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 skillgit 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/skill)<a href="https://agentmods.dev/skills/mikonos/llm-gtd/skill"><img src="https://agentmods.dev/badge/skills/mikonos/llm-gtd/skill.svg" alt="Measured on agentmods" 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 | $0.00228 | $0.01449 |
| Opus 5 | $0.00114 | $0.00724 |
| Sonnet 5 | $0.00046 | $0.00290 |
| Haiku 4.5 | $0.00023 | $0.00145 |
Grade A, and why
gtd-harness 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 8d 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.
This is a copy
100% identical to gtd-harness — 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GTD Skill · 主入口
身份视角：以 David Allen 的视角执行。目标不是维护待办清单，而是把承诺放进一个用户信任的外部系统，让大脑不用记忆。
状态层
核心清单在 memory/gtd/，纯 markdown，不打包进插件，也不进入知识索引。
| 文件 | 用途 |
|---|---|
inbox.md |
未理清输入的唯一入口 |
next-actions.md |
已理清的单步行动池 |
projects.md |
>1 步的期望成果 |
waiting-for.md |
委派 / 等别人 |
calendar.md |
hard landscape；外部 calendar provider 不可达时才兜底 |
someday-maybe.md |
暂不承诺但不愿忘 |
reference.md |
无需行动的备查 / 项目支持材料 |
horizons.md |
六高度方向校准 |
product-ideas.md |
产品 / 功能 / 场景机会入口 |
路由
| 用户意图 | 必读 | 动作 |
|---|---|---|
| 搭建、自检、状态、安装、初始化 | init/SKILL.md |
建清单、自检入口、只读检查 automation；显式 --install-cron 才安装 |
| 新输入、清空大脑、session 收尾 | capture/SKILL.md |
先落 inbox；单条默认自动 clarify，批量先全捕捉 |
| 理清 inbox、逐条处理、归位 | clarify/SKILL.md |
可行动吗 → 下一步 / 等待 / 项目 / 日历 / someday / reference |
| 做完了、对方回了、日程改了、取消了 | update/SKILL.md |
同步现实变化；销项、推进项目、处理 waiting-for 回应或纠错 |
| 清理结构、卡住项目、重复项 | organize/SKILL.md |
机械卫生自动做，只把需确认项浮上来 |
| 现在做什么、10 分钟、低精力、采购、准备、该催办 | engage/SKILL.md |
按情境 / 时间 / 精力 / 优先级选 3-5 条候选 |
| 每周回顾、系统乱了、不信任清单 | review/SKILL.md |
预回顾包 + Get Clear / Current / Creative + Horizons |
Reference 加载表
| 需要判断什么 | 何时读取 |
|---|---|
| 清单边界、动作权限、Obsidian 链接 | references/list-definitions.md；clarify / organize / review 涉及移动、删除、写入时先读 |
| 具体下一步是否合格 | references/clarify-decision-tree.md；下一步含糊或用户要理清时读 |
| 日历 provider、自动写入、fallback | references/capability-map.md；涉及 hard landscape 或写日历时读 |
| 自动节律 / cron / Approval Radar | references/automation-profiles.md；仅 init --install-cron 或 Daily Engage 自动节律时读 |
| 周回顾步骤 | references/weekly-review-checklist.md；review 时读 |
| 项目纵向规划 | references/natural-planning-model.md；项目成果、里程碑、下一步不清时读 |
| Horizons 纵轴校准 | references/horizons-of-focus.md；review 或优先级冲突时读 |
| 回归评测 | references/evals.md；改 skill 前后或做 public sync 前读 |
默认规则
- 系统未搭建（
memory/gtd/不存在）→ 先跑 init。 - 单条输入默认 capture → clarify；批量 mind sweep 先全捕捉，再批量理清。
- 明确是产品 / 功能 / 场景机会 →
product-ideas.md+ project / next-action 可见性；用户明确“只捕捉”时例外。 next-actions.md是行动池，不按@电脑/@电话主导分类；新行动写清预计时长 / 精力档 / 真实约束。- 用户宣告完成 → 从清单删除对应 next action；项目成果已达成且无下一步 → 删除项目块。
- 用户汇报现实变化（完成、回应、改期、取消、纠错）→ 走 update，不重新 capture 成新 inbox。
- 日历是 hard landscape；普通待办不得进
calendar.md。 - knowledge / idea 无承诺 → 移交 ZK 管线，不写 GTD action 清单。
memory/gtd/personalized.md可存本机偏好和私人映射；通用 skill 不依赖它。
What ships with it
34 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- capture/SKILL.md 4.4 KB
- clarify/SKILL.md 8.1 KB
- engage/SKILL.md 5.6 KB
- init/SKILL.md 3.9 KB
- organize/SKILL.md 3.5 KB
- references/automation-profiles.md 5.2 KB
- references/capability-map.md 4.8 KB
- references/clarify-decision-tree.md 2.4 KB
- references/evals.md 4.2 KB
- references/evolution-log.md 7.3 KB
- references/gtd-five-phases.md 1.2 KB
- references/horizons-of-focus.md 1.2 KB
- references/list-definitions.md 4.6 KB
- references/natural-planning-model.md 1.3 KB
- references/weekly-review-checklist.md 3.1 KB
- review/SKILL.md 8.0 KB
- scripts/gtd_env.sh 925 B runs code
- scripts/gtd_eval_check.sh 2.1 KB runs code
- scripts/gtd_init.sh 17 KB runs code
- scripts/gtd_review_prep_notify.sh 906 B runs code
- scripts/gtd_review_prep.sh 5.1 KB runs code
- scripts/gtd_status.sh 3.7 KB runs code
- templates/codex-prompts/gtd-capture.md 1.3 KB
- templates/codex-prompts/gtd-clarify.md 1.1 KB
- templates/codex-prompts/gtd-engage.md 890 B
- templates/codex-prompts/gtd-init.md 948 B
- templates/codex-prompts/gtd-organize.md 1.4 KB
- templates/codex-prompts/gtd-review.md 1.1 KB
- templates/codex-prompts/gtd-update.md 1.4 KB
- templates/codex-prompts/gtd.md 2.0 KB
- templates/project-template.md 1.1 KB
- templates/session-close-template.md 1.5 KB
- templates/weekly-review-template.md 1.1 KB
- update/SKILL.md 5.4 KB
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.
- 8d ago First seen · 77 lines · 228 tokens per session scan A d1877785f713
gtd-harness is a skill published in the GitHub repository mikonos/LLM-GTD (10 stars, last pushed 2mo ago), licensed MIT. It adds 228 tokens to every session and 1,449 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to gtd-harness, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
saga-orchestration
Implement saga patterns for distributed transactions and cross-aggregate workflows. Use this skill when implementing distributed transactions across microservices where 2PC is unavailable, designing compensating actions for failed order workflows that span inventory, payment, and shipping services, building…
task-coordination-strategies
Decompose complex tasks, design dependency graphs, and coordinate multi-agent work with proper task descriptions and workload balancing. Use this skill when breaking down work for agent teams, managing task dependencies, or monitoring team progress.
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
nx-workspace-patterns
Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.
context-driven-development
Creates and maintains project context artifacts (product.md, tech-stack.md, workflow.md, tracks.md) in a conductor/ directory. Scaffolds new projects from scratch, extracts context from existing codebases, validates artifact consistency before implementation, and synchronizes documents as the project evolves. Use when…