work-new

An interactive command for creating a work item, which is a tracked piece of development work. It supports features, bug fixes, refactoring, security work, and other user-entered types.

In plain words
What is it for?
Use it to enter a work item’s type, title, description, priority, dependencies, and related details through guided questions.
Why use it?
It turns an idea, defect, or improvement into a consistently described item that can be tracked later.

Command

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/ankushdixit/claude-plugins/work-new
Clone the repo
git clone --depth 1 https://github.com/ankushdixit/claude-plugins
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,366 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 $0.00007 $0.01366
Opus 5 $0.00003 $0.00683
Sonnet 5 $0.00001 $0.00273
Haiku 4.5 $0.00001 $0.00137

Measured 2d ago against content hash 6c4516eee186, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

work-new 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 2d 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.

solokit/commands/work-new.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Work Item Create

Create a new work item using rich interactive UI components.

Instructions

  1. First, gather basic information using the AskUserQuestion tool with these 4 questions:

    Question 1: Work Item Type

    • Question: "What type of work item would you like to create?"
    • Header: "Type"
    • Multi-select: false
    • Options (limit: 4 options max):
      • Label: "feature", Description: "Standard feature development - New functionality or enhancement"
      • Label: "bug", Description: "Bug fix - Resolve an issue or defect"
      • Label: "refactor", Description: "Code refactoring - Improve code structure without changing behavior"
      • Label: "security", Description: "Security-focused work - Address security vulnerabilities or improvements"
    • Note: User can select "Type something" to manually enter: integration_test or deployment

    Question 2: Title

    • Question: "Enter a brief, descriptive title for the work item:"
    • Header: "Title"
    • Multi-select: false
    • Options: Provide 2-4 example titles based on the type selected in Question 1:
      • If type=feature: "Add authentication system", "Implement search feature"
      • If type=bug: "Fix database connection timeout", "Resolve login error"
      • If type=refactor: "Refactor authentication module", "Simplify error handling"
      • If type=security: "Fix SQL injection vulnerability", "Add input sanitization"
    • Note: User will select "Type something" to enter their custom title

    Question 3: Priority

    • Question: "What is the priority level for this work item?"
    • Header: "Priority"
    • Multi-select: false
    • Options:
      • Label: "critical", Description: "Blocking issue or urgent requirement"
      • Label: "high", Description: "Important work to be done soon (recommended default)"
      • Label: "medium", Description: "Normal priority work"
      • Label: "low", Description: "Nice to have, can be deferred"

    Question 4: Urgent Status

    • Question: "Does this work item require immediate attention? (Only ONE item can be urgent at a time)"
    • Header: "Urgent"
    • Multi-select: false
    • Options:
      • Label: "No", Description: "Normal workflow - will be prioritized by priority level and dependencies"
      • Label: "Yes", Description: "Mark as urgent - will override all other priority and be worked on immediately"

Read the full file on GitHub · 129 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. 2d ago First seen · 129 lines · 7 tokens per session scan A 6c4516eee186

Subscribe to this mod's changes

work-new is a command published in the GitHub repository ankushdixit/claude-plugins (3 stars, last pushed 7mo ago), licensed MIT. It adds 7 tokens to every session and 1,366 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.