Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/kangarooking/loop-engineering-skill/maker-checkernpx skills add kangarooking/loop-engineering-skill --skill maker-checkergit clone --depth 1 https://github.com/kangarooking/loop-engineering-skillWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00119 | $0.01399 |
| Opus 5 | $0.00060 | $0.00700 |
| Sonnet 5 | $0.00024 | $0.00280 |
| Haiku 4.5 | $0.00012 | $0.00140 |
Grade A, and why
maker-checker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Source Metadata
Original cangjie-skill frontmatter from the distillation run:
name: maker-checker
description: |
设计 Loop 中的 Maker-Checker 模式: 用独立 agent 审查产出,避免自产自检。
当用户发现 loop 产出质量不稳定、agent 自我评估过于宽容、或需要提升产出可信度时使用。
不适用于: 产出可以客观验证 (测试通过/失败) 的任务、或成本极其敏感的场景。
关键 trigger: "agent 自评不准确"、"产出质量不稳定"、"怎么让 agent 审查 agent"。
source_book: "Loop Engineering 视频合集"
source_chapter: 视频2 (Boris Cherny) / 视频3 (小木头)
tags: [maker-checker, verification, quality, separation-of-concerns]
related_skills: [goal-verification, loop-5plus1-architecture, loop-three-elements]
Maker-Checker 模式 — 用独立 Agent 审查产出
R — Reading (原文)
"Don't get agent to self-verify its own work. It just generally didn't work that well." — Boris Cherny (视频2)
"写代码的那个模型给自己的作业打分,有的时候太宽容了。所以我们需要让另一个agent来挑刺。" — 小木头 (视频3)
I — Interpretation (自述)
核心规则: 不要让同一个 agent 做事又检查。
Maker-Checker 模式将生产和审查拆分为两个独立 agent:
- Maker: 执行任务 (写代码、写文章、生成方案)
- Checker: 审查产出,给出反馈或打分
为什么需要:
- 同一个 agent 给自己的作业打分通常过于宽容
- Agent 有盲点,看不到自己的错误
- 独立 checker 可以给出更客观的评估
A1 — Past Application (书中案例)
案例1: Boris 的代码审查 (视频2)
- Maker: 写代码的 agent -Checker: read-only 的 verifier agent,有详细 spec
- 结果: 自审经常放过问题,独立 checker 能发现更多缺陷
案例2: 缩略图评分 (视频1)
- Maker: 生成 10 个缩略图概念
- Checker: 用 Mr. Beast 风格 rubric 打分
- 教训: 如果 maker 和 checker 是同一个 agent,评分会过于主观
A2 — Future Trigger (未来触发)
- Agent 自评不准确时: "它自己说做得很好,但实际很差"
- 产出质量不稳定时: "有时好有时坏,没有保障"
- 设计 loop 验证环节时: 选择 maker-checker 作为验证策略
- 团队 code review 自动化时: 用 AI checker 替代部分人工 review
语言信号: "agent 自评不准确"、"怎么让 agent 审查 agent"、"产出质量不稳定"、"独立审查"
与相邻 skill 的区别:
goal-verification: 关注"验证什么" (标准设计); 本 skill 关注"谁来验证" (角色分工)loop-5plus1-architecture: 完整系统架构 (本 skill 是子智能体层的具体模式)loop-three-elements: 三要素框架 (本 skill 是 action 环节的质量保障)
E — Execution (可执行步骤)
Step 1: 判断是否需要 Maker-Checker
- 产出可以客观验证 (测试/数值)? → 不需要,用自动化检查
- 产出需要主观判断 (写作/设计)? → 需要 Maker-Checker
- 成本极其敏感? → 谨慎,因为多一个 agent 多一倍成本
Step 2: 设计 Maker
- 明确任务: 做什么? 输出什么?
- 提供上下文: 规则、约束、参考案例
- 输出格式: 确保 checker 能清楚审查
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 113 lines · 119 tokens per session scan A c8b2969772de
maker-checker is a skill published in the GitHub repository kangarooking/loop-engineering-skill (23 stars, last pushed 2mo ago), licensed MIT. It adds 119 tokens to every session and 1,399 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…
mcp-scripting
Write mcpScript JavaScript for discovering, inspecting, and calling MCP tools.