nextclaw: Skill for Claude Code

.agents/skills/development-design/SKILL.md

development-design is a skill for Claude Code, Codex from Peiiii/nextclaw. It costs 56 tokens per session (2,023 once invoked), scanned A, original, MIT.

A development-stage guide for deciding how a software change should be designed before it is built. It examines the problem, evidence, ownership, alternatives, state changes, compatibility, failure handling, and the need for a lasting design document or implementation plan.

In plain words
What is it for?
It is for designing features and fixes that cross system boundaries, change user-visible behavior, affect stored state or protocols, require migration or fallback, or need decisions preserved for later work.
Why use it?
It prevents teams from filling gaps with guesses or starting implementation before important choices are settled. It clarifies what should change, what should remain unchanged, and how the result will be checked.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Peiiii/nextclaw's own configuration. It tells Claude Code and Codex how to work on nextclaw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nextclaw configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Peiiii/nextclaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Peiiii/nextclaw/master/.agents/skills/development-design/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Peiiii/nextclaw

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for development-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/peiiii/nextclaw/development-design/github.svg)](https://agentmods.dev/skills/peiiii/nextclaw/development-design)
Your own site
<a href="https://agentmods.dev/skills/peiiii/nextclaw/development-design"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/development-design/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.

agentmods 80×15 button for development-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/peiiii/nextclaw/development-design"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/development-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,023 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.02023
Opus 5.5 $0.00022 $0.00809
Sonnet 5.5 $0.00011 $0.00405
Haiku 4.5 $0.00006 $0.00202

Measured 29d ago against content hash 864fa13695ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

development-design 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 29d 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.

.agents/skills/development-design/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Development Design

目标

回答“采用哪条主链路,为什么”。证据不足则返回调查。

实现前冻结验收与交付,不自行缩减用户结果。明确交付物与授权,给出 1–3 条“黄金验收”链路:目标 → 前提/真实入口 → 操作 → 响应 → 后续操作 → 结果 → 成败判定。入口、功能清单或技术调用链不能代替使用链路。标明等待成本、AI 自验证据及用户判断项;安装、测试和排障由 AI 承担。黄金验收覆盖完整标准但不替代 AI 自验;active contract 复用 IDs,按行为差异补矩阵。

验收适用性按用户行为与结果是否变化判断:没有新增 UI、只改底层或尚未发布,不构成豁免。纯内部重构且用户行为不变、规则维护或用户明确限定的源码/Review/原型交付,说明依据并提供匹配产物,不虚构产品使用链路。

稳定设计写入 docs/designs/YYYY-MM-DD-<topic>.design.md;局部方案可内联。大型交付的独立结果/决策须在实现前落盘;已有设计可引用,缺口和关键变更先补原文并链接历史。影响当前实现的选择先解决;分阶段须证明必要性。

有效合同形成或变化后,核对已有方案是否仍覆盖当前目标;受影响的设计、黄金验收和旧方案 Review 结论失效,补齐并复审后才能据此实现。未受影响部分继续复用,不把早期方案中的“未来扩展”当作新合同的范围决定。

产物分级

大型交付可按独立能力或独立审查需要拆专题设计:整体设计链接专题,专题引用上位约束并注明负责范围与适用状态,不复制全局合同。当前执行状态指向本项采用的设计和 Review 结论;拆文件不新增交付阶段。

输出设计结论与 design-document: required | not-required;feature/bugfix 共用产物门。

轻量设计限单 owner、无跨层合同/状态/兼容或真实分叉、局部可逆且不复用;写清问题、主链路、理由与验证。

出现以下任一情况,必须写入或更新稳定的 docs/designs 文档:

  • L3-L4,或跨 package、runtime、projection、transport、持久化边界;
  • 用户可见 L2 功能存在交互、信息架构或行为取舍;
  • 改变状态 owner、生命周期、不变量、协议、兼容、迁移、fallback 或失败恢复;
  • 有两个以上真实可行候选,需要记录选择与放弃理由;
  • 设计会跨会话、跨批次、交给他人实现,或预计成为后续判断依据。

L0 文档修正和 lifecycle 可跳过的 L1 单路径改动无需进入;不按 diff、工时或文件数决定是否建文档。

计划门

进入 Implementation 前输出 plan: required | not-required。单批无法可信闭环时使用开发执行 Plan 合同,否则不建;Plan 不是新 phase。

设计合同

只展开与当前任务相关的维度:

  • 大型交付记录“来源/版本 → 有效要求/ID → 设计位置 → 验证”,保留原始输入与全局约束;偏离写依据,未经授权不改用户结果。替代的旧输入保留溯源,原型不能只核对外观。
  • 用户或系统可观察问题;
  • producer、owner、consumer、已有约束与现有能力复用证据;
  • 真实分叉时的 2-4 个候选:用户价值、owner、复杂度、可逆性、验证成本及主链路;路径明显不虚构候选;
  • 状态、生命周期、不变量、失败/恢复、目录/公共入口/依赖边界;
  • 第三方框架/runtime/协议:冻结上游执行、线程、生命周期、资源与错误合同及产品保留职责;偏离须有必要性、官方依据、验证和退出条件;
  • 删除或禁止的平行路径,兼容/迁移/fallback 的必要性与退出条件;
  • 非目标与最小验证标准。

性能/成本影响选型时,沿同一代表性任务比较等待、资源和成本,区分实测、估算与未知;引用 active contract 门槛并给出昂贵分支验收路径。缺关键数据先做最小实验,不凭理论冻结结论;无相关取舍不加基准测试。

跨运行宿主、存储归属、能力目录或主要用户链路的设计,按功能设计关对账旧能力、用户目标和候选能力;关键入口、权限边界或验收路径未定时保持未就绪。

证据足够时冻结占优方案;仅当选择显著改变用户行为或范围且无法判断偏好时,才请求用户决定。

思考投入

新项目、技术栈替换或新增影响运行/部署的关键依赖,必须在搭建产品脚手架、安装正式依赖和编码前按技术栈选型形成技术决策与依据;限定问题的可丢弃验证实验可先执行。用户指定技术仍核对适用性。沿用现有栈的普通小改只说明沿用依据,不例行比较或加载该参考。

Read the full file on GitHub · 101 lines

Files

What ships with it

6 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.

Changes

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.

  1. 29d ago Changed · +2 lines 864fa13695ff
  2. 1mo ago Changed · +6 lines 593b09175f93
  3. 1mo ago Changed · +3 lines f61024885490
  4. 1mo ago Changed · -7 lines 2608afd4529f
  5. 1mo ago Changed · +2 lines d7bdf9666eab
  6. 1mo ago Changed 887289423dfd
  7. 1mo ago Changed · +3 lines 5c08e2fe2a62
  8. 1mo ago Changed ef0c8b26cb5f
  9. 1mo ago Changed · +4 lines 9e486b208178
  10. 2mo ago First seen · 88 lines · 56 tokens per session scan A 95d9d3cec3dc

Subscribe to this mod's changes

development-design is a skill published in the GitHub repository Peiiii/nextclaw (263 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 2,023 once invoked, about $0.0002 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.

Related

development-design compared with skills from other repositories

development-design next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
development-designPeiiii/nextclawSkill263yesterdayMITA56Claude Code, Codex
ha-skill-creatorshiwenwen/hope-agentSkill1.9kyesterdayMITA106Claude Code
ha-browsershiwenwen/hope-agentSkill1.9kyesterdayMITA140Claude Code
ha-logsshiwenwen/hope-agentSkill1.9kyesterdayMITA183Claude Code, Codex
ha-pet-importshiwenwen/hope-agentSkill1.9kyesterdayMITA109Codex
ha-skill-installershiwenwen/hope-agentSkill1.9kyesterdayMITA82Claude Code, Codex
email-draftshiwenwen/hope-agentSkill1.9kyesterdayMITA46Claude Code, Codex