worklog-mcp CLAUDE.md

worklog-mcp CLAUDE.md is an instructions file for Claude Code from kwrkb/worklog-mcp. It costs 1,076 tokens per session, scanned B, original, MIT.

A project instruction file for worklog-mcp, a small server that stores searchable work notes in Markdown files for AI assistants.

In plain words
What is it for?
Use it when developing, configuring, or maintaining the worklog-mcp project.
Why use it?
It gives agents the project’s design, file locations, setup commands, and storage rules before they change the code.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

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/kwrkb/worklog-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/kwrkb/worklog-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.

agentmods badge for worklog-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kwrkb/worklog-mcp/claude-md.svg)](https://agentmods.dev/instructions/kwrkb/worklog-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kwrkb/worklog-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kwrkb/worklog-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,076 This file is loaded in full into every session.
When invoked 1,076 The same file — it is already loaded in full.
Security scan B 1 finding. 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 5.1 $0.01076 $0.01076
Opus 5 $0.00538 $0.00538
Sonnet 5 $0.00215 $0.00215
Haiku 4.5 $0.00108 $0.00108

Measured 5d ago against content hash 774e7b3b0251, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

worklog-mcp CLAUDE.md scanned grade B with 1 finding 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 5d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

### Claude Code (~/.claude/settings.json)
CLAUDE.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 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

worklog-mcp is a simple, Markdown-based MCP (Model Context Protocol) server for AI assistants. It provides searchable plain-text logging functionality without databases.

Philosophy

  • Keep it Simple: No databases, no complex dependencies - just Markdown files
  • Plain Text: All data stored in human-readable ~/.worklogs/YYYY-MM.md files
  • Search First: AI searches and extracts, not humans organizing

Architecture

  • MCP Server: src/worklog_mcp/server.py - FastMCP-based server with 2 tools
  • Data Storage: Monthly Markdown files at ~/.worklogs/YYYY-MM.md
  • Dependencies: Only mcp package (no SQLite, Typer, Rich, Pydantic, platformdirs)

Installation & Setup

# Install with uv tool (recommended)
uv tool install .

# Run MCP server
worklog-mcp-server

MCP Server Setup

Claude Code (~/.claude/settings.json)

{
  "mcpServers": {
    "worklog": {
      "command": "worklog-mcp-server"
    }
  }
}

Environment Variables

Variable Description
WORKLOG_DIR Custom path for worklog storage (default: ~/.worklogs/)

Cloud Sync (Google Drive, Dropbox, etc.)

Use symlinks to sync worklogs across devices:

# Mac/Linux
ln -s ~/Google\ Drive/worklogs ~/.worklogs

# Windows (PowerShell as Admin)
mklink /D "C:\Users\<user>\.worklogs" "G:\My Drive\worklogs"

MCP Tools

save_worklog(content, tags)

Save work logs, thoughts, or solutions to monthly Markdown files.

Parameters:

  • content (str, required): Log content
  • tags (list[str], optional): Related tags

Storage Format:

### 2026-01-03 14:30:00
Tags: #python #debugging

Added try-except logging for better debugging

search_worklogs(query)

Search all Markdown files for keyword matches (case-insensitive).

Read the full file on GitHub · 161 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. 5d ago First seen · 161 lines · 1,076 tokens per session scan B 774e7b3b0251

Subscribe to this mod's changes

worklog-mcp CLAUDE.md is an instructions file published in the GitHub repository kwrkb/worklog-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,076 tokens to every session, about $0.0054 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.