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/linshidream/skill-hub/dev-lifecyclenpx skills add linshidream/skill-hub --skill dev-lifecyclegit clone --depth 1 https://github.com/linshidream/skill-hubWhat 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 | $0.00059 | $0.06738 |
| Opus 5 | $0.00030 | $0.03369 |
| Sonnet 5 | $0.00012 | $0.01348 |
| Haiku 4.5 | $0.00006 | $0.00674 |
Grade A, and why
dev-lifecycle 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 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.
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 — 493 lines — stays where its author put it; the contents beside it link to each section on GitHub.
开发全流程编排
目标
编排 dev-spec、git-flow、ci-trigger 三个 skill，实现从需求材料到部署测试环境的可中断恢复开发流程。本 skill 是协议（protocol），不是控制器——定义状态机、操作契约和转移规则，任何理解此协议的 agent 都能执行完整开发流程。
V1 的外部系统边界：CI 仅支持 Jenkins；通知步骤不在默认 cascade 内，需由上层 agent 或 V2 adapter 实现；步骤化实施只支持 single-branch，worktree 和 step branch 仅作为 V2 设计预留。
GUI merge 是非核心辅助能力，默认关闭。即使用户开启，如果本地 idea 命令或 Git mergetool 配置不可用，也必须自动降级到文本冲突流程，不能阻断 lifecycle 主流程。gui-merge.command 可以是 idea，也可以是 IDEA 可执行文件完整路径。
项目级 scaffold 阶段与状态分层
dev-lifecycle 的状态分两层，互不混淆：
| 层级 | 状态文件 | 何时写 | phase 前缀 |
|---|---|---|---|
| 项目级（一次性） | .dev-flow/project.json（不入库） |
project-init 生成骨架时 | scaffold:* |
| feature 级（每功能一份） | .dev-flow/states/<feature>.json（不入库） |
dev-spec intake 确定 feature 时 | spec:* / step:* / code:* / 集成与构建态 |
布局：
.dev-flow.yml # 配置（含 scaffold 块），入库
.dev-flow/ # 不入库（.gitignore 必须含）
├── project.json # 项目级状态（scaffold phase）
├── active # feature 活动指针
└── states/<feature>.json # feature 级状态
项目级状态记录"骨架是否就绪"，是 dev-lifecycle 的第 0 个 cascade 节点（项目级、一次性）。feature 级状态记录"某个功能的开发进度"，是现有 spec→code→ci 流程。
项目级与 feature 级的职责边界：
project-init只写项目级状态（.dev-flow/project.json），不建 feature 状态文件。dev-specintake 才建 feature 状态文件（调resolve-active-state.py set <feature>）。project-init完成后停留在 test 分支，移交 dev-spec 开始第一个功能的需求整理。
项目级状态 schema 见 schemas/project-state.schema.json。
多功能并行与活动状态解析
默认每个 feature 一份运行时状态文件，支持从 master 同时切多个 feature 并行开发而互不覆盖。布局（目标项目内，均不入库）：
.dev-flow.yml # 提交配置（不变）
.dev-flow/ # 本地，加入 .gitignore
├── active # 活动指针：当前正在开发的功能 slug（纯文本单行）
└── states/
└── <feature>.json # 每功能一份运行时状态
.dev-flow-state.json # 旧单文件，向后兼容（state.storage: single 时使用）
在 .dev-flow.yml 配置（默认即生效，可省略）：
state:
storage: per-feature # per-feature（默认）| single（旧单文件模式）
dir: .dev-flow/states
pointer: .dev-flow/active
What ships with it
9 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.
- adapters/claude-code.md 5.9 KB
- README.md 3.5 KB
- schemas/dev-flow-state.schema.json 9.9 KB
- schemas/dev-flow.schema.json 15 KB
- schemas/project-state.schema.json 3.8 KB
- scripts/resolve-active-state.py 22 KB runs code
- scripts/update-step-state.py 5.1 KB runs code
- skill.json 1.1 KB
- templates/java-maven-jenkins.yml 4.1 KB
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 First seen · 493 lines · 59 tokens per session scan A f3b6e2fff7cc
dev-lifecycle is a skill published in the GitHub repository linshidream/skill-hub (19 stars, last pushed 21d ago), licensed MIT. It adds 59 tokens to every session and 6,738 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…