new-task

new-task is a command for Claude Code from khanh-vu/claude-force. It costs 6 tokens per session (564 once invoked), scanned A, original, MIT.

A command that creates a new task file from a standard template and asks for key details such as the title, objective, priority, and type.

In plain words
What is it for?
Use it to start feature, bug-fix, refactoring, or documentation tasks with sections for requirements, acceptance criteria, scope, risks, workflow, and deliverables.
Why use it?
It gives a new piece of work a consistent starting structure instead of requiring you to create task documentation manually.

Command for Claude Code

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 commands/khanh-vu/claude-force/new-task
Clone the repo
git clone --depth 1 https://github.com/khanh-vu/claude-force

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 new-task

README.md
[![agentmods](https://agentmods.dev/badge/commands/khanh-vu/claude-force/new-task.svg)](https://agentmods.dev/commands/khanh-vu/claude-force/new-task)
Your own site
<a href="https://agentmods.dev/commands/khanh-vu/claude-force/new-task"><img src="https://agentmods.dev/badge/commands/khanh-vu/claude-force/new-task.svg" alt="Measured on agentmods" height="20"></a>
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 564 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 $0.00006 $0.00564
Opus 5 $0.00003 $0.00282
Sonnet 5 $0.00001 $0.00113
Haiku 4.5 $0.00001 $0.00056

Measured 4d ago against content hash 38daa614adfe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

new-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 4d 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.

.claude/commands/new-task.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

New Task Command

Initialize a new task in .claude/task.md using the standard template.

Process

  1. Read the task template from .claude/task.md
  2. If task.md already has content, archive it
  3. Create new task.md with template structure
  4. Prompt for key information:
    • Task title
    • Objective
    • Priority (High/Medium/Low)
    • Type (Feature/Bug Fix/Refactor/Documentation)
  5. Fill in template with provided information
  6. Leave other sections for user to complete

Template Structure

The generated task will include:

  • Objective: Clear goal statement
  • Requirements: Functional, non-functional, technical
  • Context: Background, assumptions, constraints
  • Acceptance Criteria: Specific, measurable criteria
  • Scope: What's in and out of scope
  • Resources: Links to designs, docs, data
  • Deliverables: Expected outputs
  • Success Metrics: How to measure success
  • Workflow: Suggested agent sequence
  • Risk Assessment: Potential risks and mitigations
  • Timeline: Estimated phases and duration

Interactive Mode

/new-task

> Task title: Build Product Catalog UI
> Priority: High
> Type: Feature
> Brief objective: Create responsive product catalog with filters

✅ Created new task in .claude/task.md
📝 Please complete remaining sections before running agents

Quick Mode

/new-task --quick --title "Add search feature" --type Feature

Archive Previous Task

If .claude/task.md exists:

📦 Archived previous task to .claude/archives/task-2025-11-13.md
✅ Created new task.md

Next Steps After Creation

  1. Complete all task sections
  2. Review acceptance criteria
  3. Select appropriate workflow
  4. Run first agent: /run-agent <agent-name>

Example Generated Task

# Task: Build Product Catalog UI

**Created**: 2025-11-13
**Owner**: [Your Name]
**Priority**: High
**Type**: Feature

## Objective

Create responsive product catalog with filters

[... rest of template ...]

Options

Read the full file on GitHub · 98 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. 4d ago First seen · 98 lines · 6 tokens per session scan A 38daa614adfe

Subscribe to this mod's changes

new-task is a command published in the GitHub repository khanh-vu/claude-force (5 stars, last pushed 9mo ago), licensed MIT. It adds 6 tokens to every session and 564 once invoked, about $0.0000 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.