gemini-imagegen
CommandGenerate or edit an image via a Gemini (agy) session — Gemini's generate_image tool does what Claude cannot
@vallykrieInstall CommandDevelopment
Command
/gemini-swarm
Swarm a task across parallel Gemini (agy) sessions with automatic decomposition and model routing
> /plugin marketplace add Vallykrie/gemini-swarm-skill> /plugin install gemini-swarm@gemini-swarm-skill
Command definition
gemini-swarm.mddescription: Swarm a task across parallel Gemini (agy) sessions with automatic decomposition and model routing
argument-hint: [default|auto|request] [task...]
Run the **gemini-swarm** skill (`skills/gemini-swarm/SKILL.md` in this plugin — read it now and follow it exactly).
Arguments given: `$ARGUMENTS`
Interpret them as follows:
- If the first word is `default`, `auto`, or `request`, that is the **autonomy
mode**; everything after it is the task description.
- Otherwise the mode is `default` and the whole argument string is the task.
- Mode meanings (details in the skill's Step 1):
- `default` — mirror your own current permission mode: auto-accept host →
dispatch with `--auto`; review-mode host → dispatch with `--request`.
- `auto` — always dispatch with `--auto` (agy runs sandboxed, permissions
skipped).
- `request` — always dispatch with `--request`.
If no task description remains, treat the mode as set for this conversation, confirm it in one line, and apply it when the user gives the next swarmable task. Do not ask which model to use for any subtask — routing is your job.
Decompose the task, route models, dispatch all subtasks in parallel via the `gemini-dispatcher` subagent (it calls `${CLAUDE_PLUGIN_ROOT}/scripts/dispatch.sh`), auto-accept the results, ensure the run log exists at `.gemini-swarm/logs/<ISO-timestamp>.md`, then integrate and report.
Read more
description: Swarm a task across parallel Gemini (agy) sessions with automatic decomposition and model routing argument-hint: [default|auto|request] [task...]
Run the **gemini-swarm** skill (`skills/gemini-swarm/SKILL.md` in this plugin — read it now and follow it exactly).
Arguments given: `$ARGUMENTS`
Interpret them as follows:
- If the first word is `default`, `auto`, or `request`, that is the **autonomy
mode**; everything after it is the task description.
- Otherwise the mode is `default` and the whole argument string is the task.
- Mode meanings (details in the skill's Step 1):
- `default` — mirror your own current permission mode: auto-accept host →
dispatch with `--auto`; review-mode host → dispatch with `--request`.
- `auto` — always dispatch with `--auto` (agy runs sandboxed, permissions
skipped).
- `request` — always dispatch with `--request`.
If no task description remains, treat the mode as set for this conversation, confirm it in one line, and apply it when the user gives the next swarmable task. Do not ask which model to use for any subtask — routing is your job.
Decompose the task, route models, dispatch all subtasks in parallel via the `gemini-dispatcher` subagent (it calls `${CLAUDE_PLUGIN_ROOT}/scripts/dispatch.sh`), auto-accept the results, ensure the run log exists at `.gemini-swarm/logs/<ISO-timestamp>.md`, then integrate and report.
Stats
7
Stars
0
Forks
Active
Maintenance
Shell
Language
MIT
License
Last commit
Created
Ships withgemini-swarm
Gemini does the writing. Your orchestrator plans and reviews. gemini-swarm is a Claude Code plugin/skill (portable to other harnesses) that makes Gemini the default writer for substantial work.
72 skills1 agent
Stars on GitHub
Momentum
- stars in total
- 7
Other commands on gemini-swarm.
@vallykrieInstall CommandMore commands from other plugins.
Auto-invoked
Auto-invoked
build
CommandImplement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.
@addyosmaniInstall Command