how

Files (4)

• SKILL.md
• openai.yaml · agents/
• explainer-prompt.md · references/
• explorer-prompt.md · references/

SKILL.md (first lines)

# 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.

Each spawn below names a key under `roles` in `~/.codex/pstack/models.yaml`. Use its value and the file's `reasoning_effort`, or the stated default when missing. Omit `model` for `inherit-parent`.

## Step 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.

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:

- `model`: the `how-explorer` line, default `gpt-6-luna`
- brief: explicitly read-only, with no file edits. Use a unique snake_case task name.

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)

Spawn one child agent that explores and explains in one pass:

- `model`: the `how-explainer` line, default `gpt-6-astra`
- brief: explicitly read-only, with no file edits. Use a unique snake_case task name.

Build its prompt from `references/explainer-prompt.md` without the explorer-findings section. Go to Step 4.

## Step 3. Synthesize (complex questions only)

Once all explorers have returned, spawn one child agent to synthesize their findings into one explanation:

- `model`: the `how-explainer` line, default `gpt-6-astra`
- brief: explicitly read-only, with no file edits. Use a unique snake_case task name.

Build its prompt from `references/explainer-prompt.md` with every explorer's findings filled in.

## Step 4. Present

Collect the explainer's output and interrupt every finished child. Present the result to the user. Light edits for clarity or context from the conversation are fine.

## 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.

From vuongquocphong/pstack-codex, MIT.

More from vuongquocphong/pstack-codex