shenxingy/loop

Loop Skill

Runs an autonomous improvement loop driven by a goal file (ideal end state description).

Architecture

You write: goal.md  (what the system should do — NOT a task list)
                ↓
PRE (deterministic):
  pre_flight       — goal exists, no blockers
  hydrate_context  — git log + status
  parse_todo       — extract unchecked items from goal file
                ↓
LLM CORE:
  Supervisor       — plans 1–4 tasks (output: JSON task array)
  Workers          — execute ALL tasks IN PARALLEL
                ↓
POST (deterministic + conditional LLM):
  syntax_check     — validate all changed files
  fix_syntax       — [LLM] one attempt to fix failures
  test_sample      — run verify_cmd from CLAUDE.md
  mid-iter fix     — [LLM] if test fails → fix → re-test (Stripe pattern)
  commit_changes   — commit all worker output
                ↓
Deterministic convergence check:
  - remaining unchecked items = 0 → CONVERGED
  - max iterations hit        → exit
  - stuck (N× no-commits)    → exit
                ↓
Repeat until CONVERGED or max iterations

What you write (goal.md)

# Goal: Improve orchestrator loop mode

## Requirements
- Oracle rejection re-queues task with rejection reason as context
- Worker context budget warning auto-injected at 80%
- Workers get AGENTS.md prepended automatically

## Success criteria
- python -m py_compile server.py passes
- Existing features unaffected

The supervisor does the task breakdown — not you.

Usage

/loop goal.md                                # Start loop (sonnet, max 10 iter, 4 parallel workers)
/loop goal.md --model haiku                  # Cheaper/faster supervisor+workers
/loop goal.md --max-iter 3                  # Short run to test
/loop goal.md --max-workers 2                # Limit parallel workers
/loop goal.md --max-consecutive-failures 5  # Stop after 5 consecutive worker failures (default: 3)
/loop --status                               # Check current loop progress
/loop --stop                                 # Stop loop after current iteration
/loop --dry-run goal.md                      # Preview without running
/loop --resume goal.md                       # Resume interrupted loop

After convergence

Run /commit to push any remaining uncommitted changes from workers. Run /review to verify all behavior anchors still pass after autonomous changes.