/explore

Start the change loop: compare options and settle scope before /plan. Find related work with openspec list --json and openspec context --json (CLI contract); read their pointers.

Change no repo file (limits); /plan logs answers. Explore precedes planning except review-page notes; use bounded mode under /plan. Standalone, run node .claude/skills/explore/scripts/step-title.mjs set EXPLORE --task "<the idea>".

Investigate the relevant flow

Read owning docs and source; trace trigger, result, and constraints. For non-code, read the process and authoritative sources. Separate observations from inferences. Run proportional, authorized checks: tests, scripts, builds; new code only in .scratch/. Report results before any plan; nothing outward. Name unavailable evidence and a later check.

For consequential choices, compare viable approaches, outcomes, costs; recommend with evidence. Before handoff, check material assumptions and failures against the flow; revise contradictions.

Questions during standalone exploration

Ask the shared way: two or three related ready choices, one if alone, within tool capacity. Track decisions and prerequisites in chat. Investigate a missing fact yourself; never ask the person to guess it.

Update dependencies after answers or evidence. Explain changed premises; reopen only affected decisions. Keep findings in chat, drawn as text when useful: chat shows no picture.

The 80/20 test: ask where a wrong guess makes the plan wrong, not merely different: scope, observable behavior, compatibility, acceptance criteria. Assume naming, placement, wording, and cheaply changed details, with reasons.

Search memory before asking

Before asking, recall the task and its likely paths once; read the originals cited:

node "$(git rev-parse --show-toplevel)/.claude/skills/memory/scripts/memory.mjs" recall <question>
node "$(git rev-parse --show-toplevel)/.claude/skills/memory/scripts/memory.mjs" areas <paths>

Treat dated facts as assumptions. Memory unavailable? Say so; continue with available sources.

Check for other work

For repo edits, check other work once:

node "$(git rev-parse --show-toplevel)/.claude/skills/explore/scripts/other-work.mjs"

Compare intent, not files: plans can overlap before edits.

• Overlap: name the work and why; add the overlap ask to the next group, or ask alone.
• No overlap: say nothing.
• A notes line: say it in one line and continue.

The exit round

Resolve remaining material choices the shared way:

• Apply 80/20 and tool capacity; ask only ready choices.
• Separate parts? Ask about a new workspace for each (how).
• Answers open another choice? Follow up; stop once none remains.
• A settled choice stays settled, nested calls included.
• Keep an unanswered material preference open, never called an assumption or evidence gap. Keep authorized defaults and the fallback when nobody can answer.

Summarize outcome, approach, reasons over a serious alternative, minor assumptions, and evidence limits.

• Bounded: return by the steps below.
• Standalone, typed by the person: offer next steps; only Plan it starts /plan.

When /plan invokes /explore

Planning uses bounded mode, including via /apply or /ship:

1. Reuse the conversation's intent, answers, and findings.
2. Search memory and other work unless checked; investigate only new material gaps.
3. Run the exit round for open choices; await dependent answers, retaining authorized/unattended defaults.
4. Return the summary to /plan.