Update TODO with prioritized next items

TODO.md

@@ -3,38 +3,38 @@
 ## Done
 
 - [x] Firecracker CLI runner with snapshots (~1.1s)
-- [x] Alpine rootfs with ca-certificates, podman, python3
-- [x] Global `fireclaw` command
 - [x] Multi-agent system — overseer + agent VMs + IRC + Ollama
-- [x] 5 agent templates (worker, coder, researcher, quick, creative)
-- [x] 5 Ollama models (qwen2.5-coder, qwen2.5, llama3.1, gemma3, phi4-mini)
-- [x] Agent tool access — shell commands + podman containers
-- [x] Persistent workspace + memory system (MEMORY.md pattern)
-- [x] Agent hot-reload — model/persona swap via SSH + SIGHUP
-- [x] Non-root agents — unprivileged `agent` user
-- [x] Agent-to-agent via IRC mentions (10s cooldown)
-- [x] DM support — private messages, no mention needed
-- [x] /invite support — agents auto-join invited channels
-- [x] Channel layout — #control (commands), #agents (common), DMs
-- [x] Overseer resilience — crash recovery, agent adoption
-- [x] Graceful shutdown — IRC QUIT before VM kill
-- [x] Systemd service (KillMode=process)
-- [x] Regression test suite (20 tests)
+- [x] 5 templates, 5+ models, hot-reload, non-root agents
+- [x] Tools: run_command, web_search, fetch_url, save_memory
+- [x] Discoverable skill system — SKILL.md + run.py, auto-loaded
+- [x] Persistent workspace + memory (MEMORY.md pattern)
+- [x] Overseer: !invoke, !destroy, !list, !model, !models, !templates, !persona, !status, !help
+- [x] Health checks, crash recovery, graceful shutdown, systemd
+- [x] Network policies, thread safety, trigger fix, race condition fix
+- [x] Install/uninstall scripts, deployed on 2 machines
+- [x] Refactor: firecracker-vm.ts shared helpers, skill extraction
 
-- [ ] Refactor duplicated code — waitForSocket, boot sequence, tap setup, rootfs mount/inject are copy-pasted across vm.ts, snapshot.ts, agent-manager.ts. Extract shared helpers.
+## Next up (Phase 5 — by priority)
 
-## Next up
+### Quick wins
+- [ ] Large output handling — save >2K results to file, preview + read_file
+- [ ] Iteration budget — configurable max rounds per template, prevent runaway loops
 
-- [ ] Network policies per agent — restrict internet access
-- [ ] Warm pool — pre-booted VMs for instant agent spawns
-- [ ] Persistent agent memory improvements — richer memory structure, auto-save from conversations
-- [ ] Thin provisioning — device-mapper snapshots instead of full rootfs copies
+### Medium effort
+- [ ] Skill registry git repo — shared skills on Gitea, `fireclaw skills pull`
+- [ ] Session persistence — SQLite + FTS5 in workspace
+- [ ] Context compression — summarize old turns when context gets long
+- [ ] !logs — tail agent history from workspace
+
+### Bigger items
+- [ ] Skill learning — agents create new skills from experience
+- [ ] Cron agents — scheduled agent spawns
+- [ ] Dangerous command approval — pattern detection + allowlist
+- [ ] Parallel tool execution — concurrent independent tool calls
 
 ## Polish
 
-- [ ] Agent-to-agent response quality — small models (7B) parrot messages instead of answering. Needs better prompting ("don't repeat the question, answer it") or larger models (14B+). Claude API would help here.
-- [ ] Cost tracking per agent interaction
+- [ ] Agent-to-agent response quality — 7B models parrot, needs better prompting or larger models
+- [ ] Cost tracking per interaction
 - [ ] Execution recording / audit trail
-- [ ] Agent health checks — overseer pings agents, restarts dead ones
-- [ ] Thread safety in agent.py — lock around IRC socket writes
-- [ ] Update regression tests for new channel layout
+- [ ] Update regression tests for skill system + channel layout