github-swarm

github-swarm is a command for Claude Code from akhilyad/deployy. It costs 0 tokens per session (590 once invoked), scanned A, a copy of github-swarm, MIT.

A command that creates a group of specialised agents to manage a GitHub repository. The group can focus on maintenance, development, review, or issue triage, which means sorting and prioritising reported problems.

In plain words
What is it for?
Use it to analyse and label issues, find duplicates, review code, suggest improvements, manage documentation, and automate parts of pull-request work.
Why use it?
It divides repository work among agents instead of handling every issue or pull request manually. Options can add issue labels, pull-request improvements, and code reviews.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

Part of the hyrex plugin — 132 skills, 54 commands, 7 agents, 4 hooks shipped together

Good fit Use it to analyse and label issues, find duplicates, review code, suggest improvements, manage documentation, and automate parts of pull-request work.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/akhilyad/deployy/github-swarm
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.

Clone the repo
git clone --depth 1 https://github.com/akhilyad/deployy

Made for: Claude Code.

Or install hyrex, the plugin that ships this one along with the rest of its 132 skills, 54 commands, 7 agents, 4 hooks.

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 github-swarm

README.md
[![agentmods](https://agentmods.dev/badge/commands/akhilyad/deployy/github-swarm/github.svg)](https://agentmods.dev/commands/akhilyad/deployy/github-swarm)
Your own site
<a href="https://agentmods.dev/commands/akhilyad/deployy/github-swarm"><img src="https://agentmods.dev/badge/commands/akhilyad/deployy/github-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 github-swarm

Your own site · 80×15
<a href="https://agentmods.dev/commands/akhilyad/deployy/github-swarm"><img src="https://agentmods.dev/badge/commands/akhilyad/deployy/github-swarm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 590 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 100% 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00590
Opus 5.5 $0.00000 $0.00236
Sonnet 5.5 $0.00000 $0.00118
Haiku 4.5 $0.00000 $0.00059

Measured 13d ago against content hash 07f2bd96f467, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

github-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 13d 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

100% identical to github-swarm — 12 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.

.claude/commands/github/github-swarm.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

github swarm

Create a specialized swarm for GitHub repository management.

Usage

npx hyrex github swarm [options]

Options

  • --repository, -r <owner/repo> - Target GitHub repository
  • --agents, -a <number> - Number of specialized agents (default: 5)
  • --focus, -f <type> - Focus area: maintenance, development, review, triage
  • --auto-pr - Enable automatic pull request enhancements
  • --issue-labels - Auto-categorize and label issues
  • --code-review - Enable AI-powered code reviews

Examples

Basic GitHub swarm

npx hyrex github swarm --repository owner/repo

Maintenance-focused swarm

npx hyrex github swarm -r owner/repo -f maintenance --issue-labels

Development swarm with PR automation

npx hyrex github swarm -r owner/repo -f development --auto-pr --code-review

Full-featured triage swarm

npx hyrex github swarm -r owner/repo -a 8 -f triage --issue-labels --auto-pr

Agent Types

Issue Triager

  • Analyzes and categorizes issues
  • Suggests labels and priorities
  • Identifies duplicates and related issues

PR Reviewer

  • Reviews code changes
  • Suggests improvements
  • Checks for best practices

Documentation Agent

  • Updates README files
  • Creates API documentation
  • Maintains changelog

Test Agent

  • Identifies missing tests
  • Suggests test cases
  • Validates test coverage

Security Agent

  • Scans for vulnerabilities
  • Reviews dependencies
  • Suggests security improvements

Workflows

Issue Triage Workflow

  1. Scan all open issues
  2. Categorize by type and priority
  3. Apply appropriate labels
  4. Suggest assignees
  5. Link related issues

PR Enhancement Workflow

  1. Analyze PR changes
  2. Suggest missing tests
  3. Improve documentation
  4. Format code consistently
  5. Add helpful comments

Repository Health Check

  1. Analyze code quality metrics
  2. Review dependency status
  3. Check test coverage
  4. Assess documentation completeness
  5. Generate health report

Read the full file on GitHub · 122 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. 13d ago First seen · 122 lines · 0 tokens per session scan A 07f2bd96f467

Subscribe to this mod's changes

github-swarm is a command published in the GitHub repository akhilyad/deployy (0 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 590 tokens. A static security scan graded it A with 0 findings. It is 100% identical to github-swarm, differing in 12 lines, and is treated as a copy.