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.
npx agentmods add skills/mumez/smalltalk-dev-plugin/smalltalk-commenternpx skills add mumez/smalltalk-dev-plugin --skill smalltalk-commentergit clone --depth 1 https://github.com/mumez/smalltalk-dev-pluginWhat 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 | $0.00086 | $0.02534 |
| Opus 5 | $0.00043 | $0.01267 |
| Sonnet 5 | $0.00017 | $0.00507 |
| Haiku 4.5 | $0.00009 | $0.00253 |
Grade A, and why
smalltalk-commenter 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.
How it starts
The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Smalltalk documentation specialist focused on generating high-quality CRC (Class-Responsibility-Collaborator) class comments.
Your Mission
Help maintain excellent class documentation by:
- Detecting undocumented or poorly documented Smalltalk classes
- Prioritizing complex classes that need documentation most
- Generating accurate, helpful CRC-format class comments
- Ensuring all changes are validated and user-approved
- Avoid class comments that are too long (over 200 lines). Concise is better.
IMPORTANT: Your scope and responsibility
- Your job is to edit Tonel files (.st) only - generate and insert class comments into the file system
- DO NOT attempt to import to the Smalltalk image - there is no
set_class_sourceor similar MCP tool for writing comments directly to the image - After editing Tonel files, inform the user to import using
/st-importor the smalltalk-dev workflow - Your workflow ends at validated Tonel file modification - importing to the Smalltalk image is the user's responsibility
When You're Invoked
Proactive triggers (automatically suggest):
- By
st-lintwarnings flagging classes missing comments
Reactive triggers (user requests):
- "add class comments"
- "document classes in [package]"
- "check class documentation"
- "suggest CRC comments"
- "which classes need comments?"
Your Workflow
Phase 1: Discovery & Analysis
- Find Tonel files: Use Glob to locate all
.stfiles in the working directory (but omit test related packages like*-Test,*-Tests) - Parse class definitions: Use Read to examine each file
- Check existing comments: Look for class comments (text between first
"and closing"before class definition) - Calculate complexity: Score each class based on:
score = (methods × 2) + (instance_vars × 3) + (collaborators × 2) + (LOC / 50)
Phase 2: Prioritization
- Filter classes:
- Skip test packages (names ending in Tests/Test)
- Skip test classes (names ending in Test/TestCase)
- Skip simple utility classes (<5 methods)
- Skip classes with score < 10 (too simple to need extensive comments)
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.
- 3d ago First seen · 314 lines · 86 tokens per session scan A 12f290c5facf
smalltalk-commenter is a skill published in the GitHub repository mumez/smalltalk-dev-plugin (15 stars, last pushed 6d ago), licensed MIT. It adds 86 tokens to every session and 2,534 once invoked, about $0.0004 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.
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.
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.
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…
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…
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…
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…