how

Files (3)

• SKILL.md
• 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.

Every spawn is a `subagent` call. It has no `subagent_type`, so the role is the prompt you write, and it has no `readonly` flag, so each brief states that the work is read-only and that no files may be edited. Explorers and the explainer take their routes from the `explorer` and `explainer` roles, per the shared rule below.

**Child model selection may be unavailable.** Before the first spawn in a session, glance at the `subagent` tool's own schema. When it declares `provider`, `model`, and `reasoning_effort`, pass the role's route from `config/models.yml` of this repo (or the user's `~/.dsh/pstack-models.yml`). When it declares only `prompt`, `description`, and `cwd`, every child runs on the parent's route: omit the route entirely, and get the diversity this step needs from the briefs instead. Never pass a field the schema does not declare.

Reference prompt templates live beside this file, at absolute paths under this skill folder. Read the template with the `read` tool and paste its text into the brief. A child cannot resolve a relative path against this file.

- `references/explorer-prompt.md`
- `references/explainer-prompt.md`

## 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. Spawn one explainer that explores and explains in one pass, built from `references/explainer-prompt.md` without the explorer-findings section. 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.

## 2. Explore (complex only)

Decompose the question into 2 to 4 angles, each a distinct slice of the subsystem. Issue all explorer calls in a single message, each with `references/explorer-prompt.md` and its angle filled in.

## 3. Synthesize (complex only)

Once all explorers have returned, spawn one explainer with `references/explainer-prompt.md` and every explorer's findings filled in.

## 4. Present

Present the explainer's output. Light edits for clarity or context from the conversation are fine. Do not substantially rewrite it.

## 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 hidenobunagai/dsh-pstack, MIT.

More from hidenobunagai/dsh-pstack