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 PANGKAIFENG/ai-product-manager-skills --skill delivery-loopgit clone --depth 1 https://github.com/PANGKAIFENG/ai-product-manager-skillsWrote 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/pangkaifeng/ai-product-manager-skills/delivery-loop)<a href="https://agentmods.dev/skills/pangkaifeng/ai-product-manager-skills/delivery-loop"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/delivery-loop/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/pangkaifeng/ai-product-manager-skills/delivery-loop"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/delivery-loop.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 | $0.00090 | $0.00799 |
| Opus 5 | $0.00045 | $0.00400 |
| Sonnet 5 | $0.00018 | $0.00160 |
| Haiku 4.5 | $0.00009 | $0.00080 |
Grade A, and why
delivery-loop 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 12d 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.
What it actually says
交付闭环
这是 loop 的 Codex Runtime 入口,不是新的 PRD Skill。先读取同目录 LOOP.md,再使用现有 prd-architect、ui-mockup-desktop-workbench、prd-review 和必要的 prd-to-issues 关闭交付缺口。
目标与输入
目标是关闭现有交付包的最早阻断 finding,而不是重新定义产品方案。Entry Gate 必须已有可定位的 PRD 或交付包。如果只有已确认方案而没有交付物,使用 $solution-to-delivery;如果问题或方案仍未确认,使用 $problem-to-solution。
工作流
- 建立或恢复 Loop 状态,
max_cycles固定为 3;运行适用 validator,确认 artifact hashes、producer identities 和 Review fingerprint。 - 使用
prd-review判断当前 verdict,并选择最早且唯一的阻断 finding。 - 按 finding 返回责任节点:内容和 Manifest 用
prd-architect,页面、HTML 和截图用ui-mockup-desktop-workbench,版本覆盖缺口用prd-to-issues。 - 只生成本轮 Artifact Delta,保留已经通过的内容;生产者用 actor-scoped validator 绑定身份,随后交回与全部 producer identities 独立的
prd-review。 - Review 通过且当前 artifacts/Manifest 一致时输出
package_ready;达到停止条件时进入 Human Gate 或阻塞。
边界
- 不重新定义已经确认且未被新证据推翻的方案。
- Validator 只能证明结构和一致性,不能替代独立 Review。
- 页面型需求缺少当前 UI/HTML/截图时不得标记 ready;真正无用户可见界面时可以记录不适用原因。
- 不自动发布钉钉、创建云效事项或同步 Runtime;Package 只能做无副作用 dry-run,真实写入保持
authorization_required。
输出
每轮返回 cycle、Package 根目录、active finding、return owner、closure criterion、Artifact Delta、保留项、Review verdict、状态和恢复点。用户同时要求发布时可以补做 Package dry-run,但真实写入返回 publish_status: authorization_required,不改变 Package readiness。
完成定义
只有独立 prd-review 关闭当前阻断 finding、没有其他 P0/P1,且适用 validator 证明 Manifest 与 artifacts 一致,才输出 package_ready。三轮上限、连续两轮无有效 Artifact Delta 或交付事实缺失时进入 Human Gate。可信宿主授权不属于交付缺口;当前 Agent Runtime 中 Package 已 ready 时保持 status: package_ready,并对真实写入返回 publish_status: authorization_required。
资源与验证
LOOP.md是 Review 回流、责任节点、状态字段和停止条件的权威合同,每次执行或恢复前读取。evals/evals.json覆盖 Review 修订、缺 UI 回流、单次 Review 分流、发布授权和无进展回归;修改入口后运行这些评测并保留结果。
What ships with it
3 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.
- 12d ago First seen · 43 lines · 90 tokens per session scan A e537e0699732
delivery-loop is a skill published in the GitHub repository PANGKAIFENG/ai-product-manager-skills (11 stars, last pushed 12d ago), licensed MIT. It adds 90 tokens to every session and 799 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
baoyu-diagram
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system…
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
agent-wiki
Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.
sequential-think
Multi-step reasoning engine for complex analysis and systematic problem solving. Use when: (1) Complex debugging scenarios with multiple layers, (2) Architectural analysis and system design, (3) Problems requiring hypothesis testing and validation, (4) Multi-component failure investigation, (5) Performance bottleneck…