gemini-swarm

gemini-swarm is a skill for Claude Code from Vallykrie/gemini-swarm-skill. It costs 142 tokens per session (1,964 once invoked), scanned A, original, MIT.

A workflow for delegating substantial writing or coding work to Gemini sessions through the agy command-line tool.

In plain words
What is it for?
Use it before changing more than one file or writing more than about 20 lines of code, tests, or documentation. It also supports dividing work across multiple sessions.
Why use it?
It gives an agent a defined way to split larger tasks, send the writing to other sessions, and review the results.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the gemini-swarm plugin — 2 skills, 2 commands, 1 agent shipped together

Good fit Use it before changing more than one file or writing more than about 20 lines of code, tests, or documentation. It also supports dividing work across multiple sessions.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Vallykrie/gemini-swarm-skill
Claude Code
/plugin install gemini-swarm

Made for: Claude Code.

Or install gemini-swarm, the plugin that ships this one along with the rest of its 2 skills, 2 commands, 1 agent.

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 gemini-swarm

README.md
[![agentmods](https://agentmods.dev/badge/skills/vallykrie/gemini-swarm-skill/gemini-swarm/github.svg)](https://agentmods.dev/skills/vallykrie/gemini-swarm-skill/gemini-swarm)
Your own site
<a href="https://agentmods.dev/skills/vallykrie/gemini-swarm-skill/gemini-swarm"><img src="https://agentmods.dev/badge/skills/vallykrie/gemini-swarm-skill/gemini-swarm/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for gemini-swarm

Your own site · 80×15
<a href="https://agentmods.dev/skills/vallykrie/gemini-swarm-skill/gemini-swarm"><img src="https://agentmods.dev/badge/skills/vallykrie/gemini-swarm-skill/gemini-swarm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,964 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 $0.00142 $0.01964
Opus 5 $0.00071 $0.00982
Sonnet 5 $0.00028 $0.00393
Haiku 4.5 $0.00014 $0.00196

Measured 11d ago against content hash 98d4da161f76, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

gemini-swarm 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/dispatch.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/gemini-swarm/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gemini-swarm

You are the orchestrator: you plan, decompose, route, and review. agy (Antigravity CLI) sessions running Gemini do the writing and the token-heavy bulk work. Writing substantial code or content yourself instead of dispatching it is a violation of this workflow — the user installed this skill precisely so that Gemini does the writing.

Verified against agy 1.0.15. Re-check agy --help if flags seem wrong — this CLI changes fast.

Delegate by default

Before you write anything, apply this rule:

  • Writing work that spans more than one file or more than ~20 lines → dispatch it to Gemini via this skill. This holds even when it is a single coherent task: a swarm of one subtask is a normal, valid run. Parallel fan-out is an optimization, not a precondition.
  • Trivial edits (a few lines in one file), pure planning/review, and answers that need no artifacts → do them yourself.
  • You still own everything around the writing: decomposition, prompts, model routing, integration, verification, and the final report.

If you catch yourself mid-task writing a file Gemini could have written, stop, turn the remaining work into subtask prompts, and dispatch.

Excuse for writing it yourself Reality
"It's faster if I just write it" Dispatch overhead is seconds; Gemini writes while your context stays free for review.
"This task doesn't split into parallel parts" A single-subtask dispatch is a valid swarm. Splitting is optional.
"I need fine control over this code" Put the control in the subtask prompt (exact paths, conventions, constraints), then review the result.
"The user didn't ask for a swarm" The user installed this skill so Gemini does the writing by default. Explicit invocation is not required.
"I'm already halfway through writing it" Sunk cost. Dispatch the remaining files.

Step 0 — Preflight

  1. command -v agy — if missing, stop and tell the user to install the Antigravity CLI.
  2. Locate the dispatcher script, in this order:
    • ${CLAUDE_PLUGIN_ROOT}/scripts/dispatch.sh (plugin install)
    • scripts/dispatch.sh next to this SKILL.md (standalone skill install)

Read the full file on GitHub · 170 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 170 lines · 142 tokens per session scan A 98d4da161f76

Subscribe to this mod's changes

gemini-swarm is a skill published in the GitHub repository Vallykrie/gemini-swarm-skill (6 stars, last pushed 23d ago), licensed MIT. It adds 142 tokens to every session and 1,964 once invoked, about $0.0007 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 2026-08-31.

Related

Other skills, from other repositories

notebook-kb

Use the notebook knowledge base (the local SQLite RAG /agy:notebook builds from a folder of documents) to do precise, grounded, cited work — total amounts by category, find every doc that mentions a person/organization, build a timeline, export a table — instead of re-reading prose and burning Claude's context.…

MarcosNahuel/antigravity-plugin-cc · 108 tokens

agy-prompting

Internal helper — how to tighten a user request into a sharp prompt for the Antigravity CLI (agy / Gemini 3.x with native web search and agentic tools).

MarcosNahuel/antigravity-plugin-cc · 40 tokens

alloydb-omni-kubernetes

You're an expert in AlloyDB Omni Operator running in Kubernetes. You can help users with related tasks such as creating, managing, and monitoring AlloyDB Omni DBClusters.

gemini-cli-extensions/alloydb-omni · 42 tokens

alloydb-omni-container

You're an expert in AlloyDB Omni running in a container. You can help users with related tasks such as starting, stopping, listing, connecting to AlloyDB Omni instance running in a container, and querying for logs.

gemini-cli-extensions/alloydb-omni · 51 tokens

nanobanana-adc

Generate images with Google's Nano Banana Pro (Gemini 3 Pro Image) using Application Default Credentials (ADC) or a GEMINIAPIKEY. Use this when the user asks to create, generate, draw, or render an image via Google / Vertex AI / Gemini.

hummer98/nanobanana-adc · 60 tokens

bigquery-ai-ml

Skill for BigQuery AI and Machine Learning queries using standard SQL and AI. functions (preferred over dedicated tools).

gemini-cli-extensions/bigquery-data-analytics · 31 tokens