agentmods.dev

md-anything CLAUDE.md

md-anything CLAUDE.md is an instructions file for coding agents from ojspace/md-anything. It costs 993 tokens per session, scanned A, original, MIT.

Project instructions and a runbook for md-anything, a command-line tool and MCP server that converts text files or web pages into Markdown. A runbook is a practical guide for running and checking a project.

In plain words
What is it for?
Use it to install dependencies, lint, build, test, run conversions, process folders of inputs, check capabilities, and configure MCP connections.
Why use it?
It gives coding agents the current commands, expected behavior, and error details needed to work with the project correctly.

Instructions file

not rated 49 5mo ago A scan 993 tokens original MIT
View the source file ojspace/md-anything
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/ojspace/md-anything/claude-md
Clone the repo
git clone --depth 1 https://github.com/ojspace/md-anything

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 md-anything CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ojspace/md-anything/claude-md.svg)](https://agentmods.dev/instructions/ojspace/md-anything/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ojspace/md-anything/claude-md"><img src="https://agentmods.dev/badge/instructions/ojspace/md-anything/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 993 This file is loaded in full into every session.
When invoked 993 The same file — it is already loaded in full.
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 $0.00993 $0.00993
Opus 5 $0.00496 $0.00496
Sonnet 5 $0.00199 $0.00199
Haiku 4.5 $0.00099 $0.00099

Measured 4d ago against content hash 87c92e6c2eb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

md-anything 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 4d 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.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Local runbook for md-anything.

What is actually shipped right now

  • CLI: mda
  • MCP server: md-anything-mcp
  • No shipped HTTP API surface

Quick start

git pull origin main
bun install
bun run lint
bun run build
bun run test:required
bun run src/cli.ts doctor

Core commands

# Help and examples
mda --help
mda examples

# Convert one input
mda tests/fixtures/sample.txt
mda convert tests/fixtures/sample.txt
mda convert "https://example.com/article"

# JSON output for agents/scripts
mda convert tests/fixtures/sample.txt --json

# Batch conversion
mda ingest tests/fixtures
mda ingest tests/fixtures -o ./output
mda ingest tests/fixtures -r -o ./output

# Capability report
mda doctor

# MCP setup
mda mcp install claude
mda mcp install cursor
mda mcp install windsurf

# Direct MCP server
md-anything-mcp

Important behavior notes

CLI shape

Both forms are intentionally supported:

  • bun run src/cli.ts convert <input>
  • bun run src/cli.ts <input>

If you run bun run src/cli.ts convert with no input:

  • stderr includes Missing input for convert command.
  • exit code is 1

Guided CLI errors

The CLI is expected to steer users toward the right command:

  • directory input points to mda ingest <path>
  • unknown input suggests mda --help or mda examples
  • weak extraction suggests mda doctor

Coverage lives in tests/integration/cli-ux.test.ts.

Ingest reality

Current ingest behavior is simple:

  • walks a folder
  • converts supported files
  • returns converted, skipped, failed, and per-doc metadata
  • supports -r and -o

It does not currently support source manifests, --graph, or --index.

MCP safety model

src/mcp.ts + src/mcp-support.ts enforce stricter rules than the CLI:

  • local paths must stay inside the current workspace root
  • only http / https URLs are allowed
  • private and localhost URLs are blocked by default
  • set MDA_MCP_ALLOW_PRIVATE_URLS=1 only when intentionally overriding that policy

Read the full file on GitHub · 170 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. 4d ago First seen · 170 lines · 993 tokens per session scan A 87c92e6c2eb0

Subscribe to this mod's changes

md-anything CLAUDE.md is an instructions file published in the GitHub repository ojspace/md-anything (49 stars, last pushed 5mo ago), licensed MIT. It adds 993 tokens to every session, about $0.0050 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.

Writing and docsai-agentsclaudecursordocument-processingmarkdownmcp
Related

Other instructions, from other repositories

easy-notion-mcp CLAUDE.md

Claude Code instructions for Grey-Iris/easy-notion-mcp, covering easy-notion-mcp, open source context, .meta/ publication policy (hybrid, 2026-07-02), standing priorities and commands.

Grey-Iris/easy-notion-mcp · 4,152 tokens

MistralDocAI-mcp AGENTS.md

AGENTS.md instructions for trsdn/MistralDocAI-mcp, covering agent instructions, what this repository is, what this repository is not, layout and setup.

trsdn/MistralDocAI-mcp · 1,552 tokens

GroupDocs.Comparison.Mcp AGENTS.md

AGENTS.md instructions for groupdocs-comparison/GroupDocs.Comparison.Mcp, covering agents.md — guide for ai coding agents, what this repo is, mcp tools exposed, folder layout and dependencies.

groupdocs-comparison/GroupDocs.Comparison.Mcp · 1,356 tokens

GroupDocs.Comparison.Mcp copilot-instructions.md

Copilot instructions for groupdocs-comparison/GroupDocs.Comparison.Mcp, covering run / install, or install as a global dotnet tool, or run via docker, mcp tools exposed (3) and building this repo.

groupdocs-comparison/GroupDocs.Comparison.Mcp · 1,029 tokens

CRUX-Compress AGENTS.md

Instructions for zotoio/CRUX-Compress, covering critical: crux notation, foundational crux rules (must follow), available agents, user input escalation — subagent protocol and repository-internal agents (crux-compress repo only).

zotoio/CRUX-Compress · 1,807 tokens

MistralDocAI-mcp copilot-instructions.md

Copilot instructions for trsdn/MistralDocAI-mcp: The instructions for this repository live in AGENTS.md. Read that file. It is tool-neutral and it is the only copy, so this file deliberately restates nothing.

trsdn/MistralDocAI-mcp · 47 tokens