AGENT SKILL

how

Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.

License 许可
MIT
最近更新
2026-10-17
Stars
★ 0
Forks
0

01 前言 Front Matter

name
how
description
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.

02 资源文件 3

03 SKILL.md 正文

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 spawn_agent subagent with agent_type: "default" whose message opens with Read-only. Do not modify files, commit, or push. Explorers use the how explorer line in the pstack-models block in ~/.codex/AGENTS.md (default gpt-6.1-sol-xhigh), and every explainer uses the how explainer line (default gpt-6-astra-xhigh). A role value is <model>-<effort> with the effort as the last - token, so gpt-6.1-sol-xhigh spawns with model: "gpt-6.1-sol" and reasoning_effort: "xhigh". Spawn each subagent fresh, with fork_turns: "none" (fork_context: false on the older multi-agent tools), so it starts from its brief and file pointers, not this thread's history. Run a claude:<alias>-<effort> entry through ../../scripts/pstack-seat <entry> read <workdir> <prompt-file> <out-file> (path relative to this file) as a background terminal. If it exits non-zero (3 means the claude CLI is missing), use the default and say so. Set model and reasoning_effort from that line's value, or from the default if the block or the line is missing. Leave both unset when the value is auto or inherit-parent. If spawn_agent rejects a slug, use the default and say so. If it rejects the default, use the closest valid slug of the same family from its error message. Pick each subagent's reasoning level for the job, per the Subagents section of the poteto-mode skill.

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. Spawn all explorers in one turn, 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.

04 同仓库更多 Skills