Borrowing it
Nothing to install: this file belongs to hitosea/happy-next. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hitosea/happy-next/main/.claude/skills/happy-next-release/SKILL.mdgit clone --depth 1 https://github.com/hitosea/happy-nextWrote 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/hitosea/happy-next/happy-next-release)<a href="https://agentmods.dev/skills/hitosea/happy-next/happy-next-release"><img src="https://agentmods.dev/badge/skills/hitosea/happy-next/happy-next-release/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/hitosea/happy-next/happy-next-release"><img src="https://agentmods.dev/badge/skills/hitosea/happy-next/happy-next-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 226 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00058 | $0.05140 |
| Opus 5.5 | $0.00023 | $0.02056 |
| Sonnet 5.5 | $0.00012 | $0.01028 |
| Haiku 4.5 | $0.00006 | $0.00514 |
Grade A, and why
happy-next-release scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://hub.docker.com/v2/repositories/kuaifan/$img/tags?page_size=4&ordering=last_updated" How it starts
The opening of the file, as written. The whole thing — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Happy Next 发布流程
总则
流程分四段:自动检查 → 确认发布计划 → 执行 → 失败处理。
- 根据审计结果推荐发布线组合,写进发布计划。
- 用户在调用时用自然语言说明了要发什么(如"只发 Docker"、"这次不发 CLI"、"把 v2.15.1 提交到 App Store"),按用户的意思确定发布线,其余流程相同;意思不明确时在发布计划里写出你的理解。
- 只确认一次:发布计划。用户确认(或修改后确认)即授权执行计划内的全部操作,包括推送 main、合并 PR、npm 发布、创建 tag、GitHub Release、Docker、iOS 提审和 OTA 发布。确认后直接执行,直到完成或遇到停止条件。
- 计划外的操作(计划外的改动、覆盖、重建、删除)需单独确认。
五条发布线:
| 线 | 产物 | 版本 | workflow |
|---|---|---|---|
| CLI | npm happy-next-cli |
packages/happy-cli/package.json 独立版本,由 workflow 提交 |
cli-publish.yml |
| Release | Android APK/AAB、iOS IPA、macOS Universal、Windows x64/ARM64、latest.json |
vX.Y.Z tag |
release.yml |
| Docker | kuaifan/happy-{server,app,voice,docs,web} |
同一 vX.Y.Z tag |
docker-publish.yml |
| iOS | App Store Connect 上传 | 同一 vX.Y.Z tag,提交 Release 里那份 IPA |
ios-submit.yml |
| OTA | App 的 JS 更新,发给已安装、fingerprint 相同的包 | 无版本号,按 runtime(原生 fingerprint)匹配 | 无,本地 yarn ota publish(见 happy-ota 技能(读 .claude/skills/happy-ota/SKILL.md)) |
- Release、Docker、iOS 同一次发布共用同一个不可变 tag 和 commit。
- iOS 只提交 Release 已发布的 IPA,必须在 Release 验证通过之后。
- 推送 tag 不会发布任何东西;每条线都要显式触发 workflow。
- OTA 不需要 tag,也不经过商店审核,发布后用户的 App 会自动下载,所以 App 的改动能比 Release / iOS 早几天到达用户手里。
每条线的基准
每条线以自己上一次成功发布的版本为基准审计改动:
# CLI:最近一个 CLI 版本提交
BASE_CLI=$(git log --format=%h --grep='^release: happy-next-cli' -1)
# Release:最近一个正式 GitHub Release 的 tag
BASE_APP=$(gh release list --limit 50 --exclude-drafts --exclude-pre-releases \
--json tagName -q '.[].tagName' | grep '^v[0-9]' | sort -V | tail -1)
# Docker:最近一次成功的 Docker workflow(run-name 为 "Docker vX.Y.Z")
BASE_DOCKER=$(gh run list --workflow=docker-publish.yml --status success --limit 50 \
--json displayTitle -q '.[].displayTitle' | sed -n 's/^Docker //p' | sort -V | tail -1)
# iOS:最近一次成功的提审(run-name 为 "iOS App Store vX.Y.Z")
BASE_IOS=$(gh run list --workflow=ios-submit.yml --status success --limit 50 \
--json displayTitle -q '.[].displayTitle' | sed -n 's/^iOS App Store //p' | sort -V | tail -1)
# 全局最高的 v tag
TOP_TAG=$(git tag --sort=-version:refname | grep '^v[0-9]' | head -1)
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 Changed · +14 lines · +5 tokens per session 5dbff616f235
- 18d ago Changed · -49 lines · +14 tokens per session fd0609477062
- 27d ago Changed 479600cc83dc
- 28d ago Changed · +15 lines 57d540461eaf
- 1mo ago Changed · +9 lines ded30b3056e0
- 1mo ago First seen · 448 lines · 39 tokens per session scan A 5e719b1207e6
happy-next-release is a skill published in the GitHub repository hitosea/happy-next (61 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 5,140 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
dsh-plugin-publisher
A release tool for DSH plugins, where DSH is the DeepSeek Harness used to load these add-ons. It validates an existing plugin package, publishes it through npm, Git, or a tarball, and checks that the harness can load it.
lov-skill-optimizer
Audit and optimize one or more existing Agent Skills from a canonical source path, then bump semver, update README/SKILL.md/skill.yaml/CHANGELOG.md, and verify installed copies and catalog synchronization. Checks frontmatter, trigger quality, CLI hygiene, naming, portability, version drift, dirty worktrees, shared…
lov-skill-publisher
Publish or submit a validated Skill. Default to the LovStudio official website, run lov-skill-pricing automatically, and use other channels only when explicitly named.
lov-app-delta-updater
An automatic update workflow for Tauri and Electron desktop apps. It distinguishes signed full packages from genuine delta packages, which contain only changes, and checks how updates are discovered, installed, verified, and recovered.
github-release-notes-writer
Draft or update user-focused GitHub Release Notes from verified tags, commits, pull requests, existing releases, and supplied changelog baselines. Use when preparing prerelease or stable release notes, turning GitHub's generated What's Changed list into a curated narrative, documenting upgrades or breaking changes, or…
github-release-pr-writer
Draft or update GitHub release pull request descriptions from verified tags, commits, merged pull requests, and the release diff. Use when a PR prepares a version, aligns release metadata, promotes a prerelease, or needs a reviewer-focused release summary, exact change inventory, breaking-change section, or migration…