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/movebrickschi/harness-engineering-mcp/dev-ship-retronpx skills add movebrickschi/harness-engineering-mcp --skill dev-ship-retrogit clone --depth 1 https://github.com/movebrickschi/harness-engineering-mcpWrote 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/movebrickschi/harness-engineering-mcp/dev-ship-retro)<a href="https://agentmods.dev/skills/movebrickschi/harness-engineering-mcp/dev-ship-retro"><img src="https://agentmods.dev/badge/skills/movebrickschi/harness-engineering-mcp/dev-ship-retro.svg" alt="Measured on agentmods" 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 | $0.00104 | $0.01583 |
| Opus 5 | $0.00052 | $0.00792 |
| Sonnet 5 | $0.00021 | $0.00317 |
| Haiku 4.5 | $0.00010 | $0.00158 |
Grade A, and why
dev-ship-retro 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 5d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Ship & Retro - 上线复盘阶段
适用场景
完整开发流程的收尾阶段。前置条件:
- 功能已通过
/dev-implement或手动开发完成 - 通过自查(QA、Review)
- 准备进入 PM 验收 → 上线 → 复盘
本阶段产出:PM demo 材料 + 上线 PR + 知识库沉淀。
核心原则
- PM 验收必须卡点:技术 OK ≠ 业务认可
- 上线后必须监控:避免上线即出事
- 知识必须沉淀:每次复盘自动追加到
_lessons.md,下次自动加载
启动参数收集
使用 AskQuestion 工具收集:
- 需求名称(定位
~/Projects/_requirements/[feature]/) - 目标项目 B 路径
- 是否已通过 PM 验收(决定是否跳过卡点 4)
- 部署平台(如未配置则提示先跑
/setup-deploy)
启动前验证:当前项目处于干净 git 状态、有未推送的 commits。
流程执行
前置:加载上下文
- 加载
~/Projects/_requirements/[feature]/全部文档 - 加载
~/Projects/_requirements/_lessons.md - 检查 git 状态:当前分支、commits 数量、是否有未提交改动
- 检查 B 项目部署配置(CLAUDE.md 中的 deploy 配置)
阶段 8:PM 验收 ⏸ 卡点
如果用户启动时已选"已通过 PM 验收",跳过本阶段。否则:
- 整理 demo 材料
docs/demo-package.md:- 主流程截图序列(用
cursor-ide-browser自动截图分镜) - 关键操作录屏(如可能)
- 与原型 A 的行为对比表(哪些一致、哪些主动改了、哪些已知差异)
- 已知限制说明
- 主流程截图序列(用
- 如果 A 项目仍可运行,可同时打开 A 和 B 做最终对照截图
- 调用
AskQuestion阻塞等待:prompt: "demo 材料已准备好(docs/demo-package.md)。PM 验收结果:" options: - "PM 通过,进入上线" - "PM 提出小修改(请说明)" - "PM 不认可,需要回开发阶段" - 如有小修改:完成后再次
AskQuestion确认
阶段 9:上线(Ship + Land + Canary)
/ship- 创建 PR:- 自动检测/合并 base 分支
- 跑测试
- bump VERSION + 更新 CHANGELOG
- 中文 commit 提交(遵循用户 commit 规范)
- 推送 + 创建 PR
/land-and-deploy- 合并 + 部署:- 合并 PR
- 等待 CI
- 等待部署
- 验证生产健康
/canary- 上线后监控:- 监控 console errors
- 性能基线对比
- 关键页面截图对比
- 输出 PR 链接、上线状态、监控结果
阶段 10:复盘 + 知识库沉淀
- 更新
~/Projects/_requirements/_lessons.md(如不存在则创建),追加格式:## [YYYY-MM-DD] [feature-name] ### PM 沟通踩坑 - (这次 PM 沟通中哪些问题应该早问?比如某个边界场景理解错了,回头看应该提前问) ### B 项目隐性规范 - (发现的、未文档化的约定,比如"所有 admin 接口都要加 audit log") ### A 与 B 的差异 - (A 用了什么 B 没有?反之?比如 A 用 Vue Composition,B 用 React Hooks) ### 架构决策 - (这次为什么选 X 不选 Y?记录权衡过程) ### 复用机会 - (下次类似需求可以复用这次的什么?比如新建的 BatchActionMixin 可复用) ### 踩过的坑 - (技术上遇到的坑 + 解决方案) ### 实际耗时 vs 估算 - 估算:N 小时 / 实际:M 小时 - 主要超时原因:...
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.
- 5d ago First seen · 155 lines · 0 tokens per session scan A d6999470c22c
dev-ship-retro is a skill published in the GitHub repository movebrickschi/harness-engineering-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 104 tokens to every session and 1,583 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
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
release
Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.
changelog
Create changelog files for important commits in a PR.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
refresh-arm-sdk-release
WORKFLOW SKILL — Prepares Azure.ResourceManager SDK refresh pull requests in azure-sdk-for-net. WHEN: "prepare sdk refresh", "refresh Azure.ResourceManager package", "update ARM SDK from autorest tag", "refresh changelog dependencies". INVOKES: git and GitHub pull request tools for branch, commit, push, and PR…