st-lint

st-lint is a skill for Claude Code, Codex from mumez/smalltalk-dev-plugin. It costs 52 tokens per session (882 once invoked), scanned A, original, MIT.

A code-quality checker for Tonel files, the file format Smalltalk uses to store packages and classes. It checks `.st` source files for Smalltalk best practices before they are imported into a Pharo or Squeak image.

In plain words
What is it for?
Use it before importing Smalltalk code, after editing `.st` files, or when diagnosing unexpected behavior in a package.
Why use it?
It can catch source and style problems before import, including issues that might otherwise cause confusing behavior. It also checks whether required project metadata is present and warns when it is missing.

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-lint
Any agent
npx skills add mumez/smalltalk-dev-plugin --skill st-lint
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-lint

README.md
[![agentmods](https://agentmods.dev/badge/skills/mumez/smalltalk-dev-plugin/st-lint.svg)](https://agentmods.dev/skills/mumez/smalltalk-dev-plugin/st-lint)
Your own site
<a href="https://agentmods.dev/skills/mumez/smalltalk-dev-plugin/st-lint"><img src="https://agentmods.dev/badge/skills/mumez/smalltalk-dev-plugin/st-lint.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 882 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 $0.00052 $0.00882
Opus 5 $0.00026 $0.00441
Sonnet 5 $0.00010 $0.00176
Haiku 4.5 $0.00005 $0.00088

Measured 4d ago against content hash 940ef49fe38e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

st-lint 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 4d 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-lint/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lint Tonel Files

Validate Tonel .st files for Smalltalk best practices before importing to the Smalltalk image.

When to Use

  • Before every /st-import — lint catches issues that would silently corrupt the image
  • After editing .st files — confirm no style regressions
  • When import fails with unexpected behavior — lint may reveal the root cause

Step 1: Check Meta Files (manual — MCP cannot validate these)

Before linting, verify required Tonel meta files exist:

File Location Required
.project repo root
src/.properties src/ directory
package.st each package directory

If any are missing, warn the user, suggest /st-setup-project, and continue linting — lint results are still useful even when meta files are absent, since the linter operates on .st file syntax independently.

Expected src/.properties content:

{
	#format : #tonel
}

Step 2: Collect .st Files

Resolve the target to a list of absolute paths:

  • Single file (src/MyPackage/MyClass.st): use directly, skip if it is package.st
  • Package directory (src/MyPackage): Glob **/*.st, exclude package.st
  • src root (src): Glob **/*.st across all packages, exclude package.st

Always convert to absolute paths before passing to the MCP tool.

Step 3: Lint Each File

Call mcp__smalltalk-validator__lint_tonel_smalltalk_from_file with the absolute path, one file at a time.

Step 4: Report Results

Show a summary per file:

src/MyPackage/MyClass.st — ✅ clean
src/MyPackage/AnotherClass.st — ⚠️ 2 warnings
  • [warning] Method #doSomething has no comment
  • [warning] Temporary variable 'x' shadows outer scope
src/MyPackage/BrokenClass.st — ❌ 1 error
  • [error] Syntax error near ']'

Exit status semantics:

Result Meaning Action
0 — clean No issues Proceed to import
1 — warnings only Style issues Proceed to import, consider fixing
2 — errors found Syntax/structural errors Fix before importing

Read the full file on GitHub · 88 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. 4d ago First seen · 88 lines · 52 tokens per session scan A 940ef49fe38e

Subscribe to this mod's changes

st-lint is a skill published in the GitHub repository mumez/smalltalk-dev-plugin (15 stars, last pushed 8d ago), licensed MIT. It adds 52 tokens to every session and 882 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.