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 read-only general-purpose subagent. Explorers use the how explorer line in the pstack models config (default sonnet), and every explainer uses the how explainer line (default opus). Use the pstack-harness skill to resolve each spawn's model, effort, and agent type. Its Spawn a role section also covers a missing config, inherit-parent, and a rejected value.
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.mdwith the Direct exploration instructions. Omit Explorer Findings and Synthesis. 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.
If the repo has a GitNexus index (.gitnexus/ exists) and gitnexus is on PATH, refresh it first — run gitnexus analyze --index-only once yourself before spawning anything (it is incremental and a no-op when up to date; never run it from parallel arms). Then seed exploration: gitnexus query "<concept>" for execution flows, gitnexus context <symbol> for callers/callees, gitnexus trace <from> <to> for the path between two symbols. Graph results choose where to read; the code itself remains the source of truth — the index reflects the last analyzed commit and never sees uncommitted edits. Without the index or the CLI, explore normally. When the repo has no index but gitnexus is on PATH, after answering a complex question, you may suggest gitnexus analyze to the user once for repos worth exploring again.
2. Explore (complex only)
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.
3. Synthesize (complex only)
Once all explorers have returned, spawn one explainer with references/explainer-prompt.md, every explorer's findings, and the Synthesis instructions filled in. Omit Direct exploration.
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.