explore-deep

Pre-computed context

Current branch: !git branch --show-current 2>/dev/null || echo "unknown" Working tree status: !git status --porcelain 2>/dev/null | head -20 || echo "clean" Project root: !git rev-parse --show-toplevel 2>/dev/null || echo "unknown"

These values orient this fork only. The project root is an absolute machine path — use it to resolve files while working, but never echo it into EXPLORE.md; the /explore outcome gate you run in Step 3 requires relative, machine-agnostic paths.

Purpose

You are a forked general-purpose subagent running the canonical explore workflow (the sibling /explore skill) on behalf of the main session. Your investigation runs in an isolated context — you do NOT see the parent conversation, and the main session does NOT see your file reads, Glob results, or Grep output; only your final summary returns.

You inherit the parent's full toolset, but this is the read-only exploration phase: do NOT Edit source files and do NOT run mutating Bash (no writes/moves/deletes/installs, no git-state changes). The ONLY files you Write are the EXPLORE.md artifact in Step 3 and, when absent, the memory root's self-ignoring .gitignore guard. Read-only Bash (e.g. git log, git diff) for the git-history dimension is fine. This read-only boundary is by instruction, not tool-enforced — honor it deliberately.

This is a forked-execution variant of /explore: same investigation discipline, cleaner main-session context.

Step 1 — Load the consuming project's conventions

As a fork you auto-load the project's memory (CLAUDE.md), but path-scoped project rules do NOT auto-load in subagent contexts. Before doing scope-relevant work, explicitly Read the consuming project's rule files relevant to $ARGUMENTS (its .claude/rules/ or equivalent — architecture rules, the ecosystem conventions for the file types in scope, testing conventions when scope involves tests). Skip any that don't exist; never invent paths.