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 skills/craftos-dev/craftbot/day-plannernpx skills add CraftOS-dev/CraftBot --skill day-plannergit clone --depth 1 https://github.com/CraftOS-dev/CraftBotWhat 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 | $0.00036 | $0.03794 |
| Opus 5 | $0.00018 | $0.01897 |
| Sonnet 5 | $0.00007 | $0.00759 |
| Haiku 4.5 | $0.00004 | $0.00379 |
Grade A, and why
day-planner 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 491 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Day Planner
Daily planning for proactive agent behavior. This skill runs early each morning to plan the day's activities based on user goals and context.
Trigger Context
You receive a planner trigger with:
scope: "day"type: "proactive_planner"
CRITICAL: Silent Execution (Override Standard Task Rules)
This skill overrides standard task completion rules. Unlike regular tasks:
- NO acknowledgement: Do NOT acknowledge task receipt to user
- NO confirmation: Do NOT wait for user confirmation before ending
- MUST end silently: Use
end_turnimmediately after completing planning work
EXCEPTION - Suggesting New Tasks: When you want to suggest a new recurring or scheduled task:
- Send the suggestion as your FINAL
send_message(nocontinue_work) — the run ends on that question - The user's reply arrives as a new run: if they approve → add the task, then end silently
- If they reject → end silently without adding
- If no reply ever comes, nothing is added — the suggestion simply lapses
Why? Planner runs happen automatically. Waiting for confirmation would cause work to pile up.
Core Question
Ask yourself: "How can I help the user get SLIGHTLY closer to their goals TODAY?"
Focus only on what can realistically be accomplished in a single day. Do not over-plan.
CRITICAL RULES - READ BEFORE DOING ANYTHING
Before Planning - ALWAYS Do These Checks
- Check existing scheduled tasks: Use
scheduled_task_listto see what's already scheduled - Read PROACTIVE.md: Check existing recurring tasks and the Goals, Plan, and Status section
- Check past work:
memory_searchand grepagent_file_system/EVENT.mdto see what has already been done - Read MEMORY.md: Understand user context, preferences, and past interactions
Duplicate Prevention (EXTREMELY IMPORTANT)
- NEVER suggest a task the user has already performed (check EVENT.md / memory_search)
- NEVER suggest a task that already exists as a recurring or scheduled task
- NEVER add a recurring task that duplicates an existing one
- If user performed a one-time task before and you suggest it again = VERY BAD
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.
- 2d ago First seen · 491 lines · 36 tokens per session scan A 04d57510b71a
day-planner is a skill published in the GitHub repository CraftOS-dev/CraftBot (376 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 3,794 once invoked, about $0.0002 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.
Other skills, from other repositories
turix-mac
Computer Use Agent (CUA) for macOS automation using TuriX. Use when you need to perform visual tasks on the desktop, such as opening apps, clicking buttons, or navigating UIs that don't have a CLI or API.
browser-control
Control web pages in an existing Chromium remote-debugging session with deterministic sagui commands or the browser-only AI Agent. Use when Claude Code needs to inspect tabs, observe semantic elements, navigate, click, type, send keys, scroll, or complete a browser goal through CDP without controlling native macOS UI…
agent-smoke-test
Run manual development checks for SwiftAutoGUI AI Agent actions through the local sagui CLI. Use when Claude or Codex needs to test app-control or Accessibility BasicAction generation on macOS.
macos-control
Control macOS GUI applications via mouse automation, keyboard input, screenshots, image recognition, and AppleScript execution. Use when you need to interact with macOS app UIs, take screenshots, click buttons, type text, scroll, drag, or locate images on screen.
open-record-replay
Record a user-demonstrated macOS workflow with the Open Record/Replay CLI, inspect the captured event stream, prepare a skill evidence package, and hand it to the host agent's native skill creator. Use when the user asks the agent to watch them perform a task, record a workflow, or create/refine a reusable Computer…
artifact-storage-policy
管理 Codex 交付物的專案識別、Google Drive／GitHub 路由、檔名、儲存位置與回讀驗證；凡工作報告、外部保存、交付成果或新 repository 選擇涉及遠端儲存時使用。.