What is private-journal-mcp CLAUDE.md?

Repository instructions for an AI coding agent working on a private journaling server for Claude. They explain the project structure and list commands for building, testing, watching tests, linting, formatting, and starting the server.

Use them when modifying the journaling server, its TypeScript files, journal storage, search tools, or development commands.

They provide the project’s expected workflow and architecture in one place. This reduces guesswork when making changes or checking whether they work.

How obra/private-journal-mcp configures Claude Code

About the project

obra/private-journal-mcp is an MCP server that gives Claude a local journal for recording and searching thoughts, reflections, notes, and insights. It is intended for private personal and project journaling, with semantic search performed on the user's machine. The catalogue instruction helps coding agents use its journaling workflow.

obra/private-journal-mcp · 465 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to obra/private-journal-mcp. 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/obra/private-journal-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/obra/private-journal-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/obra/private-journal-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/obra/private-journal-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/obra/private-journal-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/obra/private-journal-mcp/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/obra/private-journal-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/obra/private-journal-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 755 This file is loaded in full into every session.

When invoked 755 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00755	$0.00755
Opus 5.5	$0.00302	$0.00302
Sonnet 5.5	$0.00151	$0.00151
Haiku 4.5	$0.00076	$0.00076

Measured 2mo ago against content hash 71721f8ac915, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

private-journal-mcp 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 2mo 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 · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 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.

Common Development Commands

# Build the project
npm run build

# Run tests
npm test

# Run tests in watch mode
npm run test:watch

# Development mode with TypeScript watcher
npm run dev

# Lint the code
npm run lint

# Format the code
npm run format

# Start the server
npm start

# Run a single test file
npx jest tests/journal.test.ts

Architecture Overview

This is an MCP (Model Context Protocol) server that provides Claude with private journaling capabilities. The architecture consists of:

Core Components:

src/index.ts - CLI entry point with intelligent path resolution for journal storage
src/server.ts - MCP server using stdio transport with private journaling and search tools
src/journal.ts - File system operations for timestamped markdown entries
src/types.ts - TypeScript interfaces for the domain model

Key Architecture Patterns:

Path Resolution Strategy: PRIVATE_JOURNAL_PATH env var overrides all resolution; otherwise falls back through CWD → HOME → temp directories, avoiding system roots
Timestamped Storage: Uses YYYY-MM-DD/HH-MM-SS-μμμμμμ.md structure with microsecond precision
YAML Frontmatter: Each entry includes structured metadata (title, ISO date, Unix timestamp)
MCP Tool Pattern: Tool registration with schema validation and error handling

File Organization:

Project journals: .private-journal/ in project root for project-specific notes
Personal journals: ~/.private-journal/ for cross-project personal thoughts
Daily structure: YYYY-MM-DD/HH-MM-SS-μμμμμμ.md with microsecond precision
Search index: .embedding files alongside each journal entry for semantic search
TypeScript compilation to dist/ for production
Jest tests in tests/ directory with comprehensive file system mocking

MCP Integration Details

The server provides comprehensive journaling and search capabilities through these tools:

Read the full file on GitHub · 81 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.

2mo ago First seen · 81 lines · 755 tokens per session scan A 71721f8ac915

Subscribe to this mod's changes

private-journal-mcp CLAUDE.md is an instructions file published in the GitHub repository obra/private-journal-mcp (465 stars, last pushed 2mo ago), licensed MIT. It adds 755 tokens to every session, about $0.0030 per session on Opus 5.5. 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.

private-journal-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
private-journal-mcp CLAUDE.mdobra/private-journal-mcp	Instructions file	465	2mo ago	MIT	A	755	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

private-journal-mcp: Instructions file for Claude Code