fix-markdown-linting

fix-markdown-linting is a command for Claude Code from basher83/agent-auditor. It costs 12 tokens per session (771 once invoked), scanned A, original, MIT.

A command that checks Markdown files for style errors and assigns fixes across the repository to separate subagents when useful.

In plain words
What is it for?
Use it to find and fix Markdown linting problems in one file or across many files, with parallel work for larger sets.
Why use it?
It removes the need to inspect every Markdown error and divide the repair work by hand.

Command for Claude Code

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 commands/basher83/agent-auditor/fix-markdown-linting
Clone the repo
git clone --depth 1 https://github.com/basher83/agent-auditor

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 fix-markdown-linting

README.md
[![agentmods](https://agentmods.dev/badge/commands/basher83/agent-auditor/fix-markdown-linting.svg)](https://agentmods.dev/commands/basher83/agent-auditor/fix-markdown-linting)
Your own site
<a href="https://agentmods.dev/commands/basher83/agent-auditor/fix-markdown-linting"><img src="https://agentmods.dev/badge/commands/basher83/agent-auditor/fix-markdown-linting.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 771 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 $0.00012 $0.00771
Opus 5 $0.00006 $0.00385
Sonnet 5 $0.00002 $0.00154
Haiku 4.5 $0.00001 $0.00077

Measured 3d ago against content hash 6ccdf0d9d07e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fix-markdown-linting 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.

.claude/commands/fix-markdown-linting.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fix Markdown Linting Errors

Intelligently distribute markdown linting fixes across parallel subagents based on discovered errors.

Workflow

Step 1: Discovery

Run the rumdl parser in summary mode to analyze errors:

rumdl check . 2>&1 | scripts/rumdl-parser.py --summary

This outputs clean JSON with just the essentials:

  • total_files: Number of files with errors
  • total_errors: Total error count
  • files: Array with file paths and error counts (sorted highest first, no detailed error info)

Step 2: Decide Distribution Strategy

Based on the total_files count from Step 1:

Decision criteria:

  • 0 files → Done, no action needed
  • 1 file → Fix directly (no subagents needed)
  • 2-5 files → Run parser with --distribute N where N = total_files (one subagent per file)
  • 6+ files → Run parser with --distribute 6 for balanced workload

Example for 6+ files:

rumdl check . 2>&1 | scripts/rumdl-parser.py --distribute 6

This adds a distribution array with balanced subagent assignments.

Step 3: Parallel Execution

Using the exact file paths from the JSON distribution, launch all subagents in a single message with multiple Task tool calls to maximize efficiency.

Step 4: Final Verification

After all subagents complete, verify the actual results:

rumdl check . 2>&1 | scripts/rumdl-parser.py --summary

Compare with Step 1 results:

  • Total errors before vs after
  • Files remaining with errors
  • Actual reduction achieved

This confirms the fixes were successful and identifies any remaining issues.

Instructions for Each Subagent

Each subagent receives:

Assignment: [FILE_PATH] or [LIST_OF_FILE_PATHS]

Task:

  1. Run rumdl check [FILE_PATH] to verify current errors
  2. Analyze the linting errors reported
  3. Fix ONLY formatting/linting issues (line length, blank lines, list formatting, etc.)
  4. DO NOT alter the semantic content of the file
  5. DO NOT modify YAML frontmatter if errors are reported there
  6. After fixing, run rumdl check [FILE_PATH] again to verify resolution
  7. Report what was fixed

Read the full file on GitHub · 118 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. 3d ago First seen · 118 lines · 12 tokens per session scan A 6ccdf0d9d07e

Subscribe to this mod's changes

fix-markdown-linting is a command published in the GitHub repository basher83/agent-auditor (5 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 771 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 2026-08-31.