Skip to content
Development
Skill

/codex-explain

Explain complex code via Codex exec. Use when: understanding complex logic, tracing data flow, onboarding to unfamiliar code. Not for: code review (use codex-code-review), exploration (use code-explore). Output: structured explanation at chosen depth.

From plugin
sd0x-dev-flow
18899 skills16 agents5 hooks
Install
$ npx -y skills add sd0xdev/sd0x-dev-flow --skill codex-explain --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/codex-explain

Context preview

The summary Claude sees to decide when to auto-load this skill.

Explain complex code via Codex exec. Use when: understanding complex logic, tracing data flow, onboarding to unfamiliar code. Not for: code review (use codex-code-review), exploration (use code-explore). Output: structured explanation at chosen depth.

SKILL.md

codex-explain.SKILL.md
name: codex-explain
description: "Explain complex code via Codex exec. Use when: understanding complex logic, tracing data flow, onboarding to unfamiliar code. Not for: code review (use codex-code-review), exploration (use code-explore). Output: structured explanation at chosen depth."
allowed-tools: Read, Grep, Glob, Bash(node:*), Write

Codex Explain Skill

Trigger

  • Keywords: explain code, what does this do, how does this work, code walkthrough

When NOT to Use

  • Code review (use `codex-code-review`)
  • Bug investigation (use `bug-fix` or `issue-analyze`)
  • Architecture overview (use `code-explore`)

Workflow

Read target → [Collect context] → Codex explain → Output explanation

Step 1: Read Target File

Read file content. If `--lines` specified, extract only that range.

Step 2: Codex Explanation

Dispatch per `@skills/codex-code-review/references/codex-transport.md` § Start with the explanation prompt. See `references/codex-prompt-explain.md`.

Depth Levels

| Level | Description | | ------ | ---------------------------------------------------- | | brief | One-sentence summary | | normal | Functional overview + execution flow + key concepts (default) | | deep | + Design patterns + complexity + issues + dependencies |

Output

## Code Explanation: <target>
- **Depth**: brief / normal / deep
- **Summary**: <functional overview>
- **Execution flow**: <key paths>
- **Key concepts**: <patterns, abstractions>

Verification

  • [ ] Codex independently researched project context (imports, callers)
  • [ ] Explanation matches requested depth level
  • [ ] Key concepts are identified and explained

References

  • Explanation prompt: `references/codex-prompt-explain.md`

Examples

Input: /codex-explain src/service/order/order.service.ts
Action: Read file → Codex explain (normal) → Functional summary + detailed explanation

Input: /codex-explain src/service/xxx.ts --depth deep
Action: Read file → Codex explain (deep) → Patterns + complexity + issues

Input: /codex-explain src/xxx.ts --lines 50-100
Action: Read lines 50-100 → Codex explain → Focused explanation
Read more
Ships withsd0x-dev-flow

Language: English | 繁體中文 | 简体中文 | 日本語 | 한국어 | Español The harness layer for Claude Code. Let the model choose the path. Keep "done" verifiable. Full control plane on Claude Code. Skills-only distribution for Codex CLI and other compatible agents.

Get the whole plugin

Other skills on sd0x-dev-flow.