task

A command for sending a task to Gemini CLI, a command-line tool for Google's AI assistant, either in the foreground or as a background job.

In plain words
What is it for?
Running one-off Gemini tasks and starting longer tasks in the background, with progress checked through the companion status command.
Why use it?
It lets you hand work to Gemini while either watching its output immediately or continuing with other work until the task finishes.

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/abiswas97/gemini-plugin-cc/task
Clone the repo
git clone --depth 1 https://github.com/abiswas97/gemini-plugin-cc
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 277 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 $0.00012 $0.00277
Opus 5 $0.00006 $0.00138
Sonnet 5 $0.00002 $0.00055
Haiku 4.5 $0.00001 $0.00028

Measured 2d ago against content hash 7234f4d5c81f, 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.

plugins/gemini/commands/task.md · 34 lines

What it actually says

Run a Gemini task through the companion runtime.

Raw slash-command arguments: $ARGUMENTS

Execution mode rules:

  • If --background is in the arguments, run in a Claude background task.
  • Otherwise, run in the foreground and stream output.

Foreground flow:

  • Run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/gemini-companion.mjs" task $ARGUMENTS
  • Return the command stdout verbatim, exactly as-is.

Background flow:

  • Launch with Bash in the background:
Bash({
  command: `node "${CLAUDE_PLUGIN_ROOT}/scripts/gemini-companion.mjs" task $ARGUMENTS`,
  description: "Gemini task",
  run_in_background: true
})
  • Tell the user: "Gemini task started in the background. Check /gemini: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.

  1. 2d ago First seen · 34 lines · 12 tokens per session scan A 7234f4d5c81f

Subscribe to this mod's changes

task is a command published in the GitHub repository abiswas97/gemini-plugin-cc (47 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 277 once invoked, about $0.0001 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 2026-08-30.