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 skills add kangarooking/loop-engineering-skill --skill goal-verificationgit clone --depth 1 https://github.com/kangarooking/loop-engineering-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kangarooking/loop-engineering-skill/goal-verification)<a href="https://agentmods.dev/skills/kangarooking/loop-engineering-skill/goal-verification"><img src="https://agentmods.dev/badge/skills/kangarooking/loop-engineering-skill/goal-verification/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kangarooking/loop-engineering-skill/goal-verification"><img src="https://agentmods.dev/badge/skills/kangarooking/loop-engineering-skill/goal-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00105 | $0.01600 |
| Opus 5.5 | $0.00042 | $0.00640 |
| Sonnet 5.5 | $0.00021 | $0.00320 |
| Haiku 4.5 | $0.00011 | $0.00160 |
Grade A, and why
goal-verification 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 2mo 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 — 125 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: goal-verification
description: |
设计 Loop 的 Goal 和 Verification 环节: 将模糊目标转化为可验证的停止条件。
当用户发现 loop 产出质量不稳定、循环无法停止、或"不知道什么时候算做完"时使用。
不适用于: 目标已经非常清晰可量的任务、或非循环场景。
关键 trigger: "loop 停不下来"、"产出质量不稳定"、"怎么定义完成"、"goal 怎么写"。
source_book: "Loop Engineering 视频合集"
source_chapter: 视频1 (Adam Gillock) / 视频4 (Idoos Money)
tags: [goal-design, verification, stop-condition, quality]
related_skills: [loop-three-elements, maker-checker, loop-build-path]
Goal 可验证化 — 循环设计的质量杠杆点
R — Reading (原文)
"There's really two most important pillars: the goal (objective, not subjective) and then verification. How does the agent know what that stop condition is?" — Adam Gillock (视频1)
"A loop is only going to be as good as its done check, as the done criteria." — Adam Gillock (视频1)
I — Interpretation (自述)
循环的质量上限 = 其验证环节的质量上限。设计 Loop 时,必须回答两个问题:
- Goal (目标): 循环要达成什么? 必须是客观可验证的 — 不是"做好",而是"达到 X 指标"。
- Verification (验证): 如何判断目标已达成? 必须有可执行的检查步骤。
好 Goal vs 坏 Goal:
- ❌ "直到你满意" — 主观,不可验证
- ❌ "做好这个功能" — 模糊,无法判断
- ✅ "凑够 5 条数据" — 客观,可数
- ✅ "平均分 ≥ 9 或最多 8 轮" — 客观 + 硬停
验证方式光谱 (从客观到主观):
- 纯客观: 跑测试套件、数值指标
- 半客观: 另一个 LLM 评判
- 主观: 人类在环判断
- 模糊: 无法明确判断好坏
A1 — Past Application (书中案例)
案例1: 坏 Goal — 缩略图生成 (视频1)
- Goal: "迭代直到满意" → 主观,导致 27 分钟不可控
- 教训: 应改为"评分 ≥ 8/10 或最多 5 轮"
案例2: 好 Goal — Abbey Road 复刻 (视频1)
- Goal: "平均分 ≥ 9 或最多 8 轮" → 客观 + 硬停
- 虽然结果不完美,但循环在预期内停止
案例3: 验证光谱应用 (视频4)
- 测试套件 → 最客观,优先用
- LLM 评判 → 次选,需独立 checker
- 人类判断 → 最后手段,成本高
A2 — Future Trigger (未来触发)
- Loop 无法停止时: "跑了 3 天还没完" → 检查 stop condition 是否过主观
- 产出质量不稳定时: "有时好有时坏" → 验证环节可能不可靠
- 设计新 Loop 时: 先写 goal 和 verification,再写 action
- 调试 Loop 时: 诊断"为什么产出差" → 先看 goal 是否可验证
语言信号: "loop 停不下来"、"怎么定义完成"、"goal 怎么写"、"产出质量不稳定"
与相邻 skill 的区别:
loop-three-elements: 三要素的整体框架 (本 skill 专注 stop condition 的设计)maker-checker: 验证环节的具体实现 (本 skill 是验证的设计原则)loop-worthiness-test: 判断要不要做 loop (本 skill 是决定后如何设计)
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.
- 2mo ago First seen · 125 lines · 105 tokens per session scan A abc1843420d1
goal-verification is a skill published in the GitHub repository kangarooking/loop-engineering-skill (28 stars, last pushed 4mo ago), licensed MIT. It adds 105 tokens to every session and 1,600 once invoked, about $0.0004 per session on Opus 5.5. 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.
goal-verification compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| goal-verificationkangarooking/loop-engineering-skill | Skill | 28 | 4mo ago | MIT | A | 105 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | 6d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 317k | 9d ago | MIT | A | 21 | Claude Code |