Borrowing it
Nothing to install: this file belongs to tincopper/neeko. 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/tincopper/neeko/main/.agents/skills/neeko-check/SKILL.mdgit clone --depth 1 https://github.com/tincopper/neekoWrote 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/tincopper/neeko/neeko-check)<a href="https://agentmods.dev/skills/tincopper/neeko/neeko-check"><img src="https://agentmods.dev/badge/skills/tincopper/neeko/neeko-check/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/tincopper/neeko/neeko-check"><img src="https://agentmods.dev/badge/skills/tincopper/neeko/neeko-check.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 | $0.00062 | $0.03604 |
| Opus 5.5 | $0.00025 | $0.01442 |
| Sonnet 5.5 | $0.00012 | $0.00721 |
| Haiku 4.5 | $0.00006 | $0.00360 |
Grade A, and why
neeko-check 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 21d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neeko Check
Neeko 代码审核规范（Code Reviewer）
术语纪律（硬指令）：本项目审查只用「红线」。旧 neeko-check「支柱 / Pillar」体系 （13/15 条、编号与本表不同）已废止（根
AGENTS.md「AI 代码审查红线」明文）。本 skill 内一律按现行 15 条红线编号引用；不得再出现「支柱 / Pillar」作为规则名。
定位：审核代码是否符合三层标准：
- 项目规范 —— 15 条红线（全文按代码物理边界分文件存放；根
AGENTS.md的红线索引表是唯一台账）- 业界最佳实践 ——
docs/best-practices/index.md（React / Rust / 通用工程）- 架构设计 —— 根
AGENTS.md「架构基本原则（强制）」
按改动所在侧取红线全文，否则等于漏审：
- 跨栈红线 4 / 5 / 14 全文在根
AGENTS.md；- 后端红线 1、2、3、6、7、8、9、10、11、13、15 全文在
src-tauri/AGENTS.md；- 前端红线 12 全文在
src/AGENTS.md。审核
src-tauri/**前必须读src-tauri/AGENTS.md；审核src/**前必须读src/AGENTS.md。 以编号定位规则，不要按标题文字猜。标准缺失时提示补到对应AGENTS.md，不在本 skill 内新增规则。
核心使命
死守单机 OS 资源底线，捍卫多平台编译一致性，确保 Neeko 长期架构可维护性。
审核流程
Step 0：确定审核范围（增量 / 全量）
- 运行
git status --short与git diff --name-only HEAD，判断是否有未提交 / 已暂存改动。 - 有改动 → 走【增量审核】：
- 只对改动文件应用相关红线与最佳实践，不扫描全库。
- 除非用户明确说「全量审核 / 检查整个项目 / full check」，否则不得扩大范围。
- 无改动（工作树干净）→ 走【全量审核】：对全库应用全部红线与最佳实践。
- 报告开头必须标注：
模式：增量（N 个文件）或模式：全量。
Step 1：载入落点文件
- 根
AGENTS.md：红线索引表 + 架构基本原则（强制）。 - 改动涉及
src-tauri/**→ 读src-tauri/AGENTS.md（该侧全部红线全文）。 - 改动涉及
src/**→ 读src/AGENTS.md（红线 12 全文 + 导入防火墙 / 状态管理）。 - 需要机制依据时按需载入
.trellis/spec/{backend,frontend,security,unit-test}/。
Step 2：逐条核对 15 条红线
按下方「15 条红线导航表」定位相关红线，回落到点文件读全文再判定；缺审查项即等于漏审。
Step 3：架构与最佳实践
- 架构基本原则：高内聚低耦合 / 单一职责 / 依赖倒置 / 开闭原则 / DRY / KISS / YAGNI。
- 业界最佳实践：
docs/best-practices/index.md索引下的 React / Rust / 通用工程文件。 - 前端专属：Feature-Based 目录内聚 + 导入防火墙（
src/AGENTS.md）。 - 后端专属：Domain-Driven 目录 + Skinny Command（
src-tauri/AGENTS.md）。
Step 4：按模板输出报告
15 条红线导航表
全文以
AGENTS.md为准，本表只做定位与摘要（够用来识别并停止违规）。判据与例外一律回落到点文件。
| # | 红线 | 必须 / 禁止（摘要） | 全文落点 |
|---|---|---|---|
| 1 | 统一命令执行接口（Local/WSL/SSH） | 命令只走 core::exec / common::executor，禁止直接用 std::process::Command |
src-tauri/AGENTS.md |
| 2 | 跨平台 shell 选择（cmd /c vs sh -c） |
Local 按平台选 shell，禁止硬编码 sh -c / bash -lc |
src-tauri/AGENTS.md |
| 3 | 阻塞 I/O 隔离（spawn_blocking） |
异步中 std::fs / std::process / portable-pty 阻塞读写必须包 spawn_blocking |
src-tauri/AGENTS.md |
| 4 | IPC 大文本边界 | 单次 Command 返回 JSON ≤ 2MB；大载荷走二进制流 / 分页 | 根 AGENTS.md |
| 5 | Event 名常量化 | Event 名双端只来自单一常量源，禁止各自硬编码 | 根 AGENTS.md |
| 6 | Command 层保持极薄 | #[tauri::command] 只做参数校验 + 调度，核心逻辑落 manager/service |
src-tauri/AGENTS.md |
| 7 | if let 嵌套不超过 3 层 |
≥3 层连续解构拍平成 match；仅 1–2 条 happy path 才用 if let |
src-tauri/AGENTS.md |
| 8 | 路径安全校验（canonicalize + capabilities 白名单） |
前端传入路径消费前必须 canonicalize；capabilities 禁止 allow-all |
src-tauri/AGENTS.md |
| 9 | mod.rs 保持极薄 |
mod.rs 只允许 mod 声明 + pub use，业务 fn / impl 抽同级文件 |
src-tauri/AGENTS.md |
| 10 | 平台代码规范化（Platform Adapter） | 平台差异与单平台代码必须落 platform/<theme>/，通用文件禁止平铺 #[cfg] |
src-tauri/AGENTS.md |
| 11 | 换行边界（Line-Ending Boundary） | 禁止注入 core.autocrlf；禁止对工作区换行做字节级断言 |
src-tauri/AGENTS.md |
| 12 | 路径身份唯一化（FileRef） |
同文件判定必须走 FileRef，禁止消费侧自造字符串归一 / 别名匹配 |
src/AGENTS.md |
| 13 | 测试夹具路径平台无关 | 夹具路径一律由 tempdir() 推导，禁止硬编码 POSIX 绝对路径 |
src-tauri/AGENTS.md |
| 14 | LSP 能力声明必须与实现一致 | 声明客户端能力前先确定消费点，同一 diff 内给出实现或删声明 | 根 AGENTS.md |
| 15 | 语言差异必须落在插件数据 | 语言差异只允许作为 LspPlugin 字段，通用模块禁止 language_id 分支 |
src-tauri/AGENTS.md |
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.
- 21d ago Changed · -29 lines · +8 tokens per session e93a770df89f
- 1mo ago Changed · +5 lines 15e1789d8281
- 1mo ago First seen · 208 lines · 54 tokens per session scan A 0b700bd277c6
neeko-check is a skill published in the GitHub repository tincopper/neeko (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 62 tokens to every session and 3,604 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 2026-08-31.
Other skills, from other repositories
sage-review
Deep, platform-neutral code review for PRs and CRs in ONE thorough single pass — design reasoning (Problem Worth Solving & Solution Fit) as one dimension alongside the 9 code-level dimensions, with chain-of-consequences, self-critique, and draft-only comments. The single app-owned source of truth.
learn-from-sage
Detection-gap (miss) analysis for Code Review Sage. Learn from shipped fixes, acted-on human comments, and design outcomes to close reviewer blind spots. Inline during review stages a candidate; a human triggers a one-shot AI consolidation into the live ruleset.
review-fix-signoff-loop
Use when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context until independent signoff agents, typically Claude and Codex, both agree the work is comprehensively complete. Covers fresh-context iterations, repairable gates, dual reviewer verdict contracts…
bmad-code-review
Review code changes with several independent reviewers in parallel, then triage and present the findings. Use when the user says "run code review" or "review this code".
bmad-walkthrough
Guide a human review of a commit, PR, file, or directory. Use when invoked by name.
bmad-review
Runs one or more installed review lenses — adversarial critique, edge cases, verification gaps, structure, prose — and reports triaged findings. Use when, and only when, the user asks you to review a diff, a pull request, or an artifact — code or documents, one or many — and actually says "review"; an explicit…