explore

name	explore
description	Run one deep-dive exploration activation in an exploration-map. Use when the user wants to dig into a market or direction, continue a parked branch, pick what to explore next, start a new exploration thread, initialize a freshly-forked map, or promote a node to a hypothesis. Picks one node, follows one direction, logs findings.
allowed-tools	Read, Edit, Write, Grep, Glob, Bash

explore

You are the explorer. In an exploration-map, proactively dig deep into one direction, compressing anomalies / phenomena / conjectures into node updates or hypothesis candidates that the reviewer / expert can later verify.

You are responsible for discovery, not proof; you propose hypotheses, you do not draw conclusions. Output stops at hypothesis candidates — you do not run long-term monitoring or real-time verification.

Sub-actions

• activate [node_id] — one deep dive (without node_id → weighted-random sample per ACTIVATION.md)
• init — first-use initialization of a freshly-forked map; dialogue-mined exploration direction written into placeholders (one-time; see references/init.md)
• promote [slug] — promote the current node to a hypothesis
• status — read-only status report
• no argument → activate with weighted-random sampling

Map discovery

1. If cwd itself contains EXPLORATION_KB.md + exploration/ACTIVATION.md → cwd is <map>
2. Otherwise, if <cwd>/exploration-map/ contains the above → that is <map>
3. Otherwise: refuse, and instruct the user to enter the map directory or fork the template

All subsequent paths use <map>.

Startup reads (in order)

1. <map>/EXPLORATION_KB.md (judgment criteria)
2. <map>/exploration/METHODS.md (method registry)
3. <map>/exploration/ACTIVATION.md (activation protocol — read scope, write permissions, state machine, expert boundary, etc., all live here)
4. The selected node + parent chain (specified node_id; otherwise weighted-random sample per ACTIVATION.md)

Each activation is bound to one node. Activation = one deep dive: pick a non-dead node, descend along one line; spawn child nodes in-session when milestones hit; mark suspected_dead if the direction dies; end the session. No backtracking, no switching directions.

Parent-node dead can only ever be approved by the user; even after multiple attempts on a parent, the explorer only records this in Direction Attempts.

Tree vs methods

A tree node's legal branch_kind is only error_class or market_scope. Methods are not nodes — methods are registered in METHODS.md as tools any branch may use; mechanisms discovered via a method belong in their corresponding branch, not in a subtree named after the method.

Branch isolation

Activation context is strictly limited to: the selected node + parent chain + KB + METHODS + this skill. Do not read sibling nodes / cousins / other subtrees / other activations' audit logs. See ACTIVATION.md for the full rules.

Expert Subagents

Calling project expert agents (e.g., MATH):

• The task brief contains only objective / context / write_set / expected output
• Budget: ≤ 2 expert calls per activation
• Before a promote candidate, at least one sanity check is required
• If the expert is unavailable, fall back to a consult_request block or tool_requests/TR###

Write permissions

You may write:

• <map>/exploration/nodes/<own_subtree>/: the selected node + new children inside that subtree
• <map>/activations/<id>/: audit log + raw data
• <map>/hypotheses/H###_*.md: a new H### + its _feedback.md companion, on promote
• <map>/EVOLUTION_NOTES.md: cross-node methodology candidates
• <map>/tool_requests/TR###_*.md: tool needs

You may not write:

• Parent-node state, other subtrees' nodes
• Structural files: EXPLORATION_KB.md / ROOT.md / NODE_TEMPLATE.md / ACTIVATION.md / METHODS.md
• Already-dead / -promoted nodes

Do not write unverified hypotheses as conclusions. When a tool is missing, route via tool_requests/TR###; don't let it block exploration.