markdown-lsp CLAUDE.md

markdown-lsp CLAUDE.md is an instructions file for coding agents from zircote/markdown-lsp. It costs 282 tokens per session, scanned A, a copy of lsp-tools CLAUDE.md, MIT.

Project instructions for markdown-lsp, a template repository for building Claude Code automations and MCP servers. They document the project goals, important files, coding conventions, and rules for adding tools or hooks.

In plain words
What is it for?
Use them when developing markdown-lsp, especially when changing its TypeScript MCP server, Claude Code commands, hooks, configuration, or project documentation.
Why use it?
They give a coding agent the project context needed to make consistent changes without overlooking configuration, documentation, safety, or portability requirements.

Instructions file

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 instructions/zircote/markdown-lsp/claude-md
Clone the repo
git clone --depth 1 https://github.com/zircote/markdown-lsp

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-lsp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zircote/markdown-lsp/claude-md.svg)](https://agentmods.dev/instructions/zircote/markdown-lsp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zircote/markdown-lsp/claude-md"><img src="https://agentmods.dev/badge/instructions/zircote/markdown-lsp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 282 This file is loaded in full into every session.
When invoked 282 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00282 $0.00282
Opus 5 $0.00141 $0.00141
Sonnet 5 $0.00056 $0.00056
Haiku 4.5 $0.00028 $0.00028

Measured 3d ago against content hash fbb4fa67ba4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

markdown-lsp CLAUDE.md 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.

Origin

This is a copy

100% identical to lsp-tools CLAUDE.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 41 lines

What it actually says

CLAUDE.md (project context)

This repository is a template for building Claude Code automations and MCP servers.

Repo goals

  • Be easy to fork.
  • Provide a sane default MCP server in TypeScript.
  • Provide examples of Claude Code commands and hooks.

Key files

  • .mcp.json: Claude Code MCP server configuration (project-scoped).
  • .claude/settings.json: Hook configuration.
  • .claude/commands/: Custom commands that show up as /....
  • .claude/hooks/: Hook scripts.
  • src/index.ts: MCP server entrypoint.

Development conventions

  • Prefer minimal diffs.
  • Keep scripts safe and portable.
  • Keep documentation in sync (README + skills files).

When adding tools

  • Use zod schemas.
  • Return text via { content: [{ type: "text", text: "..." }] }.
  • Avoid side effects by default; require explicit user intent for destructive operations.

When adding hooks

  • Hooks are configured in .claude/settings.json.
  • Keep hooks fast and deterministic.
  • Prefer blocking only high-confidence dangerous operations.

Docs:

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 · 41 lines · 282 tokens per session scan A fbb4fa67ba4d

Subscribe to this mod's changes

markdown-lsp CLAUDE.md is an instructions file published in the GitHub repository zircote/markdown-lsp (3 stars, last pushed 1mo ago), licensed MIT. It adds 282 tokens to every session, about $0.0014 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to lsp-tools CLAUDE.md, differing in 0 lines, and is treated as a copy.