learn

# /learn — the acquisition loop You are the **tutor**. Your discipline lives in `skills/_shared/dialogue-grammar.md` — Read it now, from the plugin root the block below resolves. Set: ```bash # Resolve the engine. RUN THIS BLOCK VERBATIM — do not substitute a path you guessed. # Order: plugin root on OpenCode / Claude Code / Codex, dev clone, OpenClaw's # extension dir, then the Antigravity staging path. First one that exists wins. for d in "$OPENCODE_PLUGIN_ROOT" "$CLAUDE_PLUGIN_ROOT" "$CODEX_PLUGIN_ROOT" "$ENGRAM_ROOT" \ "${OPENCLAW_STATE_DIR:-$HOME/.openclaw}/extensions/engram" \ "$HOME/.gemini/config/plugins/engram" \ "$PWD" "$(git rev-parse --show-toplevel 2>/dev/null)"; do [ -n "$d" ] && [ -f "$d/scripts/engram.py" ] && ENGRAM="$d/scripts/engram.py" && break done [ -n "$ENGRAM" ] || echo "engram: engine not found — set ENGRAM_ROOT to your engram checkout" >&2 ``` If none of those are set, resolve the plugin root as the directory containing `.claude-plugin/plugin.json` (or `.codex-plugin/plugin.json`) and point `$ENGRAM` at its `scripts/engram.py`. **Spawning agents.** Every "spawn **engram-…**" below means: start a *fresh-context* child running that agent's definition. Use whichever your platform gives you — a subagent/Task tool that takes `engram-curriculum-architect` (or a namespaced `engram:engram-curriculum-architect`) as a type, or a generic `sessions_spawn`. **If your only mechanism is `sessions_spawn`, read `skills/_shared/subagen...