This workspace is home. Treat it that way.
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →This workspace is home. Treat it that way.
| リポジトリ | 説明 |
- **Be concise and direct** - Avoid repetitive explanations
This repository implements the deterministic runtime layer for GitHub-backed agentic development orchestration.
Purpose: fast rules for coding agents in this repo.
Instructions for Codex or other agents working in this repo.
**Status**: Approved
Bug fix designer — diagnoses root causes and writes fix plans for workers to execute
>These rules define how the agent should communicate, act, and collaborate with the user during development and automation tasks.The objective is to maintain clarity, reliability, and discipline while
<!-- gitnexus:start -->
**Type:** Deterministic Agent (Pricing & Quoting)
**Research Date**: 2026-01-21
**Note**: This project uses [bd (beads)](https://github.com/steveyegge/beads) for issue tracking. Use `bd` commands instead of markdown TODOs. See the **Issue Tracking with bd (beads)** section below
Repository-level operating rules for Codex and collaborators.
Ralph Loop that orchestrates Ralph Loops across a GitHub account/org.
[Engineering at Anthropic](/engineering)
[Engineering at Anthropic](/engineering)
Delegate code tasks and analysis to Codex CLI agents
- Agents extend `LlmAgent` or `BaseAgent`
**Purpose**: Coordinate multiple agents running in parallel to maximize efficiency and avoid conflicts.
I want to develop features in parallel using Git worktrees and subagents: $ARGUMENTS
Documentation for GreenLang AI Agent Workforce Deployment
Local Claude Code agents for DevTrack PM workflow — project-vision (PM), devtrack-engineer, post-generator
Demo the SubagentStop hook by spawning 3 agents and viewing the activity log
/* Most apps just need AI SDK directly */
**IMPORTANT**: This project uses **bd (beads)** for ALL issue tracking. Do NOT use markdown TODOs, task lists, or other tracking methods.
Agents support the "small steps, verify often" principle from `.claude/docs/APPROACH.md`.
> Claude Code: read this at the start of every session alongside CLAUDE.md.
- Before implementation, read `__RESOURCE_PATH__`.
**Search Demand:** VERY HIGH (launched yesterday, April 8, 2026)
> Last synced: 2026-04-21
**Objetivo Primordial:** Este documento y **todos los demás archivos `.md` que contienen reglas, directrices o conocimientos operativos** deben ser actualizados proactivamente por el Agente de IA. La
Use small, explicit roles. Do not delegate understanding or product truth.
Этот файл описывает, **как мы используем AI внутри проекта**. Он превращает
Sync agent configuration files to project
> **Purpose**: Define autonomous AI agents with roles, goals, and tools for DataOps workflows
Agentic Workflow — persistent AI development workflows with quality gates when you need them.
No two agents may edit the same file concurrently. Ownership during a workflow:
Run bootstrap-agents workflow.
**Responsibilities:**
**This tool coordinates Claude Code's actions. It does NOT write code or create content.**
**Launches multiple parallel agents for grunt work - same task, different inputs.**
The fundamental challenge in any complex problem is combinatorial explosion. The Hubble Space Telescope scheduling problem involves tens of thousands of observation requests, six scientific instrument
Gary Klein and Roberta Calderwood's field research with urban fireground commanders revealed something that challenges the foundation of most AI decision systems: **proficient decision-makers almost n
A fundamental tension in rational agent design: Commitment is computationally necessary (can't constantly reconsider every decision), but blind commitment is irrational (must respond to changing circu
In 1986, Gary Klein and colleagues studied fireground commanders — captains of firefighting companies — to understand how they made life-or-death decisions under conditions of extreme time pressure an
- Every commit should be associated with the relevant GitHub issue when one exists.
> **Contract alignment**: These docs align to ntask CLI Contract v1.0.0.
Use the installed `qrspi-codex-orchestrator` skill as the default orchestration layer for software-development work in this repository.
Skill instructions for git commit tasks.