A command that sends a coding task to a separate Copilot agent, either while waiting for the result or in the background.

Use it to delegate implementation or investigation work, choosing foreground or background execution with command options.

It lets another agent handle a longer task without requiring the current session to make the changes itself.

task — Command by mvpasarel

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/mvpasarel/gh-copilot-plugin-cc/task

Clone the repo

git clone --depth 1 https://github.com/mvpasarel/gh-copilot-plugin-cc

Or install copilot, the plugin that ships this one along with the rest of its 3 skills, 12 commands, 1 agent, 3 hooks.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 475 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin 86% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5	$0.00013	$0.00475
Opus 5	$0.00006	$0.00237
Sonnet 5	$0.00003	$0.00095
Haiku 4.5	$0.00001	$0.00047

Measured 2d ago against content hash 73bd2bbd189c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

Origin

This is a copy

86% identical to plan — 29 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/copilot/commands/task.md · 49 lines

What it actually says

Delegate an agentic task to Copilot.

Raw slash-command arguments: $ARGUMENTS

Core constraint:

Do not fix issues or apply patches yourself.
Your only job is to invoke the companion script and return Copilot's output verbatim to the user.

Execution mode rules:

If the raw arguments include --background, do not ask. Run the task in a Claude background job.
If the raw arguments include --wait, do not ask. Run the task in the foreground.
Otherwise, default recommendation is background (tasks tend to be large and long-running).
Use AskUserQuestion exactly once with two options, putting the recommended option first and suffixing its label with (Recommended):
- Run in background
- Wait for results

Argument handling:

Preserve the user's arguments exactly.
Do not strip --background or --wait yourself.
The companion script parses --background, but Claude Code's Bash(..., run_in_background: true) is what actually detaches the run.

Foreground flow:

Run:

node "${CLAUDE_PLUGIN_ROOT}/scripts/copilot-companion.mjs" task "$ARGUMENTS"

Return the command stdout verbatim, exactly as-is.
Do not paraphrase, summarize, or add commentary before or after it.

Background flow:

Launch the task with Bash in the background:

Bash({
  command: `node "${CLAUDE_PLUGIN_ROOT}/scripts/copilot-companion.mjs" task "$ARGUMENTS"`,
  description: "Copilot task",
  run_in_background: true
})

Do not call BashOutput or wait for completion in this turn.
After launching the command, tell the user: "Copilot task started in the background. Check /copilot:status for progress."

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.

2d ago First seen · 49 lines · 13 tokens per session scan A 73bd2bbd189c

Subscribe to this mod's changes

task is a command published in the GitHub repository mvpasarel/gh-copilot-plugin-cc (7 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 475 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to plan, differing in 29 lines, and is treated as a copy.

Building agents

task

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

This is a copy

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

git

checklist

clarify

specify

analyze

converge