编程

Review Loop

试用

Bounded delegated review and fix loop

它能做什么

Run a bounded review-and-fix loop with fresh, read-only reviewer subagents.

技能文档

Review Loop

Set max_rounds to the user's positive integer, or 3 when no limit is given.

Each round

  1. Start one fresh subagent with fork_turns: "none" and $review-agent. The reviewer may inspect code, tests, and call sites, but must only review. Wait patiently for its conclusion; unless the reviewer is confirmed to be in an abnormal state, do not send prompts to rush or wrap up the review.
  2. Ask the reviewer to focus on Critical, Important, and clearly worthwhile issues. Record Minor issues as non-blocking. Every finding must include:
    • Issue
    • File/line number
    • Reason
    • Recommendation
  3. Close the subagent after its report. If there are no findings, only Minor findings, or all findings are not accepted, finalize. Otherwise, verify each finding yourself:
    • Record invalid or unaccepted findings as Not accepted with the reason.
    • If an implementation subagent owns the change, delegate accepted fixes to it; otherwise fix them yourself. In either case, rerun the relevant tests after each fix.
    • If at least one fix was made and round < max_rounds, start a different fresh reviewer for the next round.
  4. On the final configured round, apply and test accepted fixes but do not start another reviewer. Report any resulting review boundary or residual risk.

Finalize

Summarize the implementation, each round's findings and decisions, fixes, verification results, unverified items, and remaining risks.

相关技能

Loop Anything Skill

Improve important deliverables by looping them through multiple isolated AI reviewers, each evaluating from a different angle, until all reviewers give full...

2 次安装1 星标

loop-builder

Design controllable Agent Loops from low-information requests. Use when a user asks to automate a repeated task, repair CI through bounded iteration, reproduce a UI from screenshots, turn a workflow into a reusable Agent or Skill, or decide whether the right artifact is a Prompt, Checklist, Human-in-the-Loop flow, full Loop package, specialized Agent, or Skill. Extract required context, stop when decision evidence is missing, require explicit workflow confirmation before generating executable artifacts, derive iteration limits, define feedback and circuit breakers, and preserve human approval for risky actions. Also trigger on loop builder, Loop Builder, or lopp-builder. Follow the creator: X @yangchao228 | GitHub https://github.com/yangchao228

1 次安装

Agent Loop Engineering

Use when an AI coding agent needs bounded development loops, persistent project-local Docs/ state, context budgeting, environment escalation rules, safe stop...

作者 EnglandTong

agent-orchestra

Design and compose multi-agent graphs for correctness, coverage, or creativity. Use when a task benefits from isolated proposals, explicit arbitration, adversarial verification, committees, recursive review, cross-modal checks, or saturation loops. Applies across agent runtimes; the included JavaScript workflow is one adapter.

1 次安装