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 skills add mikonos/LLM-GTD --skill engagegit clone --depth 1 https://github.com/mikonos/LLM-GTDWrote 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/skills/mikonos/llm-gtd/engage)<a href="https://agentmods.dev/skills/mikonos/llm-gtd/engage"><img src="https://agentmods.dev/badge/skills/mikonos/llm-gtd/engage/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.
<a href="https://agentmods.dev/skills/mikonos/llm-gtd/engage"><img src="https://agentmods.dev/badge/skills/mikonos/llm-gtd/engage.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00052 | $0.01642 |
| Opus 5 | $0.00026 | $0.00821 |
| Sonnet 5 | $0.00010 | $0.00328 |
| Haiku 4.5 | $0.00005 | $0.00164 |
Grade A, and why
gtd-engage 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 10d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GTD · engage（执行 / 选下一步）
视角：David Allen。Engage 解决「此刻做什么最有把握」。GTD 不靠「应该感」驱动，而靠四要素模型当场筛选——前提是前四步已把系统理清，否则选择本身就充满焦虑。
加载与边界
- 选行动前先按
organize/SKILL.md做机械卫生；清单边界不明读references/list-definitions.md。 - 需要 hard landscape / 自由时间窗：读
references/capability-map.md。 - Daily Engage 自动节律或 Approval Radar：读
references/automation-profiles.md。 - 自动化边界：只给 3-5 条候选菜单；不把候选说成今日承诺，不自动排进日历。
何时跑
- 用户问「现在该做什么」「这会儿做点啥」「我有 30 分钟能干嘛」。
- 早晨/一段空档开始前，要一个聚焦视图。
- 1:1 / 项目会前，要某人/某项目相关的可推进项（也可走 review 的议程视图）。
四要素筛选（依次收窄）
1. 情境（Context） ——此刻哪些真实约束决定我能不能做？ → 用硬情境 / 工具约束 / 当下状态镜头筛行动池
2. 可用时间（Time） ——我有多久？ → 时间短挑短任务
3. 精力（Energy） ——我现在脑力/体力如何？ → 精力低挑轻任务
4. 优先级（Priority）——同等条件下哪个回报最高？ → Horizons 校准（服务于哪个目标/责任领域）
可用镜头（第一版宁少勿多）
- 时间镜头：2 分钟 / 10 分钟 / 30 分钟 / 60-90 分钟。
- 精力镜头：低精力 / 中精力 / 深工作 / 情绪耗能低。
- 硬情境镜头：采购、外出顺路、在家有材料、会议前、某人在场、准备链。
- 工具/渠道约束：需要电脑、需要电话、需要文件、需要付款、需要证件、需要设备。
- 协作镜头：该催办、@议程-人、需要拍板。
旧 @电脑/@电话/@外出/@家/@议程 分组只作为历史兼容信号读取，不能因为某条在 @电脑 下就默认推荐。情境的定义是「此刻是否真能做的约束」，不是地点分类。
Allen 判断口径
- 日历先于清单：先看 hard landscape，确认下一个硬约定前真实还有多少自由时间。
- Next Actions 是行动池里的菜单，不是今日承诺：clarify 已把行动写清楚；engage 只是用镜头从行动池挑此刻合适的一步，不把清单全部排进日历，也不要求用户面对全清单。
- 过载分三类：日程重叠 = 硬冲突；next-actions 很多 = 菜单大；把太多 next-actions 都声明为今天必须完成 = 承诺过载，需要删、延期、委派或降级，而不是硬塞进日历。
工作流
- 先静默跑一遍 organize 结构卫生（按
organize/SKILL.md的机械类自动项：孤儿/stalled/情境/死勾/重复）——让「现在做什么」基于干净结构，stalled 项目不漏。只在有需你拍板项时附一句，否则不打断。 - 先读今天/当前窗口的硬约定，计算到下一个 hard landscape 前的自由时间块；外部 calendar provider 可达则以它为准，全部不可达再读
calendar.md兜底并注明「按本地兜底，可能不全」。 - 若本次是 Daily Engage 自动节律，且已启用 Approval Radar，按
references/automation-profiles.md做只读 Approval Radar：只提示需要行动或状态变化的 approval，不自动 approve/reject/remind；缺少只读权限时说明缺口后继续 Engage。 - 问清（或从上下文推断）用户的情境、可用时间、精力。支持自然语言镜头：
我只有 10 分钟、我没电了、我要出门、我在采购、明早要准备什么、有什么该催的。若日历算出的时间窗与用户口头时间不同，取更小者。 - 读
next-actions.md行动池，兼容旧@电脑/@电话/@外出/@家/@议程分组信号，但按四要素和镜头筛选，给出 3–5 条「现在最该做」的候选，标注每条预估时长和为什么适合“现在”。 - 优先级排序时向上对照 Horizons：哪条最服务于当前 30k 目标 / 20k 责任领域。不是「最急」而是「最重要且此刻可做」。
- 若今天没有足够自由时间，或用户声明的 today-must 明显超过剩余时间，输出「承诺过载」提示，并给出删、延期、委派、降级四类重谈建议；不要自动把 next-actions 排进日历。
- 顺带提示：若有 waiting-for 到期该催的，一并点出。
- 用户做完某条 → 走闭环（从 next-actions 删除该行）。
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.
- 10d ago First seen · 71 lines · 52 tokens per session scan A d608c673f258
gtd-engage is a skill published in the GitHub repository mikonos/LLM-GTD (10 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 1,642 once invoked, about $0.0003 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.
Other skills, from other repositories
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.
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.
career-coach
Personal career coach with 4 modes: weekly reports, monthly reflections, self-reviews, promotion assessments.
resume-builder
Build resume and LinkedIn profile through guided interview.
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.
career-setup
Initialize career development system (job description, ladder, reviews, goals).