lauren
e8d856f027
* docs(pstack): port the September skill audit cuts from the internal tree Port of the 2026-09-01 to 2026-09-07 audit program on the internal skill tree. Deletion-only density cuts and the mannered prose pass applied wherever the OSS sentence is the same sentence. Two new principle leaves, Attack the Premise and Test Behavior Not Implementation, with their index lines. Critique mode removed from how and its callers. PR-body briefing rules in opening-a-pr and technical-writing. Model pins stay on the setup-pstack role mechanism. No internal path, slug, or name added. * docs(pstack): restore the autopilot chooser rule that multi-phase-plan cites multi-phase-plan step 4 picks between autopilot-full and autopilot-stack "per the rule at the end of playbooks/autopilot-stack.md". The density pass removed that paragraph and left the pointer dangling. Restore the paragraph verbatim. The chooser is a rule, not a restatement, and no other file states it. Addresses the Bugbot finding on PR #329. --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2.7 KiB
name, description, disable-model-invocation
| name | description | disable-model-invocation |
|---|---|---|
| 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. | true |
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
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:
subagent_type:generalPurposemodel: your configured how-explorer model (defaultgrok-4.6-fast-xhigh)readonly:true
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 Task subagent that explores and explains in one pass:
subagent_type:generalPurposemodel: your configured how-explainer model (defaultclaude-fable-5-1-thinking-max)readonly:true
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 Task subagent to synthesize their findings into one explanation:
subagent_type:generalPurposemodel: your configured how-explainer model (defaultclaude-fable-5-1-thinking-max)readonly:true
Build its prompt from references/explainer-prompt.md with every explorer's findings filled in.
Step 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.
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.