markplane CLAUDE.md

markplane CLAUDE.md is an instructions file for coding agents from zerowand01/markplane. It costs 826 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Markplane, a project-management system that uses Markdown files as its source of truth and provides Rust command-line and web interfaces.

In plain words
What is it for?
Use them when building, testing, linting, installing, or changing the Markplane Rust workspace and its optional React web interface.
Why use it?
They give coding agents the project's architecture, required tool versions, build and test commands, and repository conventions.

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/zerowand01/markplane/claude-md
Clone the repo
git clone --depth 1 https://github.com/zerowand01/markplane

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 markplane CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zerowand01/markplane/claude-md.svg)](https://agentmods.dev/instructions/zerowand01/markplane/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zerowand01/markplane/claude-md"><img src="https://agentmods.dev/badge/instructions/zerowand01/markplane/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 826 This file is loaded in full into every session.
When invoked 826 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 $0.00826 $0.00826
Opus 5 $0.00413 $0.00413
Sonnet 5 $0.00165 $0.00165
Haiku 4.5 $0.00083 $0.00083

Measured 3d ago against content hash fbc3537a2bfd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

markplane 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.

CLAUDE.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Markplane is an AI-native, markdown-first project management system. "Mark" (markdown) + "plane" (control plane). The repo itself is the project manager — no database, no SaaS. Files are the source of truth, git is the changelog.

Tech stack: Rust CLI binary with integrated MCP server (markplane mcp subcommand) wrapping a shared core library. React + Tailwind web UI via markplane serve.

Build & Test

Requires Rust 1.93.0+ (edition 2024). Web UI also requires Node.js 18+.

cargo build --workspace              # Build all crates
cargo test --workspace               # Run all tests
cargo clippy --workspace             # Lint (must be warning-free)

Web UI (optional):

cd crates/markplane-web/ui && npm install && npm run build   # Build frontend
cargo install --path crates/markplane-cli --features embed-ui # Single binary with embedded UI

After code changes, cargo install --path crates/markplane-cli to update the local markplane binary.

Workspace Structure

Crate Type Role
markplane-core Library Data models, CRUD, sync, references, context generation
markplane-cli Binary (markplane) CLI commands, MCP server (markplane mcp), web server (markplane serve)
markplane-web/ui Next.js app React + Tailwind frontend (static export, optionally embedded via rust-embed)

Key Conventions

  • Error handling: thiserror/MarkplaneError in core, anyhow in CLI, Result<String, String> in MCP tool handlers
  • No regex: Reference extraction ([[ID]]) uses manual byte scanning
  • serde_yaml 0.9: Deprecated but kept — serde_yml is too immature
  • Integration tests: Use cargo_bin_cmd!() macro (not deprecated Command::cargo_bin())
  • Derived files: INDEX.md and .context/ are gitignored within .markplane/ — fully regenerated by markplane sync
  • Auto-sync: Runs on markplane init, markplane mcp startup, and markplane serve startup
  • ID system: {PREFIX}-{RANDOM} with 5-char alphanumeric suffix (no sequential counters)

Read the full file on GitHub · 67 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 · 67 lines · 826 tokens per session scan A fbc3537a2bfd

Subscribe to this mod's changes

markplane CLAUDE.md is an instructions file published in the GitHub repository zerowand01/markplane (181 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 826 tokens to every session, about $0.0041 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.