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 reviewgit 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/review)<a href="https://agentmods.dev/skills/mikonos/llm-gtd/review"><img src="https://agentmods.dev/badge/skills/mikonos/llm-gtd/review/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/review"><img src="https://agentmods.dev/badge/skills/mikonos/llm-gtd/review.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 | $0.00067 | $0.02319 |
| Opus 5 | $0.00034 | $0.01159 |
| Sonnet 5 | $0.00013 | $0.00464 |
| Haiku 4.5 | $0.00007 | $0.00232 |
Grade A, and why
gtd-review 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 11d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GTD · review（每周回顾 / Reflect）
视角：David Allen 原话——「The Weekly Review is the critical success factor.」没有它，前四步全部坍塌，系统在两周内失去可信、退回大脑焦虑。回顾不是补做事，是保养系统的信任。
加载与边界
- 回顾步骤：读
references/weekly-review-checklist.md。 - 清单边界 / 删除 / 移动权限：读
references/list-definitions.md。 - hard landscape / 容量判断：读
references/capability-map.md。 - Horizons 冲突或优先级判断：读
references/horizons-of-focus.md。 - 自动化边界：预处理和机械卫生可自动；删除不确定条目、砍项目、确定下周 3 件事需用户确认。
何时跑
- 每周固定一次（建议周五；节律见
references/weekly-review-checklist.md）。 - 用户说「做每周回顾」「周复盘」「过一遍我的系统」「weekly review」。
- 系统感觉乱了/不信任了——这正是该回顾的信号。
边界：AI 多做脏活，用户做承诺判断
review 不是让用户从清单里重新翻一遍。AI 应该先把系统体检、机械整理、候选动作、话术草稿尽量准备好，再把少数需要用户判断的点浮上来。
| AI 默认先做 | 必须让用户确认 |
|---|---|
| 跑 dashboard / 预回顾包；扫描 inbox、next-actions、projects、waiting-for、someday、product ideas、horizons；审计 product ideas 是否都有 project / next-action 可见性 | 删除不确定条目、砍项目、启动 someday、推进 product idea 到 PRD / 降级 / 删除、确定下周 3 件事 |
| 调用 organize 做机械卫生：错情境、重复、死勾、明显孤儿、stalled 检出 | 写日历、发消息、通知/委派他人、任何高后果动作 |
| 为 stalled project 起草下一步；为 waiting-for 起草中性催办话术；为下周重点给候选 | 在事实冲突、来源不明、风险较高时替用户拍板 |
原则：预处理可以自动，承诺判断不自动。 用户看到的应是一份「待确认的系统体检报告」，不是一堆原始清单。
0. AI 预回顾包（默认先做）
- 跑
scripts/gtd_review_prep.sh，生成只读预回顾包：全景数字、inbox 摘要、stalled 项目、waiting-for、模糊 next-action、someday 候选、product ideas 可见性审计、确认队列。 - 读外部 calendar provider（可达则优先）；全部不可达再读
calendar.md兜底并注明可能不全。 - 对下周 hard landscape 做容量扫描：哪些天已被硬约定占满，哪些焦点缺少可用时间窗；只提示重谈承诺，不自动把 next-actions 塞进日历。
- 调用
organize/SKILL.md的机械卫生流程：能自动修的先修；需要拍板的批量列出。 - 把 review 压缩成 3 类输出：
- 已自动处理：机械整理、去重、补草稿、归位。
- 建议确认：删除/启动/砍项目/补下一步/催办。
- 下周候选：AI 建议的 3 个焦点 + 理由。
三段式 + 纵轴 + 横轴（Allen 三段 + Horizons 纵轴 + Laura 三环横轴）
① Get Clear（清空）
- 清空
inbox.md：逐项 clarify 到零（调用 clarify 工作流）。 - 收拢散落各处的「东西」（笔记、脑中悬而未决）一并捕捉进系统。
② Get Current（更新）
- 过
next-actions.md：已完成的销项；不再相关的删；每条仍是有效的下一步吗？ - 过日历（hard landscape）：上周遗留/本周将至的硬约定。先读外部 calendar provider（可达则优先，见
references/capability-map.md）；全部不可达再读calendar.md兜底并注明可能不全。不把外部日历抄进 calendar.md（单一兜底）。下周 3 件事必须对照可用时间窗；若焦点超过容量，提示删、延期、委派或降级。 - 过
waiting-for.md：哪些该催了？逐条看委派日期。 - 过
projects.md：先问项目成果是否已经达成；已达成就删除整个项目块（不归档、不写「下一步行动：无」）。未达成的项目再问是否挂着至少一个有效 next-actions / waiting-for block link；多条只保留可并行的当前动作；stalled 的当场补。项目成果是否仍想要？ - 过
product-ideas.md：每条产品机会是否都有GTD 可见性，且能指向 project / next-action；缺失则当场补一个项目或下一步，不让产品机会留成冷藏 backlog。
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.
- 11d ago First seen · 96 lines · 67 tokens per session scan A da750a59b67e
gtd-review is a skill published in the GitHub repository mikonos/LLM-GTD (10 stars, last pushed 3mo ago), licensed MIT. It adds 67 tokens to every session and 2,319 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).