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.
curl -O https://raw.githubusercontent.com/Peiiii/nextclaw/master/.agents/skills/development-implementation/SKILL.mdgit clone --depth 1 https://github.com/Peiiii/nextclawWrote 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/peiiii/nextclaw/development-implementation)<a href="https://agentmods.dev/skills/peiiii/nextclaw/development-implementation"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/development-implementation/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/peiiii/nextclaw/development-implementation"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/development-implementation.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 | $0.00058 | $0.01044 |
| Opus 5.5 | $0.00023 | $0.00418 |
| Sonnet 5.5 | $0.00012 | $0.00209 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
development-implementation 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 1mo 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.
What it actually says
Development Implementation
目标
回答“如何按照已确认目标和设计，以最小、清晰、单一的路径落地”。进入时必须已有可观察结果、最近 owner、影响面、风险和最小验证标准；证据或设计不足时返回相应返工阶段。
standard 或正式 bugfix 设计还须有 design-review: passed 及预定验收标准；trivial/内联修复须有明确跳过依据与判定条件。不把设计自审或实现后的测试当作方案 Review。
实现前检查
首次实质编辑前直接回答：
- 能否删除、复用或收敛已有路径？
- 事实、状态和生命周期的 owner 是否正确？
- 是否新增无当前调用者、只服务未来可能性的 type、interface、方法、配置字段，或无语义 wrapper、adapter、factory、proxy、参数搬运和第二入口？命中时不得边写边扩张，返回设计收窄范围。
- fallback、兼容和恢复是否位于真实边界，并有可观察信号和退出条件？
- 是否新增、移动、重命名文件或改变目录角色？命中时先检查项目文件组织规则，并在编辑前运行项目已有的 planned-path preflight；没有该入口时至少核对目标路径和职责边界。
每开始一块工作，核对适用设计与 Review 是否覆盖当前部分；无 plan 也适用。大型交付有独立结果或设计决策的部分，必须定位书面方案具体段落、原始输入对齐和适用 Review 结论；缺一返回对应 owner，不能以“总体已设计”或聊天承诺放行。原先留白、尚未细化或新决策返回 Design，不边编码边补未冻结设计。已有 plan 时同时执行其设计策略；既定方案内惯例细节不新建方案。探索限定问题与判定，未完成适用设计/Review 前不作为正式交付。
实现合同
- 保持单一路径、稳定合同和可见主流程；必要、安全、清晰的最小增长允许存在。
- 同一事实、事件、状态变化或传输语义只有一个 owner 和一条标准链路。
- 新 wrapper、adapter、factory、service、manager 必须减少真实复杂度或隔离真实变化点。
- 删除或复用旧实现；不得为抵消行数扩大无关范围或损害可读性、类型和协议安全。
- 业务层传递 owner 或本次调用的数据快照，不把稳定 owner 拆成多层 proxy 和同名转发。
- 跨 workspace package 只使用公共入口或
exports。 - 前端业务状态与编排归 manager/store/presenter；组件和 hook 主要连接、展示与同步外部系统。
- 实现与已冻结设计不一致时，先区分模型缺口还是实现偏差，不边写边悄悄改变设计。
条件方法
- 当前决策涉及项目专项前端、兼容或 runtime 方法时，由已冻结设计或项目入口选择当前需要的一项，不在实现阶段重新选型。
- 只有用户明确讨论简单性、拆分收益、过度防卫、过度抽象或代码审美，且需要裁决保留、拆分还是抽象时，才读取实现工艺。
- 工具链无法运行时先核对项目固定的版本与恢复入口；不要用全局工具静默替代项目工具链。
普通实现不预读这些条件材料。
执行节奏
- 触达用户或其它任务的既有改动前先做双向范围审计，避免覆盖、revert、格式化或混入无关内容。
- 每个编辑批次只解决当前责任域；新事实改变方案时返回设计，不用局部补丁堆第二模型。
- 迭代中只运行能指导下一步的最快定向检查；完整证明留给验证阶段。
- 重启现有实例遵循 AGENTS.md 的任务内自主重启规则，不重复请求许可。
输出
返回实际实现、删除或收敛点、迭代证据、与设计的偏差以及仍需验证的风险。本阶段不能用 lint、tsc 或局部测试宣称功能已经完整验证，也不执行最终 Review、commit、push、release 或 deploy。
What ships with it
3 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.
- 1mo ago Changed a5eb655a9ab7
- 1mo ago Changed 0226619c7197
- 1mo ago Changed 20076c94527a
- 1mo ago Changed · +2 lines 39e4ff1aeef2
- 2mo ago First seen · 53 lines · 58 tokens per session scan A 231e4a07a54c
development-implementation is a skill published in the GitHub repository Peiiii/nextclaw (263 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 1,044 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.
development-implementation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| development-implementationPeiiii/nextclaw | Skill | 263 | yesterday | MIT | A | 58 | Claude Code, Codex |
| ha-skill-creatorshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 106 | Claude Code |
| ha-browsershiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 140 | Claude Code |
| ha-logsshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 183 | Claude Code, Codex |
| ha-pet-importshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 109 | Codex |
| ha-skill-installershiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 82 | Claude Code, Codex |
| email-draftshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 46 | Claude Code, Codex |