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 NocodeMrLi/mini-program-engineering-skill-suite --skill mini-program-release-skillgit clone --depth 1 https://github.com/NocodeMrLi/mini-program-engineering-skill-suiteWrote 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/nocodemrli/mini-program-engineering-skill-suite/mini-program-release-skill)<a href="https://agentmods.dev/skills/nocodemrli/mini-program-engineering-skill-suite/mini-program-release-skill"><img src="https://agentmods.dev/badge/skills/nocodemrli/mini-program-engineering-skill-suite/mini-program-release-skill/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/nocodemrli/mini-program-engineering-skill-suite/mini-program-release-skill"><img src="https://agentmods.dev/badge/skills/nocodemrli/mini-program-engineering-skill-suite/mini-program-release-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00134 | $0.01384 |
| Opus 5.5 | $0.00054 | $0.00554 |
| Sonnet 5.5 | $0.00027 | $0.00277 |
| Haiku 4.5 | $0.00013 | $0.00138 |
Grade A, and why
mini-program-release-skill 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 26d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mini-program-release-skill — 小程序发布治理
默认执行只读发布预检,形成可审计的 release-ready 判断。核对证据不等于获得外部操作权限;每一种外部状态变化都必须单独明确授权。
输入与发布目标
- 接收目标版本、目标分支、功能范围、验证报告、平台/渠道、计划窗口、回滚策略和用户授权边界。
- 先记录当前分支、提交、工作区、版本事实源、源码、构建产物和开发者工具加载目标;证据不一致时停止在
not-ready。 - 涉及微信规则、权限、隐私或审核要求且可能变化时,只查询当前官方资料;无法核对时保留
unknown。
只读发布预检
- 核对目标功能已在当前分支,版本符合语义化策略,源码与构建产物绑定同一指纹。
- 版本升级必须核对整组版本事实源:
VERSION、根 Skill 或项目元数据、README 徽章/正文、CHANGELOG、发布清单、测试断言、构建/导出清单,以及小程序开发者工具上传版本或体验版/审核版备注;不能只改一个显眼版本号。
- 版本升级必须核对整组版本事实源:
- 核对静态、单元、集成、状态矩阵以及风险所需的真机/云端证据;失败或未执行项必须映射为阻塞或残余风险。
- 核对源码和构建产物中的测试开关、模拟数据、调试入口、日志、后门路径和内部文案。
- 执行敏感信息扫描与人工匿名化复核;核对权限、隐私声明、域名/服务和实际功能一致性,但不回显凭证值。
- 准备版本说明、变更范围、已知问题、监控/观察点、回滚条件、回滚版本与复验步骤。
- 项目包含云函数、云托管、外部后端、数据库、对象存储、依赖审计或分享/公开入口时,执行 云端发布与发布后运维门禁:配置 preflight、production build/start/smoke、真实依赖 health、审计有效性、公开安全落地和运维交接分别取证。
- 分别记录代码推送、平台上传、体验版、审核提交、审核结果和正式发布的证据;任何一层缺证据都保持
unknown。 - 使用 发布治理工作流 判定阻塞,按 发布就绪记录 输出。
外部动作发生中断、超时或回执不明确时,当前状态保持 unknown;先查询平台记录、目标版本和回执,再判断已生效、未生效或仍不确定。原上传/审核/发布授权不自动成为高风险动作的重放授权。
权限与状态边界
- Git 提交不等于代码推送;代码推送不等于平台上传;构建成功也不等于平台上传。
- 平台上传不等于审核提交;审核提交不等于审核通过;审核通过不等于正式发布。
- 用户说“检查”“准备”“看看能不能发”只授权只读预检,不授权外部动作。
- 即使用户给出总目标,也应在执行平台上传、审核提交或正式发布前确认具体目标、版本和回滚条件已明确。
- 输出行动清单或结构化
proposed_actions时,每个行动条目只能包含一个外部动作。代码推送、平台上传、提交审核、正式发布、云端修改和付费资源创建不得合并授权;每项分别记录目标、版本、影响、回滚条件与requires_authorization: true。 - 不得自动推送代码、平台上传、提交审核、正式发布、修改云端、创建付费资源或改变外部状态。
最低输出
- 发布目标、当前分支、提交、版本、源码/构建/工具指纹与工作区状态。
- 验证证据、安全、测试开关、敏感信息、权限、隐私和回滚检查结果。
- 条件触发时的云配置、生产 build/start/smoke、依赖审计、分享/公开入口与发布后云环境交接结果。
- 关键证据的产生工具、格式、版本、时间、目标指纹、可采信范围和不能证明的内容。
- 每个发布层的当前状态、证据、缺失项与阻塞项。
- 当前结论:
not-ready/release-ready/uploaded/review-submitted/review-approved/released;只使用证据支持的最高状态。 - 获准外部动作、未获准动作、残余风险和下一步。
停止条件
目标版本/分支不明、验证失败、源码与产物不一致、敏感信息命中、回滚缺失或平台证据冲突时停止。需要账号、验证码、凭证、真实平台写入或付费操作但未获明确授权时,不尝试绕过。
独立与套件协作
独立安装时可执行发布就绪审查和已授权的发布步骤治理。位于套件中时,接收验证报告和微信平台约束,输出发布状态证据;不会因处于端到端流程而获得额外外部权限。
What ships with it
4 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.
- 26d ago Changed · +2 lines 273aecd80131
- 1mo ago First seen · 55 lines · 134 tokens per session scan A 2dc1c9194e2e
mini-program-release-skill is a skill published in the GitHub repository NocodeMrLi/mini-program-engineering-skill-suite (91 stars, last pushed yesterday), licensed MIT. It adds 134 tokens to every session and 1,384 once invoked, about $0.0005 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.
Other skills, from other repositories
release-skills
A release workflow for preparing and publishing a new version of a software project. A release is a named version that may include updated version files, release notes, tags, or a GitHub Release.
git-workflow
A Git workflow guide for organizing commits, branches, pull requests, releases, and automated version-control tasks. Git is the system developers use to track code changes and collaborate.
git-publish-release
A release assistant for GitHub, a service for hosting software projects. It compares project history and creates a GitHub Release with notes for a chosen version tag.
change-log-generator
Automatically generates change logs from git commits, patches, and pull requests. Use when preparing software releases, creating version summaries, or maintaining CHANGELOG.md files. Analyzes commit messages (including conventional commits), diff/patch files, and PR data to produce categorized Markdown change logs…
release-notes-writer
Automatically generate user-facing release notes from git commits, pull requests, changelogs, and code changes. Use when preparing software releases, creating version announcements, documenting what changed between versions, or communicating updates to users. Analyzes commit messages, PR descriptions, and code diffs…
release-change-analyzer
Compares HEAD with the latest published version to analyze real changes, group by type, and recommend version bumps. Use before publishing a release to understand what actually changed.