agentmods.dev

taskdog CLAUDE.md

taskdog CLAUDE.md is an instructions file for coding agents from Kohei-Wada/taskdog. It costs 2,462 tokens per session, scanned A, original, MIT.

A CLAUDE.md project instruction file for Taskdog, a task-management system with command-line, terminal-interface, and web API parts. It explains the project’s five-package monorepo—a single repository containing several related packages—and how those packages communicate.

In plain words
What is it for?
Use it to navigate the core task logic, REST server, HTTP client, command-line and terminal interfaces, and MCP server. It also explains the Clean Architecture layout, database responsibilities, package dependencies, and API-based communication flow.
Why use it?
It helps an AI assistant understand where business logic, the API, the client, and user interfaces belong. This reduces accidental dependency violations and keeps all interfaces using the project’s intended communication path.

Instructions file

not rated 351 today A scan 2,462 tokens original MIT
View the source file Kohei-Wada/taskdog
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/kohei-wada/taskdog/claude-md
Clone the repo
git clone --depth 1 https://github.com/Kohei-Wada/taskdog

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 taskdog CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kohei-wada/taskdog/claude-md.svg)](https://agentmods.dev/instructions/kohei-wada/taskdog/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kohei-wada/taskdog/claude-md"><img src="https://agentmods.dev/badge/instructions/kohei-wada/taskdog/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,462 This file is loaded in full into every session.
When invoked 2,462 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 $0.02462 $0.02462
Opus 5 $0.01231 $0.01231
Sonnet 5 $0.00492 $0.00492
Haiku 4.5 $0.00246 $0.00246

Measured 4d ago against content hash adb4584ff8e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

taskdog 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 · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 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

Taskdog is a Python task management system with a CLI/TUI and a REST API server. It manages tasks with time tracking, dependencies, schedule optimization, and rich terminal output. The codebase follows Clean Architecture and is organized as a UV workspace monorepo.

Monorepo Structure

Five packages under packages/:

  • taskdog-core: Pure business logic. Domain entities, use cases, controllers, validators, optimization strategies, SQLite + SQLAlchemy persistence with Alembic migrations. No UI/API dependencies.
  • taskdog-server: FastAPI REST API (depends on core). Routers, Pydantic request/response models, OpenAPI docs at /docs, health check, app-level exception handlers.
  • taskdog-client: HTTP client (TaskdogClient) for the server (depends on core). Used by CLI/TUI/MCP.
  • taskdog-ui: CLI (Click + Rich) and TUI (Textual), depends on core + client.
  • taskdog-mcp: MCP server for Claude Desktop (depends on client).

Communication: CLI/TUI/MCP reach all data through the HTTP API client. Only the server uses repositories and controllers directly.

Data Storage & Configuration

  • Tasks: SQLite at $XDG_DATA_HOME/taskdog/tasks.db (fallback ~/.local/share/taskdog/tasks.db).
  • Config: optional TOML at $XDG_CONFIG_HOME/taskdog/ (fallback ~/.config/taskdog/):
    • core.toml — [time], [region], [storage] (default_start/end_time, country, database_url, backend)
    • server.toml — [auth] (enabled, api_keys)
    • cli.toml — [api], [ui], [notes], [keybindings] (host, port, api_key, theme)
    • mcp.toml — [api] (host, port, api_key)
  • Priority: Environment vars > CLI args > Config file > Defaults.
  • Server host/port via taskdog-server --host --port. CLI/TUI connection via cli.toml or TASKDOG_API_HOST / TASKDOG_API_PORT. Access config via ctx.obj.config (CLI) or context.config (TUI).

Read the full file on GitHub · 130 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 · 130 lines · 2,462 tokens per session scan A adb4584ff8e4

Subscribe to this mod's changes

taskdog CLAUDE.md is an instructions file published in the GitHub repository Kohei-Wada/taskdog (351 stars, last pushed today), licensed MIT. It adds 2,462 tokens to every session, about $0.0123 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.

Pythonclickfastapimakefiletask-managementtui
Related

Other instructions, from other repositories

python-samples-fastapi-restful CLAUDE.md

Claude Code instructions for nanotaboada/python-samples-fastapi-restful, covering claude.md, claude code, tech stack, structure and coding guidelines.

nanotaboada/python-samples-fastapi-restful · 2,459 tokens

fastapi-best-practices AGENTS.md

AGENTS.md instructions for zhanymkanov/fastapi-best-practices, covering fastapi best practices for ai agents, compatibility matrix, project structure, async routes and decision rule.

zhanymkanov/fastapi-best-practices · 4,106 tokens

mayak AGENTS.md

AGENTS.md instructions for LamantinAI/mayak, covering agents.md, quick start, common commands, validation and testing.

LamantinAI/mayak · 4,238 tokens

robs_awesome_python_template AGENTS.md

Instructions for tedivm/robs_awesome_python_template, covering agent instructions and key technologies.

tedivm/robs_awesome_python_template · 219 tokens

open-python-skills AGENTS.md

Instructions for jiatastic/open-python-skills, covering project knowledge base, structure, where to look and conventions.

jiatastic/open-python-skills · 348 tokens

mayak CLAUDE.md

Claude Code instructions for LamantinAI/mayak, covering claude.md, quick start, common commands, validation and testing.

LamantinAI/mayak · 4,240 tokens