neeko: Skill for Claude Code

.agents/skills/code-walkthrough/SKILL.md

code-walkthrough is a skill for Claude Code from tincopper/neeko. It costs 128 tokens per session (3,895 once invoked), scanned A, original, Apache-2.0.

A guided code-reading and architecture review for the Neeko desktop application. Neeko uses Tauri, which combines a Rust backend with a React interface, and the guide follows data moving between those parts.

In plain words
What is it for?
Use it to walk through files, explain the application's structure, trace calls across Rust and React, and review module boundaries and cross-part contracts.
Why use it?
It helps developers understand an unfamiliar codebase and spot unused code, design inconsistencies, type mismatches, and incomplete migrations without changing the code.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is tincopper/neeko's own configuration. It tells Claude Code how to work on neeko 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 neeko configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/tincopper/neeko/main/.agents/skills/code-walkthrough/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/tincopper/neeko

Made for: Claude Code.

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 code-walkthrough

README.md
[![agentmods](https://agentmods.dev/badge/skills/tincopper/neeko/code-walkthrough/github.svg)](https://agentmods.dev/skills/tincopper/neeko/code-walkthrough)
Your own site
<a href="https://agentmods.dev/skills/tincopper/neeko/code-walkthrough"><img src="https://agentmods.dev/badge/skills/tincopper/neeko/code-walkthrough/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 code-walkthrough

Your own site · 80×15
<a href="https://agentmods.dev/skills/tincopper/neeko/code-walkthrough"><img src="https://agentmods.dev/badge/skills/tincopper/neeko/code-walkthrough.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,895 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 $0.00128 $0.03895
Opus 5.5 $0.00051 $0.01558
Sonnet 5.5 $0.00026 $0.00779
Haiku 4.5 $0.00013 $0.00390

Measured 16d ago against content hash f86881238191, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-walkthrough 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 16d 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/code-walkthrough/SKILL.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Walkthrough

与用户共同阅读 Neeko 代码,逐文件讲解 Tauri 应用架构、跨端数据流与设计决策。纯讲解 + 审查,不修改代码。


核心原则

  1. 先全景再深入 -- 先建立模块全局地图,再逐文件探索;不知道全貌就不知道该看什么
  2. 逐文件推进 -- 每次只读一个文件,讲完要点、确认用户无问题后再继续,不批量扫
  3. 证据驱动 -- 所有讲解必须引用具体文件路径和行号,不凭印象说话
  4. 主动审查 -- 阅读过程中主动标注 dead code、设计偏差、类型不一致、迁移遗漏,但不修改代码
  5. 交互确认 -- 每个文件讲完后等用户确认,用户有疑问优先解答再继续
  6. 用户主导节奏 -- 用户说"继续"才到下一个文件,用户说"看看这个"就切换焦点
  7. 双端意识 -- 始终关注 Rust 后端与 React 前端的契约关系,标注跨端依赖

Neeko 架构概览

Neeko 是基于 Tauri 2 + React 18 的桌面应用。代码分为三个域:

┌─────────────────────────────────────────────────────────────────┐
│                         React 前端 (src/)                        │
│  components/ → hooks/ → store/ ← contexts/ ← types.ts          │
└───────────────────────────┬─────────────────────────────────────┘
                            │ @tauri-apps/api/core.invoke()
                            │ Tauri Events (listen/emit)
┌───────────────────────────┴─────────────────────────────────────┐
│                    Rust 后端 (src-tauri/src/)                     │
│  commands/ → managers → models/ + storage.rs + git/ + skill/    │
└─────────────────────────────────────────────────────────────────┘

核心数据流:

  • 前端 → 后端:hooks 调用 invoke("command_name", args) → Tauri IPC → commands/<domain>.rs → managers
  • 后端 → 前端:app.emit("event-name", payload) → 前端 listen() → hooks/store 更新
  • 类型契约:src-tauri/src/models/ ↔ src/types.ts(serde 序列化)

两种模式

模式 A:三域分层(默认)

从数据模型开始,按三个域逐层向上阅读。

适用场景:新接手模块、架构改造后全貌理解、PRD 实现 review。

域与层级:

域 1: Rust 后端(src-tauri/src/)
├── Layer 1: 数据模型(models/)             -- 共享契约层,Rust ↔ TS 类型同步
├── Layer 2: 存储层(storage.rs)            -- JSON 持久化
├── Layer 3: Manager(terminal.rs, project.rs, agent.rs 等) -- 业务逻辑核心
├── Layer 4: 命令层(commands/)             -- Tauri IPC 入口,参数校验 + 错误转换
└── Layer 5: 应用组装(app/, app_state.rs)  -- 依赖注入 + 命令注册

域 2: 跨端桥接
├── Layer 6: 类型契约(models/ ↔ types.ts)  -- 结构体/接口对齐
└── Layer 7: IPC 通道(invoke/events)       -- 命令名 + 事件名映射

域 3: React 前端(src/)
├── Layer 8: 类型定义(types.ts)            -- TypeScript 接口
├── Layer 9: 状态管理(store/, contexts/)    -- 全局状态 + 领域动作
├── Layer 10: 自定义 Hooks(hooks/)         -- 业务逻辑封装 + invoke 调用
└── Layer 11: UI 组件(components/)         -- 渲染 + 用户交互

Read the full file on GitHub · 327 lines

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. 16d ago Changed f86881238191
  2. 1mo ago First seen · 327 lines · 128 tokens per session scan A 5f1b096bc6e9

Subscribe to this mod's changes

code-walkthrough is a skill published in the GitHub repository tincopper/neeko (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 128 tokens to every session and 3,895 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

kirocrew-app-dev

Build, package, and publish Kiro Crew external apps. Covers app.json manifests, UI components, crons, skills, lifecycle hooks, development mode, registry publishing, and common pitfalls.

kirodotdev/KiroCrew · 44 tokens

goal-conductor

Own a goal too large for one session ('clear the flaky-test backlog', 'push N PRs green') end to end via the work ledger — decompose into items, one session per item, read worker status as data, verify claims with the acceptance evaluator, decide each round until done. Use when handed such a goal.

kirodotdev/KiroCrew · 70 tokens

cost-efficiency-analyzer

Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for "are we spending too…

awslabs/agentcore-samples · 98 tokens

computer-use

Read and drive native desktop apps through the accessibility layer — list apps, snapshot a window as a numbered element tree, then click/type/scroll/drag by element index or screen coordinates. Use for a desktop app, not a web page. macOS + Windows; off unless enabled in Settings.

kirodotdev/KiroCrew · 62 tokens

security-conductor

Operating procedure for the kirocrew-security-conductor agent. Use when a security conductor session is seeded, inspected or debugged. Run vulnerability discovery on one target as a supervised fleet — one auditor per attack surface, an independent verifier per finding, two human gates.

kirodotdev/KiroCrew · 57 tokens

feature-demo-recording

Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…

kirodotdev/KiroCrew · 90 tokens