agentmods.dev

verify-markdown-snippets

verify-markdown-snippets is a skill for Claude Code from jpablo/vibe-types. It costs 154 tokens per session (4,701 once invoked), scanned A, original, Apache-2.0.

A checker for code examples inside Markdown files. Markdown is a text format commonly used for documentation, and fenced code blocks are sections marked as examples in a specific language.

In plain words
What is it for?
Extracting and checking Python, Rust, Scala, TypeScript, and Lean 4 snippets against pinned project environments.
Why use it?
It finds syntax and type errors in documentation examples before readers copy broken code.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/jpablo/GitHub/vibe-types.

Part of the vibe-types plugin — 7 skills shipped together

not rated 43 +1 1mo ago A scan 154 tokens original Apache-2.0
View the source file jpablo/vibe-types
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add jpablo/vibe-types
Claude Code
/plugin install vibe-types

Made for: Claude Code.

Or install vibe-types, the plugin that ships this one along with the rest of its 7 skills.

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 verify-markdown-snippets

README.md
[![agentmods](https://agentmods.dev/badge/skills/jpablo/vibe-types/verify-markdown-snippets.svg)](https://agentmods.dev/skills/jpablo/vibe-types/verify-markdown-snippets)
Your own site
<a href="https://agentmods.dev/skills/jpablo/vibe-types/verify-markdown-snippets"><img src="https://agentmods.dev/badge/skills/jpablo/vibe-types/verify-markdown-snippets.svg" alt="Measured on agentmods" height="20"></a>
Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,701 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 5.1 $0.00154 $0.04701
Opus 5 $0.00077 $0.02351
Sonnet 5 $0.00031 $0.00940
Haiku 4.5 $0.00015 $0.00470

Measured 6d ago against content hash 52c885984bef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

verify-markdown-snippets 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 6d ago.

The scan reads SKILL.md. This mod also ships 11 executable files (scripts/extract_snippets.py, scripts/match_expected_errors.py, scripts/probe_flags.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugin/skills/verify-markdown-snippets/SKILL.md · 275 lines

How it starts

The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.

verify-markdown-snippets

What this skill does

Given a markdown file, for every fenced code block:

  1. Extract the snippet, its starting line number in the source file, and the language tag on the fence.
  2. Verify it with the language's checker, always pinned to the reference project under projects/:
    • Python (```python): pure-syntax check with ast.parse, then pyright from the venv in projects/python-project/.
    • Rust (```rust): cargo check as a temporary bin target inside projects/rust-project/ (pinned toolchain + Cargo.toml dependencies).
    • Scala (```scala): scala-cli compile pinned to the Scala version and libraryDependencies parsed from projects/scala-project/build.sbt (cats, cats-effect, zio, iron available to snippets).
    • TypeScript (```typescript): tsc --noEmit --strict from the pinned compiler in projects/typescript-project/. Uses lib: ES2022 with no DOM (plus a small console shim) so domain type names in the docs don't collide with browser globals.
    • Lean 4 (```lean): lake env lean against the pinned toolchain in projects/lean-project/ (lean-toolchain). Each snippet is type-checked as an ordinary .lean compilation unit — top-level def/inductive/example/#check are valid as-is, so no wrapping is needed. #eval/#check info output is ignored; only error: diagnostics fail a snippet.
  3. Produce a report — markdown for humans, JSON for tooling — pointing at the exact fence line and showing verbatim error output from the checker.

The point is to make documentation code trustworthy: readers should be able to copy a snippet out of a doc and have it work. When that's not the case, we want a fast, automated way to find every offender.

Why pyright and not execution

The instinct is to actually run the code and see what explodes. Don't. Executing arbitrary snippets from a markdown file is slow, has side effects, and still won't catch things that fail in only some call sites.

Read the full file on GitHub · 275 lines

Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 275 lines · 154 tokens per session scan A 52c885984bef

Subscribe to this mod's changes

verify-markdown-snippets is a skill published in the GitHub repository jpablo/vibe-types (43 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 154 tokens to every session and 4,701 once invoked, about $0.0008 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.

TestingWriting and docs
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens