agentmods.dev

gtd-review

gtd-review is a skill for Claude Code from ZhdanovAlexey/obsidian-gtd-agent. It costs 81 tokens per session (1,515 once invoked), scanned A, original, MIT.

A guided weekly review for a GTD system, where GTD is a method for keeping tasks, projects, waiting items, and reference material organized. It prepares a review note from recent work, journal entries, and, when available, calendar events.

In plain words
What is it for?
Use it to review the previous week, prepare for the next two weeks, archive completed tasks, inspect blocked work, synchronize projects, and create a review note.
Why use it?
It gathers unfinished, stale, blocked, and completed work in one place so the week does not disappear into scattered files. It also checks that finished actions are reflected in their projects.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

not rated 6repo 1mo ago A scan 81 tokens original MIT

Good fit Use it to review the previous week, prepare for the next two weeks, archive completed tasks, inspect blocked work, synchronize projects, and create a review note.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zhdanovalexey/obsidian-gtd-agent/gtd-review
View source ↗ ZhdanovAlexey/obsidian-gtd-agent
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.

Any agent
npx skills add ZhdanovAlexey/obsidian-gtd-agent --skill gtd-review
Clone the repo
git clone --depth 1 https://github.com/ZhdanovAlexey/obsidian-gtd-agent

Made for: Claude Code.

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.

agentmods badge for gtd-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/zhdanovalexey/obsidian-gtd-agent/gtd-review/github.svg)](https://agentmods.dev/skills/zhdanovalexey/obsidian-gtd-agent/gtd-review)
Your own site
<a href="https://agentmods.dev/skills/zhdanovalexey/obsidian-gtd-agent/gtd-review"><img src="https://agentmods.dev/badge/skills/zhdanovalexey/obsidian-gtd-agent/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.

agentmods 80×15 button for gtd-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/zhdanovalexey/obsidian-gtd-agent/gtd-review"><img src="https://agentmods.dev/badge/skills/zhdanovalexey/obsidian-gtd-agent/gtd-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,515 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00081 $0.01515
Opus 5 $0.00041 $0.00758
Sonnet 5 $0.00016 $0.00303
Haiku 4.5 $0.00008 $0.00152

Measured 12d ago against content hash 682705cf1a1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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 12d 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.

vault/.claude/skills/gtd-review/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Weekly Review (GTD)

Ты готовишь еженедельный обзор так, чтобы пользователю осталось только пройтись и принять решения. Черновую аналитику делаешь сам, не заставляешь искать руками.

Шаги

  1. Календарь. Если подключён MCP-календарь — подтяни прошедшие 7 дней (что было, не забыто ли что зафиксировать) и следующие 14 дней (к чему готовиться). Кратко выпиши заметные события и встречи, требующие подготовки.

  2. Архив выполненного за неделю. Пройди GTD/Next.md и GTD/Waiting.md:

    • Каждому выполненному - [x] без даты проставь ✅ ГГГГ-ММ-ДД; перенеси все [x] из активных секций в ## Done (Next) / # Done (Waiting). Делаешь сам и показываешь отчётом — не спрашивая по каждому.
    • Проверка синхронизации (страховочная сетка). Для каждого выполненного пункта со ссылкой [[Проект]]: отметь шаг [x] в «## Следующие шаги» проекта и добавь строку в «## Лог». Пройди и старые [x] в ## Done, не только этой недели.
    • Если у проекта закрыты все шаги и результат достигнут — предложи status: done (решение подтверждает пользователь). Иначе проект всплывёт как беспризорный в скане ниже — это нормально.
    • Запомни список перенесённого — он станет основой секции «✅ Сделано за неделю».
    • Чистка Next.md (в самом конце, после создания файла обзора). Очисти секцию ## Done: архивом служит файл обзора. Оставь строку-указатель на свежий обзор. Это держит Next лёгким.

  3. Скан хранилища — собери и покажи списком:

    • Протухшие дедлайны: проекты со status: active и deadline: в прошлом (сегодня бери из системной даты).
    • Проекты без следующего шага: активные проекты, у которых нет открытого - [ ] ни внутри файла, ни в GTD/Next.md (по wikilink). Главные кандидаты на гниль.
    • Пора пинговать: пункты в GTD/Waiting.md с датой с ГГГГ-ММ-ДД старше ~5–7 дней.
    • Inbox: число неразобранных пунктов (если >0 — предложи сначала /gtd-inbox).

  4. Сверка с горизонтами и стандартами. Глянь 🧭 Стратегия.md (цели + Runway). Двигаются ли #runway-задачи? Затем пройди по Areas/**, раздел «Заметки / стандарты» каждой области: это регулярные практики и ритуалы. Проверь по каждому — держится или просело? Что просело — предложи действие в Next.md.

Read the full file on GitHub · 85 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.

  1. 12d ago First seen · 85 lines · 0 tokens per session scan A 682705cf1a1c

Subscribe to this mod's changes

gtd-review is a skill published in the GitHub repository ZhdanovAlexey/obsidian-gtd-agent (6 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 1,515 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.

Claude CodePlanningProductivityai-agentdataviewgtdobsidianobsidian-vault
Related

Other skills, from other repositories

obsidian-meta-bind

Authoring buttons, input fields, view fields, and embeds for the Obsidian Meta Bind plugin. Use whenever the user asks to add an interactive control, button, input, viewfield, INPUT[...] / VIEW[...] / BUTTON[...] syntax, or a meta-bind code block. Covers schema, valid enum values, inline references, JS Engine…

lexbritvin/obsidian-skills-pack · 103 tokens

obsidian

Obsidian vault management — create notes, backlinks, tags, and Dataview queries via file operations.

furkangonel/cowrangler · 24 tokens

obsidian-tasks-syntax

Creates and edits Obsidian Tasks plugin task lines with emoji-based or Dataview-style dates, priorities, recurrence, dependencies, and statuses. Use when the user asks to add a task, create a todo, set a due date, change priority, add recurrence, make a recurring reminder, edit a checkbox line, or anything involving…

lexbritvin/obsidian-skills-pack · 136 tokens

obsidian-tasks-query

Creates Obsidian Tasks plugin query blocks with filters, sorting, grouping, and layout options. Use when the user asks to build a task dashboard, show overdue tasks, list tasks by priority, create a task view or report in a note, write a tasks code block, group tasks by project, filter tasks by folder or date, make a…

lexbritvin/obsidian-skills-pack · 89 tokens

obsidian

Organize Obsidian vaults with Markdown, URI links, Templater, Dataview, and local plugin workflows.

alivirgo/Major-AI-Skills · 29 tokens

prepdojo-applications

Log and update job applications in the user's PrepDojo tracker (CSV files inside their Obsidian vault, read live by a Dataview dashboard). Trigger when the user says things like "log this application", "I applied to X", "add this to my tracker", or reports a stage change — "X moved me to phone screen", "got rejected…

aaaxy/PrepDojo · 136 tokens