OneLinersCommand workbench
Guides
Operational guides

Complete procedures with a way back.

Searchable, versioned procedures with prerequisites, verification, concrete output, and rollback.

Guides
243
Favorites
0
243 launch guides · 2601 reviewed steps
5 of 243 guides

AI/ML · Software Engineering · Security

Package reusable Codex workflows with Skills, plugins, hooks, and MCP

Turn a proven workflow into a narrowly triggered SKILL.md, package it in a versioned Codex plugin, add fail-closed policy hooks and least-privilege MCP dependencies, test activation and denial paths, distribute through a controlled marketplace, and revoke safely.
Save to collectionCreate a collection in the sidebar first.
caution180 minadvanced10 stepsCodex

AI/ML · Software Engineering · Security

Complete a repository change safely with Codex

Use Codex to investigate an unfamiliar repository, freeze scope and acceptance criteria, implement a focused change, run proportional tests, review the complete diff, commit intentionally, and recover without erasing unrelated work.
Save to collectionCreate a collection in the sidebar first.
caution120 minadvanced10 stepsCodex CLI

AI/ML · Software Engineering · Security

Set up Codex CLI safely from zero

Install and authenticate Codex CLI, establish project trust, write layered AGENTS.md instructions, create read-only and workspace-write profiles, constrain network access and approvals, and verify the effective configuration before real changes.
Save to collectionCreate a collection in the sidebar first.
caution90 minadvanced10 stepsCodex CLI

AI/ML · Software Engineering · Security

Automate repository maintenance safely with Codex

Combine codex exec, the TypeScript Codex SDK, and openai/codex-action@v1 into bounded maintenance workflows with read-only defaults, scoped credentials, structured artifacts, explicit write jobs, human review gates, and resumable failure handling.
Save to collectionCreate a collection in the sidebar first.
caution180 minadvanced10 stepsNode.js

AI/ML · Security · Software Engineering

Connect an AI coding assistant to MCP servers and review permissions before enabling tools

Evaluate an MCP server as executable supply chain and delegated authority, pin its identity, constrain a local runtime or verify a remote trust endpoint, configure a positive tool allowlist, review OAuth scopes, observe real effects, test prompt injection, set per-tool approvals and rehearse complete removal.
Save to collectionCreate a collection in the sidebar first.
caution180 minintermediate10 stepsCodex desktop, CLI, or IDE extension