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/peiiii/nextclaw/development-lifecyclenpx skills add Peiiii/nextclaw --skill development-lifecyclegit clone --depth 1 https://github.com/Peiiii/nextclawWhat 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 | $0.00051 | $0.01840 |
| Opus 5 | $0.00026 | $0.00920 |
| Sonnet 5 | $0.00010 | $0.00368 |
| Haiku 4.5 | $0.00005 | $0.00184 |
Grade A, and why
development-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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Lifecycle
Lifecycle observer
当前 observer：development-task-telemetry。
- observer 路径存在即启用，只在进入本流程时加载一次；它只接收既定 task / phase，不参与路由、返工或完成门。
- 子 Agent 接收父任务的 observer、task-id 与 phase；缺失或加载失败时说明 unavailable 并继续。
- 把“当前 observer”设为空即可停用；本节不复制 observer 的具体输出协议。
定位
这是普通源码、脚本、测试、运行链路和从方案到实现任务的唯一默认流程 owner。开始时只加载本入口；进入某一阶段后才加载该阶段 owner，不预读未来阶段。
总流程只负责阶段状态和任务完成，不拥有调查、设计、实现、验证、review、发布或沉淀的内部方法。
风险为 L3-L4，或用户明确给出验收标准、要求大型/多阶段/低监督完整交付时，加载 acceptance-contract-governance，建立 active contract 与 stable acceptance IDs；它不是新 phase，普通 L0-L2 任务不加载。
开始
并发提交或主线并发时，读取Worktree 合同。
先确定六件事：
- 一个可观察的最小完整结果；
- 任务类型：
feature、bugfix或small-change； - 最近 owner 和影响面；
- 风险等级 L0-L4；
- 当前阶段；
- 完成任务所需的最小可信证据。
命中时记录 contract-id、parent-goal、ledger 落点和 Required acceptance IDs；设计/计划清单先登记，不能凭文档存在进入 gate。
用户当前任务同时明确开启省 Token 并要求子代理时才读取省 Token 委派合同；效率、省 Token 或并行本身不授权委派。
风险定义：L0 文档/元信息；L1 局部低风险代码或展示；L2 交互、状态、局部行为或明确 bug；L3 跨 owner/transport、持久化、兼容或运行链路；L4 发布、迁移、生产或不可逆操作。
任务类型按主要意图互斥归类：bugfix 恢复已有合同；feature 新增或实质改变能力；small-change 仅用于前两者都不成立且局部、可逆、沿用惯例的琐碎改动。依次判断并在 Task Understanding 冻结；新证据改变意图时显式修正。类型不替代风险，telemetry 不参与分类。
bugfix 还必须在 Task Understanding 显式选择 reproduce 或 skip-reproduction 并留下证据；复现不是独立 phase，具体门槛归 Task Understanding 和 Validation owner。
设计门
Task Understanding 后、Implementation 前显式判断 Design，任务类型不能自动决定。仅当同时记录 skip-design、design-document: not-required 和单一路径依据，风险 L0-L1，只触达一个 owner，不改变跨层合同/状态/持久化/兼容/迁移/fallback，无未决工作流、交互取舍或真实方案分叉，且改动局部可逆、验证直接时跳过；feature 还须结果与行为边界清楚，bugfix 还须根因、路径和修后判定确认。否则进入 development-design，返回设计文档与 plan 决定；plan 不是 phase。diff 小、时间紧或“显然”不是依据。
阶段路由
按当前阶段只选择一个 owner：
- 任务理解、现状取证、范围和成功条件：
development-task-understanding。 - 设计门不满足全部跳过条件，或用户明确要求设计：
development-design。 - 按已确认目标和设计修改产物：
development-implementation。 - 证明行为、合同和运行链路：
development-validation。 - 判断改动是否可接受并关闭 findings：
development-review。 - 结果交接、提交、发布或部署：
development-delivery。 - 任务结束前的轻量反思和条件沉淀：
development-retrospective。
What ships with it
2 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.
- 2d ago First seen · 118 lines · 51 tokens per session scan A d344b6317cbd
development-lifecycle is a skill published in the GitHub repository Peiiii/nextclaw (253 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 1,840 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
add-linear
Add Linear channel integration via Chat SDK. Issue comment threads as conversations.
ha-skill-creator
Create, edit, improve, or audit Hope Agent skills. Use when the user wants to: (1) create a new skill from scratch, (2) edit or improve an existing skill, (3) review or clean up a SKILL.md file, (4) run evaluations to test skill effectiveness, (5) optimize skill descriptions for better trigger accuracy. Trigger…
ha-browser
Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…
ha-logs
Self-service diagnostics — query Hope Agent's local SQLite databases (logs / sessions / background jobs) directly via the exec tool to investigate problems, analyze usage, and locate root causes. Trigger on: user reports something broken / failing / slow / stuck / not responding ('X 不工作', 'X 报错', 'X 卡住', '为什么 X 失败'…
china-translate
中英互译 + 本地化 - 技术翻译、UI本地化、文化适配、避免机翻腔.
weibo-poster
微博内容创作 - 140字优化、话题热搜、@提及策略、配图描述、发布时机.