — only commits touching that directory are considered.


Phase 1: Gather Data

# Ensure main is up to date
git checkout main && git pull origin main

# Read current version from manifest
cat plugins/<plugin-id>/manifest.json | grep '"version"'

# Find existing tags for this plugin
git tag --list '<plugin-id>-v*' --sort=-v:refname | head -10

# Determine last stable tag (no -beta in name) and last beta tag
LAST_STABLE=$(git tag --list '<plugin-id>-v*' --sort=-v:refname | grep -v '\-beta\.' | head -1)
LAST_BETA=$(git tag --list '<plugin-id>-v*-beta.*' --sort=-v:refname | head -1)

# Collect commits since last tag (stable or beta, whichever is newer)
# Use the newer of the two as the base
git log <last-tag>..HEAD --oneline --no-merges -- plugins/<plugin-id>/

If no previous tags exist for this plugin, collect all commits touching plugins/<plugin-id>/.

Determine beta increment: if LAST_BETA exists and is newer than LAST_STABLE, increment its beta number. Otherwise, start at -beta.1.


Phase 2: Classify Commits

Classify each commit using first-match-wins:

  1. Featurefeat: prefix, or clearly new user-visible functionality
  2. Bug Fixfix: prefix, or user-visible bug correction
  3. Internalperf: prefix, optimizations, performance improvements
  4. Non-Userchore:, ci:, test:, docs:, build:, refactor:

Skip version bump commits entirely (chore: bump version to ...).


Phase 3: Coalesce

  • A Feature absorbs closely related fixes (show final state only)
  • Multiple fixes in the same area → one entry
  • Keep distinct items separate
  • Drop all Non-User items completely — they never appear in release notes or PR body
  • Internal items appear only as "Improvements" in the PR body (not in the title)

Read the full file on GitHub · 186 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 186 lines · 43 tokens per session scan A b7fc55eadade

Subscribe to this mod's changes

prepare-beta is a skill published in the GitHub repository Agent-Clubhouse/Clubhouse-Workshop (2 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 1,698 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.