ticktick

ticktick is a skill for Claude Code from jawello/ticktick-mcp. It costs 104 tokens per session (684 once invoked), scanned A, a copy of ticktick, MIT.

An AI-assisted TickTick task-management skill for turning conversation into tasks, reminders, and updates. TickTick is an app for organizing to-dos and due dates.

In plain words
What is it for?
Create, list, inspect, update, complete, or delete tasks, including tasks with natural-language due dates and inferred priorities.
Why use it?
It removes the need to manually translate a request into task fields such as date, priority, project, and status.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ticktick-mcp plugin — 2 skills, 1 MCP server shipped together

Good fit Create, list, inspect, update, complete, or delete tasks, including tasks with natural-language due dates and inferred priorities.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jawello/ticktick-mcp/ticktick
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.

Any agent
npx skills add jawello/ticktick-mcp --skill ticktick
Clone the repo
git clone --depth 1 https://github.com/jawello/ticktick-mcp

Made for: Claude Code.

Or install ticktick-mcp, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

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 ticktick

README.md
[![agentmods](https://agentmods.dev/badge/skills/jawello/ticktick-mcp/ticktick/github.svg)](https://agentmods.dev/skills/jawello/ticktick-mcp/ticktick)
Your own site
<a href="https://agentmods.dev/skills/jawello/ticktick-mcp/ticktick"><img src="https://agentmods.dev/badge/skills/jawello/ticktick-mcp/ticktick/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.

agentmods 80×15 button for ticktick

Your own site · 80×15
<a href="https://agentmods.dev/skills/jawello/ticktick-mcp/ticktick"><img src="https://agentmods.dev/badge/skills/jawello/ticktick-mcp/ticktick.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 684 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.00104 $0.00684
Opus 5.5 $0.00042 $0.00274
Sonnet 5.5 $0.00021 $0.00137
Haiku 4.5 $0.00010 $0.00068

Measured 1mo ago against content hash f0ae5d1e0364, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ticktick 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 1mo 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.

Origin

This is a copy

100% identical to ticktick — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/ticktick/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TickTick Task Management Skill

Turn any conversation into action. This skill connects Claude to your TickTick account so you can capture, review, and complete tasks just by talking.

Available Tools

  • ticktick_create_task — create a task (title, due date, priority, project, tags)
  • ticktick_list_projects — list all projects/lists
  • ticktick_list_tasks — list tasks in a project
  • ticktick_get_task — get details of a specific task
  • ticktick_update_task — update title, due date, priority
  • ticktick_complete_task — mark a task as done
  • ticktick_delete_task — permanently delete a task

Behavior Guidelines

Creating Tasks

  • Always create immediately — don't ask for confirmation unless something is genuinely ambiguous
  • Parse natural language dates: "tomorrow" → next day's date, "Friday" → upcoming Friday, "next week" → Monday of next week. Format as YYYY-MM-DDT00:00:00+0000
  • Infer priority from language: "urgent", "important", "ASAP" → priority 5 (High); "when you get a chance" → priority 1 (Low); default → priority 0 (None)
  • Default to Inbox if no project is mentioned (leave project_id empty)
  • If user mentions a project (e.g., "add to Work"), call ticktick_list_projects first to find the ID, then create

Listing Tasks

  • If no project is specified, call ticktick_list_projects first, then show tasks across relevant projects
  • Present tasks in a clean, readable format — not raw JSON

Completing / Deleting Tasks

  • For completing: call ticktick_list_tasks to find the task ID if needed, then ticktick_complete_task
  • For deleting: confirm it's destructive if the user seems unsure, then delete

Examples

User: "Remind me to call the dentist on Friday" → ticktick_create_task with title="Call the dentist", due_date set to upcoming Friday

User: "Add 'review Q1 report' to my Work project, high priority, due next Monday" → ticktick_list_projects to get Work project ID → ticktick_create_task with all fields

Read the full file on GitHub · 59 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. 1mo ago First seen · 59 lines · 104 tokens per session scan A f0ae5d1e0364

Subscribe to this mod's changes

ticktick is a skill published in the GitHub repository jawello/ticktick-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 104 tokens to every session and 684 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to ticktick, differing in 0 lines, and is treated as a copy.