菜单
Orchestrator/agent/Codex delegation matrix. Reference this when scoping a task to determine who owns what. Covers three Codex modes: reviewer-only (default), implementer+reviewer, and no Codex.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/grandamenium/cortextos --skill delegation-matrix命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
You need to write or update memory. This happens at session start, heartbeat, session end, or when you learn something worth keeping. Memory is how you maintain continuity across restarts and context compactions — without it, every session starts blind.
You need to write or update memory. This happens at session start, heartbeat, session end, or when you learn something worth keeping. Memory is how you maintain continuity across restarts and context compactions — without it, every session starts blind.
Migrate ANY cortextOS agent from the claude-code runtime to the live codex-app-server runtime. Use this whenever a user wants to convert, port, move, or switch a Claude-cortextOS agent to Codex / gpt-5-codex / gpt-5.5, "make agent X run on codex", "turn this claude agent into a codex agent", or asks how a Claude agent's CLAUDE.md / .claude/skills / .mcp.json / hooks map onto the codex-app-server adapter. Takes a source agent name and produces a SEPARATE codex-shaped agent (non-destructive, dry-run by default). Trigger even if they only say "migrate <agent> to codex" without naming the artifacts. Do NOT use for creating a brand-new codex agent from scratch (use `cortextos add-agent`) or for hermes/orchestrator/analyst runtimes.
基于 SOC 职业分类
正在显示 SKILL.md
| name | delegation-matrix |
| effort | low |
| description | Orchestrator/agent/Codex delegation matrix. Reference this when scoping a task to determine who owns what. Covers three Codex modes: reviewer-only (default), implementer+reviewer, and no Codex. |
| triggers | ["who owns","delegation","codex or agent","should codex","task scoping","who does this","delegation matrix","codex mode"] |
Reference when scoping any task. Dividing line: execution-heavy → Codex (if configured as implementer). Judgment-heavy → Agent always.
Codex is a configurable option. Pick the mode that matches your setup:
| Mode | Codex role | When to use |
|---|---|---|
| Mode 1 (default) | Reviewer only | Out of the box — Codex reviews Agent output before PR |
| Mode 2 | Implementer + reviewer | Codex is set up and trusted for implementation |
| Mode 3 | Not used | No Codex in your stack — Agent handles everything |
| Work type | Orchestrator | Agent | Codex (Modes 1+2) |
|---|---|---|---|
| Requirement intake from user | owns | — | — |
| Task decomposition + dispatch | owns | consults | — |
| Briefings and status to user | owns | input | — |
| Architecture decisions | — | owns | — |
| Spec writing + acceptance criteria | — | owns | — |
| Security and domain modeling | — | owns | — |
| Ambiguous / judgment calls | routes | owns | — |
| PR decisions (file, scope, merge) | — | owns | — |
| First-pass implementation (clear spec) | — | owns (Modes 1+3) / delegates (Mode 2) | owns (Mode 2) |
| Mechanical refactors and migrations | — | owns (Modes 1+3) / delegates (Mode 2) | owns (Mode 2) |
| Repetitive multi-file edits | — | owns (Modes 1+3) / delegates (Mode 2) | owns (Mode 2) |
| Test drafting and fixture setup | — | owns (Modes 1+3) / delegates (Mode 2) | owns (Mode 2) |
| Code review before PR | — | owns (Mode 3) | owns (Modes 1+2) |
For tasks >~20 lines or touching multiple files:
For one-liners and config changes: Agent writes directly in all modes.
Even in Mode 2, some work stays with the Agent:
Deployment note: replace "Orchestrator" / "Agent" with your actual agent names.
