obsidian-tasks-syntax

obsidian-tasks-syntax is a skill for Claude Code, Codex from lexbritvin/obsidian-skills-pack. It costs 136 tokens per session (1,619 once invoked), scanned A, original, MIT.

A guide for writing task checkbox lines understood by the Obsidian Tasks plugin. It covers dates, priorities, recurring tasks, dependencies, and task status using specific emoji markers and date formats.

In plain words
What is it for?
Use it to create or edit tasks with due dates, scheduled or start dates, priorities, recurring reminders, dependencies, and completion or cancellation details.
Why use it?
It prevents task details from being misread because the markers are missing, out of order, or written in an unsupported format. It also clarifies the difference between a deadline, a planned date, and a start date.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create or edit tasks with due dates, scheduled or start dates, priorities, recurring reminders, dependencies, and completion or cancellation details.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lexbritvin/obsidian-skills-pack/obsidian-tasks-syntax
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 lexbritvin/obsidian-skills-pack --skill obsidian-tasks-syntax
Clone the repo
git clone --depth 1 https://github.com/lexbritvin/obsidian-skills-pack

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin obsidian-tasks-syntax/plugin install obsidian-tasks-syntax after adding the marketplace above.

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 obsidian-tasks-syntax

README.md
[![agentmods](https://agentmods.dev/badge/skills/lexbritvin/obsidian-skills-pack/obsidian-tasks-syntax/github.svg)](https://agentmods.dev/skills/lexbritvin/obsidian-skills-pack/obsidian-tasks-syntax)
Your own site
<a href="https://agentmods.dev/skills/lexbritvin/obsidian-skills-pack/obsidian-tasks-syntax"><img src="https://agentmods.dev/badge/skills/lexbritvin/obsidian-skills-pack/obsidian-tasks-syntax/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 obsidian-tasks-syntax

Your own site · 80×15
<a href="https://agentmods.dev/skills/lexbritvin/obsidian-skills-pack/obsidian-tasks-syntax"><img src="https://agentmods.dev/badge/skills/lexbritvin/obsidian-skills-pack/obsidian-tasks-syntax.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,619 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 $0.00136 $0.01619
Opus 5 $0.00068 $0.00809
Sonnet 5 $0.00027 $0.00324
Haiku 4.5 $0.00014 $0.00162

Measured 5d ago against content hash 31fc7329d145, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

obsidian-tasks-syntax 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 5d 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.

skills/obsidian-tasks-syntax/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Creating Tasks

Task Format Setting

The Tasks plugin has two mutually exclusive ways to write metadata on a task line, chosen in Settings → Tasks → Task Format:

  • Tasks Emoji Format (default) — emoji signifiers, positional. Covered below.
  • Dataview Format — inline fields ([key:: value]), read by both Tasks and the Dataview plugin.

Check which one a vault uses before writing a task line — check taskFormat in the Tasks plugin's data.json ("emoji" or "dataview"), or ask the user. Writing emoji signifiers into a vault set to Dataview format (or vice versa) means Tasks won't parse the metadata at all.

Task Line Format — Tasks Emoji Format

- [ ] Task description 🔼 🔁 every week 🛫 2025-01-01 ⏳ 2025-01-05 📅 2025-01-10

Order matters: description first, then priority, then recurrence, then dates. The Tasks plugin parses emoji signifiers by position — putting them out of order can cause misreads. Dates are always YYYY-MM-DD — natural language like "tomorrow" is not recognized on task lines (it only works in query blocks).

Task Line Format — Dataview Format

- [ ] Task description [priority:: medium] [repeat:: every week] [start:: 2025-01-01] [scheduled:: 2025-01-05] [due:: 2025-01-10]

Fields are matched by name, not position — order does not matter. Each field is its own [key:: value] bracket; don't combine several keys inside one bracket. Dates are still always YYYY-MM-DD.

Emoji → Dataview field name:

Emoji Dataview field Note
📅 due date due
⏳ scheduled date scheduled
🛫 start date start
➕ created date created
✅ done date completion not done
❌ cancelled date cancelled
🔺⏫🔼🔽⏬ priority priority values: highest, high, medium, low, lowest (omit for Normal)
🔁 recurrence repeat not recurrence; rule text unchanged (every week, etc.)
🆔 id id
⛔ dependsOn dependsOn

Read the full file on GitHub · 122 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. 5d ago Changed · +34 lines · +22 tokens per session 31fc7329d145
  2. 12d ago First seen · 88 lines · 114 tokens per session scan A 5e9b2ca1d6ae

Subscribe to this mod's changes

obsidian-tasks-syntax is a skill published in the GitHub repository lexbritvin/obsidian-skills-pack (2 stars, last pushed 7d ago), licensed MIT. It adds 136 tokens to every session and 1,619 once invoked, about $0.0007 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.