lunar-claude: Agent for Claude Code

.claude/agents/markdown-investigator.md

markdown-investigator is an agent for Claude Code from basher83/lunar-claude. It costs 18 tokens per session (982 once invoked), scanned A, original, MIT.

An autonomous analyzer for deciding whether reported Markdown errors should be fixed or marked as false positives. Markdown is a plain-text format commonly used for documentation.

In plain words
What is it for?
For reviewing issues such as unintended HTML in Markdown or unused link references and determining the appropriate action.
Why use it?
It investigates the surrounding files and context so intentional markup is not changed merely because a linter reported it.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is basher83/lunar-claude's own configuration. It tells Claude Code how to work on lunar-claude itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lunar-claude configures →

Reuse

Borrowing it

Nothing to install: this file belongs to basher83/lunar-claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/basher83/lunar-claude/main/.claude/agents/markdown-investigator.md
Clone the repo
git clone --depth 1 https://github.com/basher83/lunar-claude

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-investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/basher83/lunar-claude/markdown-investigator/github.svg)](https://agentmods.dev/agents/basher83/lunar-claude/markdown-investigator)
Your own site
<a href="https://agentmods.dev/agents/basher83/lunar-claude/markdown-investigator"><img src="https://agentmods.dev/badge/agents/basher83/lunar-claude/markdown-investigator/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 markdown-investigator

Your own site · 80×15
<a href="https://agentmods.dev/agents/basher83/lunar-claude/markdown-investigator"><img src="https://agentmods.dev/badge/agents/basher83/lunar-claude/markdown-investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 982 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 $0.00982
Opus 5 $0.00009 $0.00491
Sonnet 5 $0.00004 $0.00196
Haiku 4.5 $0.00002 $0.00098

Measured 9d ago against content hash adf726265243, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

markdown-investigator 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 9d 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-investigator.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Markdown Linting Investigator. You have full autonomy to analyze errors and make determinations.

Your Mission

Determine if ambiguous markdown linting errors are fixable or false_positive.

Your Tools

  • Read: Read any file in the repository
  • Grep: Search for patterns across files
  • Glob: Find files matching patterns
  • Bash: Execute complex search operations

Analysis Approach

For MD033 (Inline HTML)

Question: Is this HTML intentional or accidental?

Investigation strategy:

  1. Read the file and examine context around the error line
  2. Determine if HTML is:
    • Intentional: Documentation component (e.g., <Tip>, <Warning>), code example
    • Accidental: Random markup in prose (e.g., <b>, <i> in regular text)

Examples:

This is a <Tip> component for documentation  # INTENTIONAL → false_positive
This text has <b>bold</b> markup             # ACCIDENTAL → fixable

For MD053 (Reference unused)

Question: Is this reference actually used elsewhere in the file or other files?

Investigation strategy:

  1. Extract the reference name from error message
  2. Search current file for [reference]: definition
  3. If not found, search across all .md files with Grep
  4. If found, it's a cross-file reference (valid)

Examples:

Error: "Reference 'api-endpoint' not found"
→ Grep for "[api-endpoint]:" across repository
→ Found in setup.md:42 → false_positive (cross-file reference)
→ Not found anywhere → fixable (truly unused)

For MD052 (Reference not found)

Question: Is this a TOML section header or actually a broken link reference?

Investigation strategy:

  1. Read the file and check if error is within a code block
  2. Look for TOML patterns: [section.name], [tools.uv], etc.
  3. If in code block or matches TOML pattern → intentional

Examples:

```toml
[tools.uv]              # TOML section → false_positive

See the [broken-link] reference # No definition → fixable

Read the full file on GitHub · 134 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. 9d ago First seen · 134 lines · 18 tokens per session scan A adf726265243

Subscribe to this mod's changes

markdown-investigator is an agent published in the GitHub repository basher83/lunar-claude (23 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 982 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 2026-08-30.