A setup and status-check tool for a GTD system. It creates the main task lists, checks connections to supported services, and reports whether recurring routines are installed.

Use it when first enabling GTD, repairing a missing-list setup, checking service connections, or explicitly installing GTD routines such as weekly review and daily task selection.

It removes the need to build the folder and list structure by hand. Its status mode can check the setup without changing files or scheduled routines.

gtd-init — Skill for Claude Code and Codex by mikonos: A setup and status-check tool for a GTD system.

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 skills/mikonos/llm-gtd/init

Any agent

npx skills add mikonos/LLM-GTD --skill init

Clone the repo

git clone --depth 1 https://github.com/mikonos/LLM-GTD

Made for: Claude Code, Codex.

Or install llm-gtd, the plugin that ships this one along with the rest of its 8 skills, 8 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mikonos/llm-gtd/init.svg)](https://agentmods.dev/skills/mikonos/llm-gtd/init)

Your own site

<a href="https://agentmods.dev/skills/mikonos/llm-gtd/init"><img src="https://agentmods.dev/badge/skills/mikonos/llm-gtd/init.svg" alt="Measured on agentmods" height="20"></a>

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,093 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00075	$0.01093
Opus 5	$0.00037	$0.00547
Sonnet 5	$0.00015	$0.00219
Haiku 4.5	$0.00007	$0.00109

Measured 6d ago against content hash 7e5528e81d51, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

gtd-init 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 6d 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.

plugins/llm-gtd/skills/gtd-harness/init/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GTD · init（搭建 / 自检）

视角：David Allen。GTD 的第一道工序是把可信系统的盒子摆好——一个不能自我初始化的系统等于让用户手工搭建，违反「降低进入门槛」。

加载与边界

只搭建或 --status：运行脚本即可，不读额外 reference。
涉及 --install-cron / 初始化自动节律：先读 references/automation-profiles.md。
适配层或 calendar provider 有疑问：读 references/capability-map.md。
自动化边界：默认只读检查；只有用户显式要求才创建/更新 automation。

何时跑

首次启用 GTD skill（memory/gtd/ 不存在）。
任何命令自检报告清单缺失。
想确认三平台适配层是否打通（--status）。
想确认 GTD 自动节律（Weekly Review / Monthly Reflect / Daily Engage）是否已安装。
用户明确要求安装 / 初始化 GTD cron / automation（--install-cron）。

工作流

运行初始化脚本（幂等、零破坏，已存在的清单跳过不覆盖）：
```
bash <this-skill>/scripts/gtd_init.sh
```
它会建齐 memory/gtd/ 核心八清单（含 next-actions 行动池兼容骨架与 Horizons 模板）和产品想法扩展清单，自检适配层，并只读检查自动节律安装现状。
只自检不写文件：bash …/scripts/gtd_init.sh --status

--status 会检查：
- GTD skill 真源和三平台入口是否可达。
- Weekly Review / Monthly Reflect / Daily Engage 是否已有本机 automation。
- 它只报告现状，不创建、不暂停、不修改 cron。
自动节律安装（只在用户显式要求时执行，例如 /gtd init --install-cron / “初始化 GTD cron”）：
- 先读 references/automation-profiles.md。
- 先检查现有 $CODEX_HOME/automations/*/automation.toml，优先更新已有 automation，不创建重复项。
- 在 Codex 中必须调用 automation_update 创建/更新；不要用 shell 手写 ~/.codex/automations。
- 默认安装/更新：Weekly Review、Monthly Reflect、Daily Engage + Approval Radar。
- Daily Engage 若本机已有上午或晚间入口，沿用并更新已有入口；若都没有，默认创建上午入口。若用户明确选了晚间，则创建/更新晚间入口。
- Session Clarify 仅在用户明确要自动扫描 Codex session 时安装。
- 安装后运行 bash …/scripts/gtd_init.sh --status 验证。
可选一次性导入旧数据（默认不跑；旧 open loops.md 只读不改）：
```
bash <this-skill>/scripts/gtd_init.sh --import-legacy
```
把旧 @自己→next-actions、@等待→waiting-for、@项目→projects，标注 marker 防重复导入。导入项落在「待补轻字段」段，需逐条 clarify 补预计时长 / 精力档 / 真实约束。
读就绪报告：确认新建/跳过数、适配层自检结果、自动节律现状，按提示引导用户跑第一次 capture。

质量检查

核心八清单 + 产品想法扩展清单文件齐全（bash …/scripts/gtd_status.sh 能跑出 dashboard）
重跑只跳过、不覆盖（幂等）
--status 能只读报告 Weekly Review / Monthly Reflect / Daily Engage 的安装现状
只有用户显式要求 --install-cron / 初始化 cron 时才创建或修改 automation
Codex 场景通过 automation_update 创建/更新，不手写 automation 文件
若导入：旧 open loops.md 字节不变（可 md5 前后比对）
自检如报「真源/入口缺失」→ 提示先确认 skill 安装路径或插件入口是否可达

Read the full file on GitHub · 66 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.

6d ago First seen · 66 lines · 75 tokens per session scan A 7e5528e81d51

Subscribe to this mod's changes

gtd-init is a skill published in the GitHub repository mikonos/LLM-GTD (9 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 1,093 once invoked, about $0.0004 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 2026-08-31.

Planning Productivity agent-skills ai-agent anthropic claude-code codex cursor

give-me-tips

Explains any senpi tip in depth, including Tip: lines in the TUI. Use when the user asks about a tip, what a tipped feature does, or which tips they can see.

code-yeongyu/oh-my-openagent · 45 tokens

career-coach

Personal career coach with 4 modes: weekly reports, monthly reflections, self-reviews, promotion assessments.

davekilleen/Dex · 24 tokens

resume-builder

Build resume and LinkedIn profile through guided interview.

davekilleen/Dex · 12 tokens

daily-plan

Build today's plan from calendar, tasks, priorities and commitments, with smart scheduling suggestions. Use when the user says 'plan my day', 'what's on today', 'help me focus', or starts the morning. Also use proactively at the first session of the day. Not for reviewing a finished day; use daily-review.

davekilleen/Dex · 69 tokens

getting-started

Interactive post-onboarding tour that adapts to whatever data exists (calendar, Granola, or none). Use right after onboarding, or when the user says 'show me around', 'how do I start'. Also use proactively when the vault is < 7 days old. Not for the initial setup itself; use setup.

davekilleen/Dex · 70 tokens

career-setup

Initialize career development system (job description, ladder, reviews, goals).

davekilleen/Dex · 18 tokens