task-status

A command for checking background work started by other workflow commands, including whether tasks are running, completed, or failed.

In plain words
What is it for?
Use it to list tasks, inspect one task by its ID, or wait for a task to complete.
Why use it?
It removes the need to guess whether delegated work has finished or manually track several tasks.

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/data-wise/claude-plugins/task-status
Clone the repo
git clone --depth 1 https://github.com/Data-Wise/claude-plugins
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 1,868 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 $0.00000 $0.01868
Opus 5 $0.00000 $0.00934
Sonnet 5 $0.00000 $0.00374
Haiku 4.5 $0.00000 $0.00187

Measured yesterday against content hash 5ca8f1f53903, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-status 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.

workflow/commands/task-status.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/task-status - Background Task Status

Check status of background tasks launched by workflow commands.

Purpose

Monitor background tasks from:

  • /workflow:brainstorm --background
  • /workflow:refine (option 2: background)
  • Any other command with background delegation

Usage

/workflow:task-status              # List all tasks
/workflow:task-status <task_id>    # Check specific task
/workflow:task-status --wait <task_id>  # Wait for completion

When invoked:

Without Arguments: List All Tasks

BACKGROUND TASKS
════════════════════════════════════════════════════════════

🔄 ACTIVE ({count}):

  {task_id} - {command} "{topic}"
    Started: {time_ago}
    Estimated: {estimated_duration}
    Status: Running...

  {task_id2} - {command2} "{topic2}"
    Started: {time_ago2}
    Estimated: {estimated_duration2}
    Status: Running...

────────────────────────────────────────────────────────────
✅ COMPLETED ({count}):

  {task_id3} - {command3} "{topic3}" ✓
    Completed: {time_ago3}
    Duration: {actual_duration3}

────────────────────────────────────────────────────────────
❌ FAILED ({count}):

  {task_id4} - {command4} "{topic4}" ✗
    Failed: {time_ago4}
    Error: {error_summary}

────────────────────────────────────────────────────────────
💡 COMMANDS:

  /workflow:task-output <id>  - View results
  /workflow:task-cancel <id>  - Cancel running task
  /workflow:task-status <id>  - Check specific task

Implementation:

  1. Check for .claude/tasks.json file
  2. If doesn't exist, check Claude Code's internal task tracking via /tasks command
  3. Parse task list and categorize by status
  4. Format output with clear sections
  5. Show time estimates and actual durations

With Task ID: Check Specific Task

/workflow:task-status abc123

Output for RUNNING task:

TASK STATUS: abc123
════════════════════════════════════════════════════════════

Command: /workflow:brainstorm "improve test coverage"
Status: 🔄 Running
Started: 2 minutes ago
Estimated: 2-3 minutes
Progress: ~66% (2 of 3 min)

────────────────────────────────────────────────────────────
💡 NEXT STEPS:

  • Wait a bit longer (~1 minute remaining)
  • Continue working, I'll notify when done
  • Check again: /workflow:task-status abc123
  • Cancel: /workflow:task-cancel abc123

Or wait for completion:
  /workflow:task-status abc123 --wait

Read the full file on GitHub · 327 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 · 327 lines · 0 tokens per session scan A 5ca8f1f53903

Subscribe to this mod's changes

task-status is a command published in the GitHub repository Data-Wise/claude-plugins (7 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,868 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 2026-08-31.