🔀
AutomationPython

Cross-Agent Delegation

by alinaqi

Cross-Agent Delegation is an Automation skill for Claude Code, published by alinaqi in maggy.

704 stars57 forkson alinaqi/maggyAdded 2026/08/23Repository updated 2026/08/18
ai-codingclaudeclaude-codedeveloper-toolsproject-initializationpythonreactsecuritytypescript
Install in seconds
Install Cross-Agent Delegation
Copy Cross-Agent Delegation into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/alinaqi/maggy/tree/main/skills/cross-agent-delegation ~/.claude/skills/cross-agent-delegation

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/alinaqi/maggy.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/cross-agent-delegation/SKILL.md in alinaqi/maggy
Installs to
~/.claude/skills/cross-agent-delegation
Collection
One of 25 skills cataloged from this repository
Category
Automation — 2226 skills

What Cross-Agent Delegation does

Cross-Agent Delegation routes coding tasks between Claude, Kimi, and Codex using iCPG signals and mnemos checkpoints. Use it when you want automated delegation, scoring, and post-change review in Claude Code.

Cross-Agent Delegation is cataloged under Automation on DirSkills. Cross-Agent Delegation comes from a repository tagged ai-coding, claude, claude-code, developer-tools and project-initialization.

Documentation

README

Cross-Agent Delegation

Claude Code orchestrates task routing to Kimi and Codex. The user interacts with Claude only — delegation happens behind the scenes.


Tool Detection

At session start, detect available tools:

command -v kimi &>/dev/null && HAS_KIMI=true || HAS_KIMI=false
command -v codex &>/dev/null && HAS_CODEX=true || HAS_CODEX=false

Codex Auto-Review (Stop Hook — Automatic)

When Codex is installed, a Stop hook reviews code after tests pass:

  1. TDD loop check runs tests
  2. codex-auto-review.sh runs Codex on the diff
  3. Critical/High findings feed back to Claude (exit 2)
  4. Clean reviews pass through (exit 0)

Fully automatic. No user or Claude action needed.


Kimi Delegation (Claude Orchestrates)

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Cross-Agent Delegation

  • What else does alinaqi publish alongside Cross-Agent Delegation?

    Cross-Agent Delegation is one of 25 skills that DirSkills catalogs from alinaqi/maggy, the repository it ships in. Its siblings there include AI Engine Optimization, AI Models Reference and AWS Aurora. Each one is a separate skill with its own page in this directory, installs the same way Cross-Agent Delegation does, and is maintained by alinaqi in that same repository. The rest of the collection is listed on the alinaqi/maggy page.

  • How does Cross-Agent Delegation compare to other Automation skills?

    Cross-Agent Delegation ranks #1078 by stars among the 2226 Automation skills in this catalog. The most-starred ones next to it are Autonomous Loops, Autonomous Agent Harness and Automation Audit Ops. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Cross-Agent Delegation against them. Open each page to compare what they document and how they install.

More from alinaqi/maggy

Cross-Agent Delegation is one of 25 skills cataloged on DirSkills from alinaqi/maggy.

See all 25 skills →
🤖
2026/08/23

AI Engine Optimization

AI Engine Optimization helps shape pages for AI search engines and chat answers. It uses semantic triples, page templates, and content clusters to improve how content is cited in generated responses.
SEO
70457
🤖
2026/08/23

AI Models Reference

AI Models Reference lists current Claude, OpenAI, Gemini, Eleven Labs, Replicate, and related model choices with example APIs. Use it when you need to pick a model for reasoning, code, vision, embeddings, voice, or image generation.
AI Engineering
70457
🗄️
2026/08/23

AWS Aurora

AWS Aurora covers serverless v2, RDS Proxy, Data API, and connection pooling for MySQL- and PostgreSQL-compatible workloads. Use it when setting up Aurora-backed apps, especially Lambda and other serverless services.
DevOps
70457
🗄️
2026/08/23

AWS DynamoDB

AWS DynamoDB covers single-table design, access-pattern modeling, and GSI patterns for building queries around how data is read. Use it when designing DynamoDB schemas or implementing SDK v3 access in TypeScript or Python.
DevOps
70457
🤝
2026/08/23

Agent Teams

Agent Teams coordinates a default roster of Claude Code agents for feature work. It enforces a fixed TDD pipeline from spec and tests through review, security checks, and PR creation.
AI Engineering
70457
🤖
2026/08/23

Agentic Development

Agentic Development builds autonomous AI agents that plan, use tools, and verify multi-step tasks. It uses Pydantic AI for Python and Claude Agent SDK for Node.js/Next.js projects.
AI Engineering
70457