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-reviewnpx skills add Peiiii/nextclaw --skill development-reviewgit 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-review)<a href="https://agentmods.dev/skills/peiiii/nextclaw/development-review"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/development-review.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00058 | $0.01004 |
| Opus 5 | $0.00029 | $0.00502 |
| Sonnet 5 | $0.00012 | $0.00201 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
development-review 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 yesterday.
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 Review
目标
回答“这份已经实现并验证的改动是否可以被接受”。优先检查正确性、回归风险、契约清晰度和可维护性压力，而不是停留在样式偏好。
进入
- 有实现产物时，在验证证据稳定后进入；
- 用户明确要求代码 review、PR review、风险扫描或拟议修复评审时可直接进入；
- 纯文档、措辞和普通元信息只做内容、结构和 diff review，不运行代码维护性脚本；
- 普通局部改动使用轻量 review，L3-L4、跨模块、结构大改或用户明确要求时执行完整 findings-first review。
自动检查
源码、脚本、测试或运行链路配置改动先运行一次 diff-only 检查：
node .agents/skills/development-review/scripts/check-maintainability.mjs
范围明确时优先缩窄：
node .agents/skills/development-review/scripts/check-maintainability.mjs --paths <touched-files...>
--non-feature 只用于明确把非测试净增 <= 0 设为交付合同的治理/减债任务，普通 bugfix、refactor 或 cleanup 不默认启用。
脚本默认阻塞本次新增或恶化的文件/函数/目录预算违规、新复杂度、eslint-disable 绕过、职责错配、红区缺少记录和治理违规；历史债务、接近预算线和普通净增长只作为信号。不得为消除普通净增长扩大无关范围、压缩可读性或删除类型/协议保护。
Findings-first 审查
- 明确 diff、触达文件、相邻合同和受影响测试。
- 重建改动前后真实用户或调用方可观察行为。
- 优先检查正确性、边界、状态迁移、异步、数据流、API/UI 合同和运行失败模式。
- 判断测试是否保护稳定外部行为；只有真实回归路径缺保护时才把缺测试列为 finding。
- 检查改动是否把单次实例抬成全局机制、把局部经验固化为公共合同，或让抽象层级高于证据；同时检查重复真相、隐藏 fallback、无收益抽象，以及小 diff 保留的错误 owner、重复生命周期和确定迁移债。
- 双向比较删除无收益路径与继续压缩造成的欠设计，按全生命周期净复杂度选择修正，不预设抽象或最小改动为答案。
- 对重复 UI 骨架判断是否应采用共享骨架、类型化配置和薄壳组合。
- 输出按严重级别排序的 findings、证据、风险和可信修复方向。
净增长本身不是 finding；更小实现只有在不新增双 owner、错误边界、迁移债和恢复缺口时才是有效反例。强行压行、隐藏或转移复杂度同样是 finding。
条件主观复核
只有以下情况才读取主观可维护性复核：
- 自动检查告警需要主观判断；
- 抽象、owner、文件或目录边界发生明显变化；
- 改动跨模块、规模较大或维护风险明显；
- 用户明确要求二次复核。
自动检查通过后的普通局部改动不追加完整主观复核。
通过与返工
- 只要存在一个未关闭 finding，Review 就不通过，返回
rework和 Design 或 Implementation 目标。 - 修改产物后，旧验证证据失效；必须重新验证并再次 Review。
- 只有 findings 清零后才允许输出
no findings或等价通过结论。 - 外部阻塞导致 finding 无法关闭时，明确阻塞项和风险，结论仍然不通过。
输出
顺序固定为：
- 按严重级别排序的 findings；
- 开放问题或前提假设；
no findings或未通过结论、自动检查范围、主要警告和剩余风险。
本阶段不修改实现、不重新执行功能验证，也不 commit、push、release 或 deploy。
What ships with it
12 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.
- agents/openai.yaml 364 B
- references/subjective-review.md 836 B
- scripts/check-maintainability.mjs 1.5 KB runs code
- scripts/maintainability-guard-core.mjs 15 KB runs code
- scripts/maintainability-guard-directory-budget.mjs 2.4 KB runs code
- scripts/maintainability-guard-directory-budget.test.mjs 2.6 KB runs code
- scripts/maintainability-guard-hotspots.mjs 5.1 KB runs code
- scripts/maintainability-guard-hotspots.test.mjs 1.4 KB runs code
- scripts/maintainability-guard-line-changes.mjs 3.7 KB runs code
- scripts/maintainability-guard-lint.mjs 1.6 KB runs code
- scripts/maintainability-guard-support.mjs 12 KB runs code
- scripts/maintainability-guard-support.test.mjs 2.7 KB runs code
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.
- yesterday Changed 56216a760059
- 5d ago First seen · 73 lines · 58 tokens per session scan A ccafca3553ac
development-review is a skill published in the GitHub repository Peiiii/nextclaw (254 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 1,004 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
ha-mac-control
Hope Agent native macOS desktop control — the standard maccontrol status / diagnostics / apps / dock / spaces / snapshot / visual / windows / menu / clipboard / dialog loop, target-first action rules, no-blind-coordinate policy, and recovery for stale AX/window/menu/dialog state. Load whenever using maccontrol, or…
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'…
ha-pet-import
Safely import, select, switch, or enable a compatible desktop pet in Hope Agent. Resolve packages from any origin, including local folders, zip archives, pet.json plus a sprite, PNG/WebP atlases, chat attachments, repository or cloud files, direct HTTPS artifact URLs, and download pages. Use whenever a user asks to…
feishu
Use when the user mentions 飞书 / Feishu / Lark workspace operations: docx (云文档) read/write, bitable (多维表格) records / views / dashboards, drive (云盘) upload/download, wiki (知识库) link resolution, approval (审批) instance create/cancel/query, calendar (日历) event create/list/update + attendees, contact (联系人) user/department…