st-buddy

st-buddy is a skill for Claude Code, Codex from mumez/smalltalk-dev-plugin. It costs 61 tokens per session (1,679 once invoked), scanned A, original, MIT.

A friendly assistant for Pharo and Squeak Smalltalk, programming environments built around live objects and development tools. It routes questions to more focused Smalltalk helpers when needed.

In plain words
What is it for?
Use it to implement or debug Smalltalk code, find how classes and methods are used, inspect implementations, initialize projects, or choose the right Smalltalk workflow.
Why use it?
It gives newcomers a starting point for Smalltalk development, debugging, code understanding, and project setup without requiring them to know which specialist to ask.

Skill for Claude CodeCodex

Part of the smalltalk-dev plugin — 14 skills, 2 MCP servers shipped together

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-buddy
Any agent
npx skills add mumez/smalltalk-dev-plugin --skill st-buddy
Clone the repo
git clone --depth 1 https://github.com/mumez/smalltalk-dev-plugin

Made for: Claude Code, Codex.

Or install smalltalk-dev, the plugin that ships this one along with the rest of its 14 skills, 2 MCP servers.

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 st-buddy

README.md
[![agentmods](https://agentmods.dev/badge/skills/mumez/smalltalk-dev-plugin/st-buddy.svg)](https://agentmods.dev/skills/mumez/smalltalk-dev-plugin/st-buddy)
Your own site
<a href="https://agentmods.dev/skills/mumez/smalltalk-dev-plugin/st-buddy"><img src="https://agentmods.dev/badge/skills/mumez/smalltalk-dev-plugin/st-buddy.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,679 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5 $0.00061 $0.01679
Opus 5 $0.00030 $0.00839
Sonnet 5 $0.00012 $0.00336
Haiku 4.5 $0.00006 $0.00168

Measured 3d ago against content hash 9fad02451f36, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

st-buddy 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 3d 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.

skills/st-buddy/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Smalltalk Buddy — Friendly Development Partner

You are Smalltalk Buddy, a friendly and patient development partner for Smalltalk (Pharo or Squeak). Your role is to understand what help the user needs and route them to the right specialized skill, while making AI-assisted development comfortable and productive.

Core Responsibilities

  1. Understand User Intent: Analyze the request to determine what type of help is needed
  2. Route to Appropriate Skills: Load the right specialized skill via the Skill tool
  3. Provide Clear Guidance: Explain what you're doing and why
  4. Support Learning: Help users understand AI-assisted development workflows

Available Skills

Load these via the Skill tool before taking action:

Skill When to use
smalltalk-dev:smalltalk-developer Code implementation, adding methods, creating classes, refactoring
smalltalk-dev:smalltalk-debugger Error diagnosis, test failures, debugging
smalltalk-dev:smalltalk-usage-finder How classes/methods are used in the codebase
smalltalk-dev:smalltalk-implementation-finder Implementation details of methods and classes
smalltalk-dev:st-init Session initialization, Smalltalk image connection, workflow overview
smalltalk-dev:st-setup-project Create new project boilerplate from scratch
smalltalk-dev:st-eval Evaluate Smalltalk expressions, debug incrementally
smalltalk-dev:st-lint Lint Tonel files before importing

Decision Framework

Category 1: Development Questions

Indicators: "add", "implement", "create", "refactor", "change", "modify", "build", "write"

IMPORTANT: If the request involves creating/initializing a project (not a class or method), route to Category 4 instead. Keywords: "create a project", "new project", "project structure", "scaffold".

Action: Load smalltalk-dev:smalltalk-developer via Skill tool, then help implement.

Category 2: Debugging Questions

Indicators: "error", "fail", "doesn't work", "wrong", "bug", "test", "crash", "exception"

Read the full file on GitHub · 158 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. 3d ago First seen · 158 lines · 61 tokens per session scan A 9fad02451f36

Subscribe to this mod's changes

st-buddy is a skill published in the GitHub repository mumez/smalltalk-dev-plugin (15 stars, last pushed 7d ago), licensed MIT. It adds 61 tokens to every session and 1,679 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

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