tstack: Reusable Agent Skills for Claude Code and Codex

Repositoryt3dotgg/tstackTool

tstack provides curated agent skills for Claude Code and Codex to automate Git and pull request workflows. It enables autonomous PR generation, multi-model review consensus, and CI monitoring. The collection is designed for software developers using autonomous coding agents.

Key points

  1. Compatible with Claude Code and Codex, falling back to native tools if T3 Code features are unavailable.
  2. full-send automates testing, reviewing, opening, monitoring, and merging pull requests end-to-end.
  3. Features multi-agent loops like council (three provider models until consensus) and sol-loop (review with GPT Sol).
  4. Requires authenticated GitHub CLI (gh) and Python 3 for PR status monitoring scripts.
  5. Modular design allows customization via CLAUDE.md or AGENTS.md configuration files.

Why it matters

It demonstrates a practical pattern for orchestrating coding agents through chained CLI skills and multi-model consensus across different AI providers.

Analysis

Core Functionality and Problem Solved

tstack addresses common friction in daily development workflows when working with agentic coding assistants. Instead of manually inspecting CI outputs or writing repetitive pull request descriptions, it introduces pre-packaged skills. Notable capabilities include file-pr (concise problem-led descriptions), takeover (completing someone else's branch while maintaining author credit), and babysit-pr (watching CI and bot feedback to fix genuine findings).

Model Consensus Workflows

The collection highlights multi-model reviews:

  • council: Gathers feedback from three models across distinct providers until consensus is reached.
  • sol-loop: Iterates changes in a loop with GPT Sol.

Requirements and Maturity

Users need an authenticated GitHub CLI (gh) and python3 for babysit-pr's pr-wait script. Delegation across different providers requires delegate_task via T3 Code or a custom harness. Released under the MIT license, the repository acts as an extensible starter kit meant to be tailored within local agent configuration files (CLAUDE.md or AGENTS.md).

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 28 October 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Repository:coleam00/skills

    Cole's AI Skills: Modular Skill Files for Coding Agents

    The GitHub repository 'coleam00/skills' provides a collection of 33 practical skills designed for AI coding agents such as Claude Code. Instead of maintaining a monolithic 2,000-line CLAUDE.md instruction file, each skill resides in a standalone folder with a SKILL.md file and is loaded on demand. The set revolves around a standard development cycle: prime, plan, implement, validate, review, commit, and PR.

    482starsPython

    AI & LLMs· Tool

  • Repository:chhoumann/t3-pstack

    t3-pstack: Multi-Model Orchestration for Coding Agents

    t3-pstack adapts Lauren Tan's pstack and Michael Denyer's pstack-claude for T3 Code, dispatching subagents, review panels, and fan-outs across Claude, GPT, and Grok via T3's MCP tools.

    172starsJavaScript

    AI & LLMs· Tool

  • Repository:DanMcInerney/orchflows

    orchflows: Reusable AI Agent Workflows Defined in Markdown

    orchflows is a Python utility for designing and orchestrating reusable multi-agent workflows within subagent-capable environments like Claude Code or Codex.

    119starsPython

    AI & LLMs· Tool

  • Repository:vercel-labs/skills

    vercel-labs/skills: Universal CLI for AI Agent Skills

    skills is an open-source CLI by Vercel Labs designed to discover, install, and execute modular capabilities across coding agents including Claude Code, Cursor, OpenCode, and Codex.

    31.8kstarsTypeScript

    AI & LLMs· Tool

  • Repository:humanlayer/skills

    HumanLayer Skills: Modular Extensions for Claude Code

    HumanLayer's 'skills' repository delivers a curated set of modular extensions for Claude Code, focusing on configuration tuning, React type refinements, and automated agent loops.

    1.4kstarsTypeScript

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.