converter-qa

converter-qa is a skill for Claude Code, Codex from fabioc-aloha/Alex_Skill_Mall. It costs 18 tokens per session (837 once invoked), scanned A, original, MIT.

A test harness for checking that document-conversion tools produce the expected files and structure. It includes checks for Word, email, Markdown linting, templates, navigation, and command-line options.

In plain words
What is it for?
Run regression, unit, smoke, structure, and output-format checks for converter modules such as Markdown-to-Word and Markdown-to-email.
Why use it?
It catches broken conversions and formatting changes after code updates, before a new version is released.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node .github/muscles/converter-qa.cjs.

Good fit Run regression, unit, smoke, structure, and output-format checks for converter modules such as Markdown-to-Word and Markdown-to-email.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/fabioc-aloha/Alex_Skill_Mall
agentmods
npx agentmods add skills/fabioc-aloha/alex_skill_mall/converter-qa

Made for: Claude Code, Codex.

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 converter-qa

README.md
[![agentmods](https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/converter-qa/github.svg)](https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/converter-qa)
Your own site
<a href="https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/converter-qa"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/converter-qa/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for converter-qa

Your own site · 80×15
<a href="https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/converter-qa"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/converter-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 837 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00018 $0.00837
Opus 5 $0.00009 $0.00418
Sonnet 5 $0.00004 $0.00167
Haiku 4.5 $0.00002 $0.00084

Measured 7d ago against content hash 36ed8585fa50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

converter-qa 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 7d 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.

plugins/converters/converter-qa/skills/converter-qa/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Converter QA Framework

Trust your converters -- 284 assertions prove they work

Test harness that validates all converter outputs: md-to-word regression tests, md-to-eml structure validation, shared module unit tests, file size bounds, and output format verification.

When to Use

  • After modifying any converter muscle or shared module
  • Before releasing a new version of the converter pipeline
  • When adding new features to md-to-word, md-to-eml, or shared modules
  • As part of the pre-publish quality gate

Test Suites

Suite Covers Assertions
Shared module tests All 8 shared modules (preprocessor, mermaid, config, etc.) ~120
md-to-word smoke End-to-end Word conversion with multiple style presets ~40
md-to-word OOXML Visual regression (XML structure, table styling) ~30
md-to-eml structure Email HTML, CID images, frontmatter mapping ~20
markdown-lint All 19 lint rules with positive and negative cases ~30
md-scaffold Template generation for all 5 template types ~15
nav-inject Navigation injection, dry-run, init ~10
CLI flag parsing All CLI flags for md-to-word (new flags) ~15
Lua filter syntax Pandoc Lua filter validation ~4

Usage

# Run all tests
node .github/muscles/converter-qa.cjs

# Run a specific suite
node .github/muscles/converter-qa.cjs --suite=word
node .github/muscles/converter-qa.cjs --suite=shared

# Verbose output (show passing tests)
node .github/muscles/converter-qa.cjs --verbose

Adding Tests

Tests use a minimal zero-dependency framework:

suite('My test suite', () => {
  assert(condition, 'description of what is being tested');
  skip('description of skipped test');  // for known issues
});

Quality Gate Integration

This muscle is part of the pre-publish quality gate:

  1. converter-qa.cjs runs all 284 assertions
  2. Zero failures required to pass
  3. Skips are tracked but don't block (used for environment-dependent tests)

Read the full file on GitHub · 111 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. 7d ago First seen · 111 lines · 18 tokens per session scan A 36ed8585fa50

Subscribe to this mod's changes

converter-qa is a skill published in the GitHub repository fabioc-aloha/Alex_Skill_Mall (4 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 837 once invoked, about $0.0001 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 2026-09-03.