A startup routine for Smalltalk development in Pharo or Squeak, which are environments for writing and running Smalltalk code. It checks the project and connection to the Smalltalk image, then explains the available workflow.

Use it when beginning a Smalltalk session, checking the development setup, or orienting yourself to the commands and project workflow.

It catches missing project structure or an unavailable image connection before development begins. It also points to project setup when the workspace is not ready.

st-init — Skill by mumez

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/mumez/smalltalk-dev-plugin/st-init

Any agent

npx skills add mumez/smalltalk-dev-plugin --skill st-init

Clone the repo

git clone --depth 1 https://github.com/mumez/smalltalk-dev-plugin

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,304 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00072	$0.01304
Opus 5	$0.00036	$0.00652
Sonnet 5	$0.00014	$0.00261
Haiku 4.5	$0.00007	$0.00130

Measured 2d ago against content hash cd1c691fef3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

st-init scanned grade C with 2 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 2d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl https://get.pharo.org | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl https://get.pharo.org | bash

skills/st-init/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Initialize Smalltalk Development Session

Start a Smalltalk (Pharo or Squeak) development session: verify project structure, confirm the Smalltalk image connection, and orient to the development workflow.

Initialization Sequence

1. Check Project Structure

if [ ! -f ".project" ] && [ ! -d "src" ]; then
  echo "No Smalltalk project structure detected"
fi

✅ .project OR src/ found → continue
⚠️ Neither found → recommend smalltalk-dev:st-setup-project skill

If no project exists, offer to create one:

⚠️  No Smalltalk project structure detected in current directory.

Use /st-setup-project MyProjectName to set up:
  • .project configuration file
  • src/ directory with package structure
  • BaselineOf class and Core/Tests packages

Would you like to run /st-setup-project now?

User says yes: Invoke smalltalk-dev:st-setup-project skill, then continue with steps 2–4.
User says no / continue anyway: Proceed directly to step 2 (load smalltalk-developer) without project setup. Note in the status report that project structure is missing.

2. Load smalltalk-developer Skill

Use the Skill tool to load smalltalk-dev:smalltalk-developer. This activates the full development workflow guidance.

3. Verify Smalltalk Image Connection

Run Smalltalk version via eval:

mcp__smalltalk-interop__eval: 'Smalltalk version'

✅ Returns version string → connected, proceed
❌ Fails or times out → follow Connection Setup below

4. Confirm Ready

Report status to user:

✅ Smalltalk image connected: Pharo X.Y (...) [or Squeak X.Y (...)]
✅ smalltalk-developer skill loaded
📋 Development workflow: Edit → Lint → Import → Test

Connection Setup

If the Smalltalk image is not connected, check Docker availability first:

docker --version

Docker Setup (Recommended, Pharo only)

Generate compose.yml in the project root:

services:
  sis-pharo:
    image: mumez/smalltalk-interop-docker
    ports:
      - "5900:5900"
      - "6901:6901"
      - "8086:8086"
    environment:
      SIS_PORT: 8086
    volumes:
      - /tmp:/root/screenshots
      - .:/root/repos

Read the full file on GitHub · 180 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.

2d ago First seen · 180 lines · 72 tokens per session scan C cd1c691fef3e

Subscribe to this mod's changes

st-init is a skill published in the GitHub repository mumez/smalltalk-dev-plugin (15 stars, last pushed 6d ago), licensed MIT. It adds 72 tokens to every session and 1,304 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Languages claude-code marketplace mcp pharo-smalltalk plugin smalltalk

exec

Execute plan tasks sequentially using subagents. Use when user says 'exec', 'execute plan', 'run plan', or wants to implement a plan file task by task with isolated subagents.

umputun/cc-thingz · 41 tokens

pr

Comprehensive PR/issue review - analyzes architecture, tests, identifies unrelated changes mixed in, drafts review comment or issue comment. Use when user asks to review a PR, check a PR, look at PR changes, or comment on an issue.

umputun/cc-thingz · 51 tokens

backlog

Read, work, and maintain a Git repo's deferred-work items in docs/backlog/, one file per item. Use when the user says "backlog", "check backlog", "what's on my backlog", "work the backlog", "address the backlog", "add to backlog", "clean up backlog", or when a review or task produced items that are real but not being…

umputun/cc-thingz · 96 tokens

ask-codex

Consult OpenAI Codex for investigation, debugging, or code review. Use when user explicitly asks to "ask codex", "check with codex", "codex review", or as a last resort when stuck after 4+ failed attempts at debugging, investigation, or bug fix and completely out of ideas. Codex is slow (2-5 min), so only escalate…

umputun/cc-thingz · 103 tokens

clarify

This skill should be used when user appears confused, frustrated, or shows misalignment between expectations and reality. Triggers on phrases like "I don't understand", "this doesn't make sense", "confused", "wait, shouldn't it...", "why is this happening", "I thought X did Y", contradictory statements, or frustration…

umputun/cc-thingz · 91 tokens

brainstorm

Use before any creative work or significant changes. Activates on "brainstorm", "let's brainstorm", "deep analysis", "analyze this feature", "think through", "help me design", "explore options for", or when user asks for thorough analysis of changes, features, or architectural decisions. Guides collaborative dialogue…

umputun/cc-thingz · 87 tokens

st-init