github-multi-repo

github-multi-repo is a skill for Claude Code from ruvnet/ruv-FANN. It costs 21 tokens per session (5,827 once invoked), scanned A, a copy of github-multi-repo, MIT.

A coordination tool for teams that maintain several related Git repositories, such as separate frontend, backend, and shared-code projects.

In plain words
What is it for?
Use it to coordinate changes across repositories, synchronize dependencies, test integrations, manage shared templates, and coordinate deployments.
Why use it?
It helps keep packages, versions, integrations, and repository structures aligned across projects.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the TodoWrite tool.

Good fit Use it to coordinate changes across repositories, synchronize dependencies, test integrations, manage…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ruvnet/ruv-fann/github-multi-repo
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.

Any agent
npx skills add ruvnet/ruv-FANN --skill github-multi-repo
Clone the repo
git clone --depth 1 https://github.com/ruvnet/ruv-FANN

Made for: Claude Code.

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-multi-repo

README.md
[![agentmods](https://agentmods.dev/badge/skills/ruvnet/ruv-fann/github-multi-repo.svg)](https://agentmods.dev/skills/ruvnet/ruv-fann/github-multi-repo)
Your own site
<a href="https://agentmods.dev/skills/ruvnet/ruv-fann/github-multi-repo"><img src="https://agentmods.dev/badge/skills/ruvnet/ruv-fann/github-multi-repo.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,827 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 $0.00021 $0.05827
Opus 5 $0.00010 $0.02913
Sonnet 5 $0.00004 $0.01165
Haiku 4.5 $0.00002 $0.00583

Measured 3d ago against content hash ab86c4e0b303, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

github-multi-repo 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 3d 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-multi-repo — 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/skills/github-multi-repo/SKILL.md · 875 lines

How it starts

The opening of the file, as written. The whole thing — 875 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Multi-Repository Coordination Skill

Overview

Advanced multi-repository coordination system that combines swarm intelligence, package synchronization, and repository architecture optimization. This skill enables organization-wide automation, cross-project collaboration, and scalable repository management.

Core Capabilities

🔄 Multi-Repository Swarm Coordination

Cross-repository AI swarm orchestration for distributed development workflows.

📦 Package Synchronization

Intelligent dependency resolution and version alignment across multiple packages.

🏗️ Repository Architecture

Structure optimization and template management for scalable projects.

🔗 Integration Management

Cross-package integration testing and deployment coordination.

Quick Start

Initialize Multi-Repo Coordination

# Basic swarm initialization
npx claude-flow skill run github-multi-repo init \
  --repos "org/frontend,org/backend,org/shared" \
  --topology hierarchical

# Advanced initialization with synchronization
npx claude-flow skill run github-multi-repo init \
  --repos "org/frontend,org/backend,org/shared" \
  --topology mesh \
  --shared-memory \
  --sync-strategy eventual

Synchronize Packages

# Synchronize package versions and dependencies
npx claude-flow skill run github-multi-repo sync \
  --packages "claude-code-flow,ruv-swarm" \
  --align-versions \
  --update-docs

Optimize Architecture

# Analyze and optimize repository structure
npx claude-flow skill run github-multi-repo optimize \
  --analyze-structure \
  --suggest-improvements \
  --create-templates

Features

1. Cross-Repository Swarm Orchestration

Repository Discovery
// Auto-discover related repositories with gh CLI
const REPOS = Bash(`gh repo list my-organization --limit 100 \
  --json name,description,languages,topics \
  --jq '.[] | select(.languages | keys | contains(["TypeScript"]))'`)

// Analyze repository dependencies
const DEPS = Bash(`gh repo list my-organization --json name | \
  jq -r '.[].name' | while read -r repo; do
    gh api repos/my-organization/$repo/contents/package.json \
      --jq '.content' 2>/dev/null | base64 -d | jq '{name, dependencies}'
  done | jq -s '.'`)

// Initialize swarm with discovered repositories
mcp__claude-flow__swarm_init({
  topology: "hierarchical",
  maxAgents: 8,
  metadata: { repos: REPOS, dependencies: DEPS }
})

Read the full file on GitHub · 875 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. 3d ago First seen · 875 lines · 21 tokens per session scan A ab86c4e0b303

Subscribe to this mod's changes

github-multi-repo is a skill published in the GitHub repository ruvnet/ruv-FANN (378 stars, last pushed 28d ago), licensed MIT. It adds 21 tokens to every session and 5,827 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to github-multi-repo, differing in 0 lines, and is treated as a copy.