Codex Team
Align AgentOps workflows with Claude Code 2.1.x slash commands, sub-agent frontmatter, and worktree isolation when running parallel coding teammates.
Overview
codex-team is a journey-wide agent skill that documents the Claude Code 2.1.x feature contract AgentOps skills rely on—usable whenever a solo builder needs to align parallel agents, slash commands, and worktree isolation
Install
npx skills add https://github.com/boshu2/agentops --skill codex-teamWhat is this skill?
- Pins baseline to Claude Code 2.1.x (verified against changelog 2.1.75) with upstream CHANGELOG as source of truth
- Documents preferred slash commands: /agents, /hooks, /permissions, /memory, /mcp, /output-style, /effort, /color
- Specifies modern sub-agent frontmatter: model, description, tools, memory scope, background, worktree isolation
- Prioritizes Claude-native parallel safety: session `claude --worktree`, agent `isolation: worktree`, and sparse `worktre
- Shared contract across AgentOps skills so docs do not drift to legacy naming
- Baseline target: Claude Code 2.1.x family
- Last verified against upstream changelog: 2.1.75
- Documents 8 core slash commands including /effort and /color
Adoption & trust: 881 installs on skills.sh; 384 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your AgentOps skills and docs reference Claude Code features inconsistently, so parallel agents and hooks break when the CLI surface changes.
Who is it for?
Indie builders maintaining Claude Code agent teams, custom sub-agents, or monorepo parallel sessions who want one shared compatibility contract.
Skip if: Builders who only use a single non-Claude IDE agent with no `.claude/agents` layout and no need for worktree or hooks documentation.
When should I use this skill?
You are authoring or updating AgentOps skills and need the shared Claude Code 2.1.x feature baseline for commands, agents, and worktree isolation.
What do I get? / Deliverables
You get a single verified baseline for slash commands, sub-agent frontmatter, and worktree isolation patterns that downstream AgentOps skills can cite instead of legacy naming.
- Aligned AgentOps skill references to current slash commands and agent frontmatter
- Documented worktree and sparse-checkout patterns for parallel writes
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Define `.claude/agents` with `isolation: worktree` before two features land in the same monorepo paths.
Prefer `/mcp` and `/permissions` in skill text so MCP servers attach without ad-hoc CLI flags.
Verify parallel PR bots use `-w` / worktree settings so reviewers do not stomp the same files.
Bump the changelog verification note after upstream 2.1.x releases so hooks docs stay accurate.
Document which `/output-style` and `/effort` defaults your public agent recipes assume for customers.
How it compares
Use as an internal compatibility spec for Claude Code—not a substitute for Anthropic’s official docs or a generic MCP integration skill.
Common Questions / FAQ
Who is codex-team for?
Solo and indie developers orchestrating Claude Code with custom agents, hooks, and parallel worktrees who need AgentOps skills to stay on the same 2.1.x feature baseline.
When should I use codex-team?
During Build when configuring agent-tooling; before Ship when isolating parallel writers; and during Operate when updating runbooks after a Claude Code release—any time you need the current slash-command and worktree contract.
Is codex-team safe to install?
It is documentation-heavy metadata for agent workflows; review the Security Audits panel on this Prism page and only grant the shell, git, and filesystem access your own AgentOps scripts actually require.
SKILL.md
READMESKILL.md - Codex Team
# Claude Code Latest Features Contract This document is the shared source of truth for Claude Code feature usage across AgentOps skills. ## Baseline - Target Claude Code release family: `2.1.x` - Last verified against upstream changelog: `2.1.75` - Changelog source: `https://raw.githubusercontent.com/anthropics/claude-code/main/CHANGELOG.md` ## Current Feature Set We Rely On ### 1. Core Slash Commands Skills and docs should assume these commands exist and prefer them over legacy naming: - `/agents` - `/hooks` - `/permissions` - `/memory` - `/mcp` - `/output-style` - `/effort` — set model effort level (low/medium/high). Opus 4.6 defaults to medium. - `/color` — set prompt-bar color per session (useful for distinguishing parallel sessions) Reference: `https://code.claude.com/docs/en/slash-commands` ### 2. Agent Definitions For custom teammates in `.claude/agents/*.md`, use modern frontmatter fields where applicable: - `model` - `description` - `tools` - `memory` (scope control) - `background: true` for long-running teammates - `isolation: worktree` for safe parallel write isolation Reference: `https://code.claude.com/docs/en/sub-agents` ### 3. Worktree Isolation When parallel workers may touch overlapping files, prefer Claude-native isolation features first: - Session-level isolation: `claude --worktree` (`-w`) - Agent-level isolation: `isolation: worktree` - Sparse checkout: `worktree.sparsePaths` setting — limit worktree to relevant directories in large monorepos If unavailable in a given runtime, fall back to manual `git worktree` orchestration. Reference: changelog `2.1.49`, `2.1.50`, and `2.1.75`. ### 4. Hooks and Governance Events Hooks-based workflows should include modern event coverage: - `WorktreeCreate` - `WorktreeRemove` - `ConfigChange` - `SubagentStop` - `TaskCompleted` - `TeammateIdle` - `PostCompact` — fires after session context compaction. Use for auto-recovery (e.g., re-inject context). - `InstructionsLoaded` — fires when CLAUDE.md loads. Use for policy enforcement. **HTTP hooks:** Hooks can POST JSON to a URL and receive JSON responses, in addition to shell script execution. Use these for auditability, policy enforcement, and cleanup. Reference: `https://code.claude.com/docs/en/hooks` ### 5. Settings Hierarchy Skill guidance must respect settings precedence: 1. Enterprise managed policy 2. Command-line args 3. Local project settings 4. Shared project settings 5. User settings Reference: `https://code.claude.com/docs/en/settings` ### 6. Agent Inventory Command Use `claude agents` as the first CLI-level check to confirm configured teammate profiles before multi-agent runs. Reference: changelog `2.1.50`. ### 7. Session Management - `--from-pr <url>` — start or resume a session linked to a specific GitHub PR - `--worktree` (`-w`) — start session in an isolated git worktree Reference: `https://code.claude.com/docs/en/cli-reference` ### 8. Tool Enhancements - **Read tool:** `pages` parameter for PDFs — read specific page ranges (e.g., `pages: "1-5"`). Large PDFs (>10 pages) require this parameter. - **Bash tool:** Wildcard permission patterns — `Bash(npm *)` or `Bash(* install)` for flexible auto-approval. ### 9. Effort Levels The `/effort` command controls model reasoning depth: - `low` — fast, shallow reasoning. Good for research/exploration agents. - `medium` — balanced (Opus 4.6 default). - `high` — deep reasoning. Good for implementation and complex debugging. Skill recommendation: set effort per agent role — low for judges/explorers, high for implementors. ## Skill Authoring Rules 1. Do not reference deprecated permission command names (`/allowed-tools`, `/approved-tools`). 2. Multi-agent skills (`council`, `swarm`, `research`, `crank`, `codex-team`) must explicitly point to this contract. 3. Prefer declarative agent isolation (`isolation: worktree`) over ad hoc branch/worktree shell choreography where runtime supports it. 4. Keep manual `git worktree` fallback documen