SKILL·B06F28

codex-host

avelikiy
Updated 2 days ago
2 views
93
13
93
View on GitHub
Designgeneral

About

The codex-host skill runs the complete great_cto Codex pipeline with controlled writes, verification evidence, and human approval gates. Use it when developers need to execute or inspect full great_cto pipelines rather than individual skills. It requires preflight checks, uses operator-owned policy files, and manages the entire lifecycle including optional artifact releases.

Quick Install

Claude Code

Recommended
Primary
npx skills add avelikiy/great_cto -a claude-code
Plugin CommandAlternative
/plugin add https://github.com/avelikiy/great_cto
Git CloneAlternative
git clone https://github.com/avelikiy/great_cto.git ~/.claude/skills/codex-host

Copy and paste this command in Claude Code to install this skill

Documentation

Controlled Codex host

Use the supported CLI entrypoint. Do not imitate Claude Code hooks or manually chain roles: the controller reads shared/pipeline.toml, persists the cursor and owns every write and gate transition.

Preflight

great-cto codex-host doctor
great-cto codex-host list --dir /absolute/project

doctor.state=blocked means do not start. Docker may be unavailable when no checks/release policy is requested; GitHub CLI may be unavailable when the local adapter is used. The run store must not be group/world accessible.

Start

Policies must be operator-owned absolute files outside the worker project. Allowed paths are explicit controller write boundaries.

great-cto codex-host start \
  --dir /absolute/project \
  --prompt "the requested outcome" \
  --allow src,tests,docs \
  --checks-policy /absolute/operator/checks.json \
  --release-policy /absolute/operator/release.json

Read the returned status, pending and release object. Never treat exit 2 as success: it means a gate, manual action or blocked evidence requires attention.

Gates and recovery

Show the operator the exact gate/release summary and wait for explicit approval. Then pass back the controller-issued token; never synthesize or persist one in a project file.

great-cto codex-host approve RUN_UUID --token GATE_TOKEN
great-cto codex-host approve-release RUN_UUID --token RELEASE_TOKEN
great-cto codex-host resume RUN_UUID

Use recover only after inspecting the recorded reason. Recovery reuses the same candidate and refuses unknown partial writes. cancel revokes unexecuted approval but does not delete external audit evidence.

Release boundary

The local and GitHub Release adapters publish immutable artifacts and declare activation: none. They do not deploy traffic. Local rollback means selecting a previous directory; GitHub rollback is a newly gated superseding release. Production activation needs a separate adapter and approval contract.

Detailed policy schemas and limitations are in docs/HOST-CODEX.md.

GitHub Repository

avelikiy/great_cto
Path: skills/codex-host
0
agentic-codingai-agentsclaude-codeclaude-code-pluginclaude-code-skillsclaude-code-subagents
FAQ

Frequently asked questions

What is the codex-host skill?

codex-host is a Claude Skill by avelikiy. Skills package instructions and resources that Claude loads on demand, so Claude can perform codex-host-related tasks without extra prompting.

How do I install codex-host?

Use the install commands on this page: add codex-host to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.

What category does codex-host belong to?

codex-host is in the Design category, tagged general.

Is codex-host free to use?

Yes. codex-host is listed on AIMCP and free to install.

Related Skills

executing-plans
Design

Use the executing-plans skill when you have a complete implementation plan to execute in controlled batches with review checkpoints. It loads and critically reviews the plan, then executes tasks in small batches (default 3 tasks) while reporting progress between each batch for architect review. This ensures systematic implementation with built-in quality control checkpoints.

View skill
requesting-code-review
Design

This skill dispatches a code-reviewer subagent to analyze code changes against requirements before proceeding. It should be used after completing tasks, implementing major features, or before merging to main. The review helps catch issues early by comparing the current implementation with the original plan.

View skill
connect-mcp-server
Design

This skill provides a comprehensive guide for developers to connect MCP servers to Claude Code using HTTP, stdio, or SSE transports. It covers installation, configuration, authentication, and security for integrating external services like GitHub, Notion, and custom APIs. Use it when setting up MCP integrations, configuring external tools, or working with Claude's Model Context Protocol.

View skill
web-cli-teleport
Design

This skill helps developers choose between Claude Code Web and CLI interfaces based on task analysis, then enables seamless session teleportation between these environments. It optimizes workflow by managing session state and context when switching between web, CLI, or mobile. Use it for complex projects requiring different tools at various stages.

View skill