how · diff
git:20261012.14c3b4f to git:20261026.385852f
12 added, 24 removed. Audit A to A.
---
name: how
description: "Explain how code works by reading it: a subsystem's runtime flow, its architecture, where something should live. Use for \"how does X work\", \"X 는 어떻게 동작해\", \"이 구조 설명해줘\", \"이건 어디에 둬야 해\", or a walkthrough before changing code. Why it is this way, or why it was decided, is why."
---
# How
Explore the codebase to answer "how does X work?" questions. Produce architectural explanations at the level of a senior engineer onboarding onto a subsystem, enough to build a working mental model, not so much that it reads like annotated source code.
- ## Step 1. Assess Complexity
+ Explorers are the built-in read-only `Explore` subagent. The explainer is one `general-purpose` `Agent` on `opus`, told in its prompt that it only reads and writes the explanation and must not edit files.
+ ## 1. Assess complexity
+
If the scope is ambiguous, state your interpretation and explore. The user can redirect.
- - **Simple** (a single module, a small utility, a narrow question such as "how does function X work"): no explorers. One explainer explores and explains in a single pass. Go to Step 2b.
- - **Complex** (a subsystem spanning multiple files or services, a cross-cutting feature, a full architectural overview): spawn parallel explorers first, then hand off to the explainer. Go to Step 2a.
+ - **Simple** (a single module, a small utility, a narrow question such as "how does function X work"): no explorers and no explainer. Explore and explain it yourself in one pass, following the Instructions and Output Format in `references/explainer-prompt.md` (skip its explorer-findings parts). Go to step 4.
+ - **Complex** (a subsystem spanning multiple files or services, a cross-cutting feature, a full architectural overview): go to step 2.
When in doubt, take the simple path.
- ## Step 2a. Explore (complex questions only)
-
- Decompose the question into 2 to 4 exploration angles, each a distinct slice of the subsystem. Spawn all explorers in a single message:
-
- - `subagent_type`: `Explore` (the built-in read-only explorer)
-
- Each explorer gets the prompt in `references/explorer-prompt.md` with its angle filled in. Then go to Step 3.
-
- ## Step 2b. Direct Explain (simple questions)
-
- Explore and explain it yourself in one pass, following the Instructions and Output Format in `references/explainer-prompt.md` (skip its explorer-findings parts). Go to Step 4.
-
- ## Step 3. Synthesize (complex questions only)
+ ## 2. Explore (complex only)
- Once all explorers have returned, spawn one `Agent` subagent to synthesize their findings into one explanation. Synthesize once; do not re-run it per explorer:
+ Decompose the question into 2 to 4 angles, each a distinct slice of the subsystem. Spawn all explorers in a single message, each with `references/explorer-prompt.md` and its angle filled in.
- - `subagent_type`: `general-purpose`
- - `model`: `opus`
- - Tell it in the prompt that it only reads and writes the explanation; it must not edit files.
+ ## 3. Synthesize (complex only)
- Build its prompt from `references/explainer-prompt.md` with every explorer's findings filled in.
+ Once all explorers have returned, spawn one explainer with `references/explainer-prompt.md` and every explorer's findings filled in. Synthesize once; do not re-run it per explorer.
- ## Step 4. Present
+ ## 4. Present
- Present the explainer's output to the user. Light edits for clarity or context from the conversation are fine. Do not substantially rewrite it.
+ Present the explainer's output. Light edits for clarity or context from the conversation are fine. Do not substantially rewrite it.
- ## Output Format
+ ## Output format
The explanation uses the sections defined in `references/explainer-prompt.md`, dropping any that do not apply: Overview, Key Concepts, How It Works, Where Things Live, Gotchas.