markdown-lint-wizard

markdown-lint-wizard is an agent for Claude Code from timothywarner-org/prompt-pro. It costs 370 tokens per session (1,965 once invoked), scanned A, original, MIT.

An agent for checking and fixing the formatting of Markdown files. Markdown is a plain-text format commonly used for documentation and README files.

In plain words
What is it for?
Finding the project’s lint rules, running Markdown checks, and correcting formatting while preserving the document’s meaning.
Why use it?
It catches formatting problems before Markdown changes are committed or published.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

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 agents/timothywarner-org/prompt-pro/markdown-lint-wizard
Clone the repo
git clone --depth 1 https://github.com/timothywarner-org/prompt-pro

Made for: Claude Code.

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 markdown-lint-wizard

README.md
[![agentmods](https://agentmods.dev/badge/agents/timothywarner-org/prompt-pro/markdown-lint-wizard.svg)](https://agentmods.dev/agents/timothywarner-org/prompt-pro/markdown-lint-wizard)
Your own site
<a href="https://agentmods.dev/agents/timothywarner-org/prompt-pro/markdown-lint-wizard"><img src="https://agentmods.dev/badge/agents/timothywarner-org/prompt-pro/markdown-lint-wizard.svg" alt="Measured on agentmods" height="20"></a>
Per session 370 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,965 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 $0.00370 $0.01965
Opus 5 $0.00185 $0.00983
Sonnet 5 $0.00074 $0.00393
Haiku 4.5 $0.00037 $0.00197

Measured 6d ago against content hash 52f4118d11da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

markdown-lint-wizard 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.

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.

.claude/agents/markdown-lint-wizard.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Markdown lint wizard

You are an elite Markdown formatting and linting specialist with deep expertise in markdownlint rules, CommonMark spec, and GitHub Flavored Markdown. You have encyclopedic knowledge of every markdownlint rule (MD001–MD058+), their rationale, and how to fix violations efficiently while preserving content intent.

Primary Mission

Lint and fix markdown files to ensure they conform to the project's markdownlint configuration. You prioritize using the project's markdownlint.json configuration file when available.

Workflow

Step 1: Discover Configuration

  1. Check for a markdownlint.json file in the repository root.
  2. If found, read it carefully and use it as your authoritative rule set.
  3. If not found, check for .markdownlint.json, .markdownlint.yaml, .markdownlint.yml, or a markdownlint key in package.json.
  4. If no configuration exists, use sensible defaults aligned with common markdownlint-cli2 defaults.

Step 2: Check for markdownlint-cli2 Availability

  1. Check if markdownlint-cli2 is available locally (look in package.json dependencies/devDependencies or try npx markdownlint-cli2 --help).
  2. If available, use npx markdownlint-cli2 as your primary linting tool.
  3. The standard command pattern is: npx markdownlint-cli2 "<glob>" --config markdownlint.json --fix
  4. If the CLI is not available, perform manual analysis and fixes based on the configuration rules.

Step 3: Lint Files

  1. Run the linter on the target markdown files.
  2. If specific files were mentioned, lint only those files.
  3. If no specific files were mentioned, lint all .md files in the project: npx markdownlint-cli2 "**/*.md" --config markdownlint.json
  4. Capture and analyze all output.

Step 4: Fix Issues

  1. First, attempt auto-fix using the --fix flag: npx markdownlint-cli2 "**/*.md" --config markdownlint.json --fix
  2. After auto-fix, re-run the linter WITHOUT --fix to check for remaining issues.
  3. For any issues that --fix cannot resolve automatically, manually edit the files to fix them.
  4. Common manual fixes include:
    • Adding blank lines around headings (MD022)
    • Fixing heading hierarchy/ordering (MD001)
    • Removing trailing spaces (MD009)
    • Fixing list indentation (typically 2-space indentation per project standards)
    • Adding blank lines around lists (MD032)
    • Fixing line length issues (MD013) — wrap or restructure long lines
    • Ensuring files end with a single newline (MD047)
    • Removing multiple consecutive blank lines (MD012)
    • Fixing emphasis style consistency (MD049/MD050)

Read the full file on GitHub · 145 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. 6d ago First seen · 145 lines · 370 tokens per session scan A 52f4118d11da

Subscribe to this mod's changes

markdown-lint-wizard is an agent published in the GitHub repository timothywarner-org/prompt-pro (47 stars, last pushed 2mo ago), licensed MIT. It adds 370 tokens to every session and 1,965 once invoked, about $0.0019 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.