markdown-quality-fixer

markdown-quality-fixer is an agent for Claude Code from timohaa/scopewalker-mcp. It costs 28 tokens per session (437 once invoked), scanned A, original, MIT.

A helper that checks changed Markdown files—plain-text documents commonly used for README files and documentation—and fixes style warnings and table layout.

In plain words
What is it for?
Use it after creating or editing .md files to find changed files, apply automatic Markdown fixes, format tables, and report issues that still need manual work.
Why use it?
It removes repetitive cleanup before commits and helps keep documentation consistent.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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/timohaa/scopewalker-mcp/markdown-quality-fixer
Clone the repo
git clone --depth 1 https://github.com/timohaa/scopewalker-mcp

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-quality-fixer

README.md
[![agentmods](https://agentmods.dev/badge/agents/timohaa/scopewalker-mcp/markdown-quality-fixer.svg)](https://agentmods.dev/agents/timohaa/scopewalker-mcp/markdown-quality-fixer)
Your own site
<a href="https://agentmods.dev/agents/timohaa/scopewalker-mcp/markdown-quality-fixer"><img src="https://agentmods.dev/badge/agents/timohaa/scopewalker-mcp/markdown-quality-fixer.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 437 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 $0.00028 $0.00437
Opus 5 $0.00014 $0.00218
Sonnet 5 $0.00006 $0.00087
Haiku 4.5 $0.00003 $0.00044

Measured yesterday against content hash 83afc4be83ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

markdown-quality-fixer 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 yesterday.

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-quality-fixer.md · 50 lines

What it actually says

Markdown Quality Fixer Agent

Make every target Markdown file pass markdownlint and table-formatting checks.

Workflow

1. Identify Target Files

git status --porcelain

Filter for .md files that are new (??, A) or modified (M). If no specific files are changed, process all .md files in the project.

2. Process All Target Files in One Batch

Both tools accept multiple file paths in a single invocation. Run the mechanical steps as a single Bash call. Pass the step 1 target list as literal arguments. Zsh does not word-split an unquoted $FILES variable, so it would pass the whole list as one path:

npx markdownlint --fix README.md TOOLS.md docs/patterns.md          # auto-fix
npx markdown-table-formatter README.md TOOLS.md docs/patterns.md    # align tables
npx markdownlint README.md TOOLS.md docs/patterns.md                # what remains
  1. Auto-fix, format tables, and check remaining: the call above.
  2. Manual fix: resolve the issues the final markdownlint still reports and auto-fix could not handle, editing each file it names.
  3. Final verify: re-run the same npx markdownlint <all files> once; a single call covers every file you edited and must produce zero warnings.

Invoke a command on one file alone only to diagnose a single stubborn warning.

3. Project Config

Respect the rules disabled in .markdownlint.json (read it first); do not fix issues for disabled rules.

Critical Rules

  • Preserve semantic meaning: do not change the content, only fix formatting
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. yesterday Changed · -8 tokens per session 83afc4be83ff
  2. 5d ago First seen · 50 lines · 36 tokens per session scan A 82140419f14d

Subscribe to this mod's changes

markdown-quality-fixer is an agent published in the GitHub repository timohaa/scopewalker-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 437 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.