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.
npx agentmods add instructions/kwrkb/worklog-mcp/claude-mdgit clone --depth 1 https://github.com/kwrkb/worklog-mcpWrote 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.
[](https://agentmods.dev/instructions/kwrkb/worklog-mcp/claude-md)<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>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 | $0.01076 | $0.01076 |
| Opus 5 | $0.00538 | $0.00538 |
| Sonnet 5 | $0.00215 | $0.00215 |
| Haiku 4.5 | $0.00108 | $0.00108 |
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) 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.mdfiles - 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
mcppackage (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 contenttags(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).
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.
- 5d ago First seen · 161 lines · 1,076 tokens per session scan B 774e7b3b0251
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.
Other instructions, from other repositories
solo-biz-playbook AGENTS.md
AGENTS.md instructions for ggplab/solo-biz-playbook, covering agents.md, read first, working rules and project notes.
solo-biz-playbook CLAUDE.md
Claude Code instructions for ggplab/solo-biz-playbook, covering claude.md, read first and project-specific notes.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.