taskwarrior

A command-line integration for Taskwarrior, a text-based task manager. It lets the agent inspect and change tasks, including adding notes to them.

In plain words
What is it for?
List pending tasks, summarize overdue or high-priority work, inspect task details, create tasks, complete tasks, and attach notes.
Why use it?
It removes the need to remember Taskwarrior commands for common task-management work. It also provides structured task data for summaries and details.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/adampoit/ai/taskwarrior
Any agent
npx skills add adampoit/ai --skill taskwarrior
Clone the repo
git clone --depth 1 https://github.com/adampoit/ai

Made for: Claude Code, Codex.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 842 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00050 $0.00842
Opus 5 $0.00025 $0.00421
Sonnet 5 $0.00010 $0.00168
Haiku 4.5 $0.00005 $0.00084

Measured yesterday against content hash 8c33b9ab1084, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

taskwarrior 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 yesterday.

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/taskwarrior/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Taskwarrior

Inspect and manage tasks with task.

task +PENDING export

List Tasks

Preferred command (JSON output):

task +PENDING export

With custom filters:

task project:work due:today +PENDING export

For tasks that fall between two dates (entry, completion, due, or modified time), use Bash variables:

start_date="<start-date>"
end_date="<end-date>"
task "((entry.after:${start_date} and entry.before:${end_date}) or (end.after:${start_date} and end.before:${end_date}) or (due.after:${start_date} and due.before:${end_date}) or (modified.after:${start_date} and modified.before:${end_date}))" export

Use task rc.verbose=nothing ... for concise text output when not using export.

Task Summary

Build summary counts with these commands:

task +PENDING export
task +OVERDUE export
task due:today +PENDING export
task due:tomorrow +PENDING export
task priority:H +PENDING export

Summarize counts plus notable tasks (for example overdue or high priority).

Task Details

Get one task by ID or UUID:

task <task-id-or-uuid> export

Add Task

Create a task (mutating):

task add "Write Q1 planning notes" project:planning due:tomorrow priority:M +work +writing

Attach Notes

task-note is an external Taskwarrior helper, not a built-in task command. Confirm it is installed before using it:

command -v task-note

It takes exactly one argument. It ensures the task has a Notes file: <notes-dir>/<uuid>.md (read this file for full content) annotation, then opens the note in an interactive editor via taskopen:

task-note <task-id-or-uuid>

Notes live in $XDG_DATA_HOME/tasknotes/<uuid>.md (default ~/.local/share/tasknotes/<uuid>.md).

Non-interactive (agents)

task-note <task> with no subcommand opens an editor, so agents should use the subcommands instead:

task-note <task-id-or-uuid> set <<'EOF'
# Note title

Note body...
EOF

task-note <task-id-or-uuid> append <<'EOF'
More details...
EOF

task-note <task-id-or-uuid> show   # print the note contents
task-note <task-id-or-uuid> path   # print the note file path

Read the full file on GitHub · 126 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. yesterday First seen · 126 lines · 50 tokens per session scan A 8c33b9ab1084

Subscribe to this mod's changes

taskwarrior is a skill published in the GitHub repository adampoit/ai (2 stars, last pushed 7d ago), licensed MIT. It adds 50 tokens to every session and 842 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.

Related

Other skills, from other repositories