task

task is a command for Claude Code from eddiebelaval/squire. It costs 0 tokens per session (619 once invoked), scanned A, original, MIT.

A conversational workflow for creating a task file from a rough request.

In plain words
What is it for?
Use it to define feature work, bug fixes, refactors, or research tasks and record the constraints and desired result.
Why use it?
It turns an incomplete idea into a task with a project, priority, work type, goal, and acceptance criteria without requiring manual template editing.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

Good fit Use it to define feature work, bug fixes, refactors, or research tasks and record the constraints and desired result.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/eddiebelaval/squire/task
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.

Clone the repo
git clone --depth 1 https://github.com/eddiebelaval/squire

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 task

README.md
[![agentmods](https://agentmods.dev/badge/commands/eddiebelaval/squire/task/github.svg)](https://agentmods.dev/commands/eddiebelaval/squire/task)
Your own site
<a href="https://agentmods.dev/commands/eddiebelaval/squire/task"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/task/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 task

Your own site · 80×15
<a href="https://agentmods.dev/commands/eddiebelaval/squire/task"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 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 $0.00000 $0.00619
Opus 5 $0.00000 $0.00309
Sonnet 5 $0.00000 $0.00124
Haiku 4.5 $0.00000 $0.00062

Measured 5d ago against content hash 99ab93a061b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

task 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.

commands/task.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/task - Quick Task Creation

You are helping create a new task file in the current project's workspace. This is a conversational process — you ask the questions, the user answers (by voice or text), and you fill in the template. The user should never have to manually edit bracket placeholders.

Arguments

  • $ARGUMENTS: Task title and/or description (can be rough — you'll refine it)
  • Flags: --priority <critical|high|medium|low>, --project <name>

Conversational Flow

Phase 1: Quick Setup (use AskUserQuestion)

Ask these together in a single AskUserQuestion call:

  1. Project — Which project is this for? (if not provided and can't be auto-detected)
  2. Priority — How urgent? Options: Critical, High, Medium (default), Low
  3. Type — What kind of work? Options: Feature, Bug fix, Refactor, Research

Phase 2: Details (conversational — just ask, let them talk)

Based on the title/description the user already gave, ask follow-up questions naturally. Don't ask all at once — be conversational:

  • "What's the goal? What should be true when this is done?" (becomes Acceptance Criteria)
  • "Any technical constraints or approaches you're already thinking about?" (becomes Implementation Notes)
  • "Any files you know are involved?" (becomes Related Files)

Important: If the user gives short answers, that's fine. Don't push for detail they don't have. A task with just a title and priority is perfectly valid.

Phase 3: Create and Fill

  1. Run ~/.claude/generators/new-task.sh with the title, priority, and project flags
  2. Read the created file
  3. Replace all [bracket placeholders] with the user's actual answers
  4. Write the updated file
  5. Show a brief summary of what was created

Example Conversation

User: /task Add email notifications for Homer

Claude: [AskUserQuestion: Priority? Type?]

User: High priority, it's a feature

Claude: Got it. What should happen when this is done — what does "email notifications working" look like?

User: Agents should get an email when a new lead comes in and when an amendment is submitted

Claude: Makes sense. Any thoughts on implementation — Resend, specific templates?

User: Yeah use Resend, we already have it set up with [email protected]

Claude: [Creates file, fills in all sections, shows summary]

Read the full file on GitHub · 62 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 First seen · 62 lines · 0 tokens per session scan A 99ab93a061b3

Subscribe to this mod's changes

task is a command published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 619 tokens. 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 2026-09-03.