feat: workflow intelligence, quality loop, completion promises, parallel teams

Sprint 1 — Workflow Intelligence (A1-A3):
- Conditional escalation: fast→standard on 2+ CRITICALs
- Guardian fast-path: skip remaining reviewers on clean pass
- Confidence-triggered escalation: pause/upgrade/probe on low scores

Sprint 2 — Quality Loop (B1-B2, B5-B6):
- Maker self-review checklist before submitting to Check phase
- Proposal diff ("What Changed") on cycle 2+ revisions
- Convergence detection: escalate to user if same finding persists 2 cycles
- Cross-archetype dedup: merge duplicate findings from different reviewers

Sprint 3 — Completion & Verification (B3-B4):
- Completion promise: user-defined done criteria checked in Act phase
- Post-merge verification: run tests on main, auto-revert on failure

Sprint 4 — Parallel & Scale (C1-C4):
- Parallel team orchestration: 2-3 independent teams with merge gate
- Task dependency graph in autonomous queue format
- Auto-resume on interruption via .archeflow/state.json
- Budget-aware scheduling with automatic workflow downgrade

skills/autonomous-mode/SKILL.md

@@ -147,7 +147,57 @@ Create `.archeflow/queue.md`:
 - [ ] Add user API endpoints (standard) | depends: user model
 - [ ] Add user UI (standard) | depends: user API endpoints
 ```
-Dependencies are processed in order. Parallel-safe tasks run concurrently.
+Dependencies are processed in order: a task with `depends: X` waits until X completes successfully. Tasks without dependencies or with resolved dependencies can run in parallel (see Parallel Team Orchestration in the orchestration skill).
+
+### With Completion Criteria
+```markdown
+- [ ] Fix login bug | fast | done: login_test.py passes
+- [ ] Add rate limiting | standard | done: Guardian approves AND load_test.sh passes
+```
+Completion criteria are checked in the Act phase. If the test command fails even when reviewers approve, the task cycles back.
+
+## Budget-Aware Scheduling
+
+Set a token or cost budget for the session. The orchestrator tracks estimated cost per task and adapts:
+
+```
+Budget: $5.00 (or ~2M tokens)
+```
+
+| Budget Remaining | Action |
+|-----------------|--------|
+| > 50% | Run tasks at their selected workflow level |
+| 25-50% | Downgrade `thorough` → `standard`, `standard` → `fast` |
+| < 25% | Run remaining tasks as `fast` only |
+| Exhausted | Stop. Log remaining tasks as "skipped — budget exhausted" |
+
+Budget is tracked per-task in the session log. Estimated cost = agents spawned x model tier pricing.
+
+## Auto-Resume on Interruption
+
+If a session is interrupted (crash, timeout, user cancel), save state for resumption:
+
+### On Interruption
+Write `.archeflow/state.json`:
+```json
+{
+  "session_id": "...",
+  "current_task": 2,
+  "current_phase": "check",
+  "current_cycle": 1,
+  "completed_tasks": [1],
+  "queue": ["task3", "task4"],
+  "worktree_branch": "archeflow/maker-abc",
+  "timestamp": "2026-04-03T22:15:00Z"
+}
+```
+
+### On Next Session Start
+If `.archeflow/state.json` exists:
+1. Report: "Found interrupted ArcheFlow session from [timestamp]. Task [N] was in [phase] phase."
+2. Offer: "Resume from where we left off? Or start fresh?"
+3. If resume: pick up from the saved phase. The worktree branch is still intact.
+4. If fresh: clean up state file and worktrees, start over.
 
 ## Overnight Session Checklist