github-swarm

A command that creates a group of specialized agents to manage a GitHub repository. GitHub is a service for hosting code, issues, and pull requests.

In plain words
What is it for?
Use it to analyze and label issues, review code, suggest pull-request improvements, categorize duplicates, or manage a repository with a chosen focus.
Why use it?
It divides repository work such as maintenance, development, review, or issue triage among agents with focused roles.

Command for Claude Code

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/f-amine/vibe-stack/github-swarm
Clone the repo
git clone --depth 1 https://github.com/f-amine/vibe-stack

Made for: Claude Code.

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 596 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00596
Opus 5 $0.00000 $0.00298
Sonnet 5 $0.00000 $0.00119
Haiku 4.5 $0.00000 $0.00060

Measured yesterday against content hash 8af56205449b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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 — 0 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 claude-flow 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 claude-flow github swarm --repository owner/repo

Maintenance-focused swarm

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

Development swarm with PR automation

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

Full-featured triage swarm

npx claude-flow 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. yesterday First seen · 122 lines · 0 tokens per session scan A 8af56205449b

Subscribe to this mod's changes

github-swarm is a command published in the GitHub repository f-amine/vibe-stack (21 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 596 tokens. A static security scan graded it A with 0 findings. It is 100% identical to github-swarm, differing in 0 lines, and is treated as a copy.