NoizuPromptLingo: Command for Claude Code

.claude/commands/listen-task-queue.md

listen-task-queue is a command for Claude Code from noizu-labs-ml/NoizuPromptLingo. It costs 48 tokens per session (1,285 once invoked), scanned A, original, MIT.

A command that watches a task queue and processes tasks through pending, in-progress, and review stages. A task queue is a shared list of work waiting to be assigned or completed.

In plain words
What is it for?
Use it to find pending work, assign complexity, process tasks, answer questions, upload artifacts, and update task status.
Why use it?
It removes the need to repeatedly check for new tasks and manually update their progress.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; mentions Claude Code.

This is noizu-labs-ml/NoizuPromptLingo's own configuration. It tells Claude Code how to work on NoizuPromptLingo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything NoizuPromptLingo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to noizu-labs-ml/NoizuPromptLingo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/noizu-labs-ml/NoizuPromptLingo/main/.claude/commands/listen-task-queue.md
Clone the repo
git clone --depth 1 https://github.com/noizu-labs-ml/NoizuPromptLingo

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 listen-task-queue

README.md
[![agentmods](https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/listen-task-queue.svg)](https://agentmods.dev/commands/noizu-labs-ml/noizupromptlingo/listen-task-queue)
Your own site
<a href="https://agentmods.dev/commands/noizu-labs-ml/noizupromptlingo/listen-task-queue"><img src="https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/listen-task-queue.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,285 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 $0.00048 $0.01285
Opus 5 $0.00024 $0.00642
Sonnet 5 $0.00010 $0.00257
Haiku 4.5 $0.00005 $0.00128

Measured 3d ago against content hash 4a1423547e36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

listen-task-queue 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 3d 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/listen-task-queue.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Queue Listener Command

Enter Task Queue Listener Mode for queue: $ARGUMENTS

Arguments

  • $ARGUMENTS — Queue ID or name to listen to

Setup

  1. Use the list_task_queues MCP tool to find the queue ID if only a name was provided
  2. Use get_task_queue to get the queue details and verify it exists
  3. Store the queue_id for subsequent operations

Polling Loop

Poll for updates using the following workflow:

  1. Initial Fetch: Call get_task_queue_feed with queue_id and no since parameter to get recent events

  2. Store Timestamp: Save the next_since value from the response

  3. Process Events: For each event in the feed:

    • task_created: Review the new task, assign complexity using assign_task_complexity
    • status_changed: Acknowledge status changes
    • message: Respond to questions by calling add_task_message
    • artifact_added: Acknowledge artifact uploads
  4. Check Pending Tasks: Call list_tasks with status=pending to find tasks waiting for work

    • For each pending task assigned to you or unassigned:
      • Use update_task_status to mark as in_progress
      • Work on the task
      • Upload results using add_task_artifact (artifact or git_branch)
      • Update status to review when done (human will mark done)
  5. Poll Again: After processing, call get_task_queue_feed with the stored since parameter

  6. Repeat: Continue the loop, pausing briefly between polls


API Endpoints for Reference

The MCP server exposes these polling endpoints:

GET /api/tasks/queues/{queue_id}/feed?since={timestamp}&limit=100

Returns:

{
  "events": [...],
  "next_since": "2024-01-15T12:34:56.789",
  "queue_id": 1
}

SSE Stream (Alternative)

For real-time updates, agents can connect to the SSE endpoint:

GET /api/tasks/queues/{queue_id}/stream

This streams events as they occur in Server-Sent Events format.


Claude Code Hook Integration

For automatic context injection, configure Claude Code hooks to check for task queue updates. This injects updates as context after MCP tool calls without requiring explicit polling.

Read the full file on GitHub · 166 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. 3d ago First seen · 166 lines · 48 tokens per session scan A 4a1423547e36

Subscribe to this mod's changes

listen-task-queue is a command published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 1,285 once invoked, about $0.0002 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 2026-09-04.