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/chentao326/vibe-code/vibe-initnpx skills add chentao326/vibe-code --skill vibe-initgit clone --depth 1 https://github.com/chentao326/vibe-codeWrote 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/chentao326/vibe-code/vibe-init)<a href="https://agentmods.dev/skills/chentao326/vibe-code/vibe-init"><img src="https://agentmods.dev/badge/skills/chentao326/vibe-code/vibe-init.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 | $0.00093 | $0.03285 |
| Opus 5 | $0.00046 | $0.01643 |
| Sonnet 5 | $0.00019 | $0.00657 |
| Haiku 4.5 | $0.00009 | $0.00329 |
Grade A, and why
vibe-init 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 3d 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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibe-init — 首次 onboarding
让用户从零到能跑第一次评估。新项目 ≤ 5 分钟,已有项目(含历史导入)≤ 10 分钟。
Overview
Phase 0: 检测当前状态
Phase 0.5: 判断新项目 vs 已有项目 → 分叉
Phase 1: 首屏告知(文案因项目状态不同)
Phase 2: 5-6 个问题(一问一答;已有项目多一问"要不要导入历史")
Phase 3: 创建脚手架
Phase 3.5: 历史导入(仅已有项目 + 用户同意)
Phase 4: 安装 hook
Phase 5: 给下一步清单
Workflow
Phase 0: 检测当前状态
- 检查当前目录是否存在
.vibe-state.json- 存在 → 提示"项目已初始化,要重新初始化会覆盖配置——确认?"
- 不存在 → 继续
- 检测项目状态——跑一条命令即可:
git log --oneline 2>/dev/null | wc -l
- 结果 > 0 → 已有项目(有 git 历史)
- 结果 = 0 或 git 不可用 → 新项目/空项目
- 如果是已有项目,额外收集:
- 总 commit 数
- 最早 commit 日期 → 算项目年龄
- 总文件数(
git ls-files | wc -l) - 主要语言(
git ls-files | sed 's/.*\.//' | sort | uniq -c | sort -rn | head -5)
Phase 0.5: 分叉
新项目 → Phase 1 用标准文案,Phase 2 问 5 个问题。
已有项目 → Phase 1 用已有项目文案(含项目统计),Phase 2 问 6 个问题(多一问"要不要导入历史")。
Phase 1: 首屏告知
新项目文案:
🎯 Vibe Code — 初始化
你的下一次编码已经在改写 3 个月后的你。
判断力是客观存在的,区别是你**看见**还是**没看见**。
这套让你看见。
接下来 3-5 分钟我问你 5 个问题,搞清楚你做什么项目、用什么工具。
两件事先说在前面:
1. **早期评估会不准**——前 5 个任务精度大概 ±40%,这是事实。
工具用 🔴🟠🟡🟢🔵 标 confidence,不藏数字。
2. **强烈建议导对标项目**——一个优秀的开源项目,工具立刻有参考 anchor。
准备好开始吗?
已有项目文案:
🎯 Vibe Code — 初始化
你的项目已经跑了 {N} 天,{M} 个 commit,{F} 个文件。
——但你知道自己哪些判断准、哪些判断偏吗?
这套让你的每一次编码变成实验:评估→预估→复盘→进化。
过去 {N} 天的"感觉"没法追回了,但从今天开始的每一行都能被校准。
接下来 3-5 分钟我问你几个问题。最后会问你要不要从 git 历史里导入
几个过去的重要任务——让 rubric 一开始就了解你的项目长什么样。
准备好开始吗?
Phase 2: 问题(一问一答,不批量)
Q1-Q5:所有项目都问
Q1: 项目类型
"你的项目更接近哪一种? a) Web 应用(React/Vue/Next.js 等) b) CLI 工具 c) 库/SDK d) 移动应用 e) 其他"
记录到 project_type:
- a →
"web-app" - b →
"cli" - c →
"lib" - d →
"mobile" - e →
"other"
Q2: 主要语言
"项目主要用什么语言? a) TypeScript/JavaScript b) Python c) Go d) Rust e) Java/Kotlin f) 其他"
记录到 primary_language。
Q3: 数据采集方式
"任务完成后的数据怎么收集? a) 自动采集(推荐)——有 git 就行,自动统计 diff/lint/时间 b) 手动——每次复盘时我口头问你"
- 选 a →
data_collection = "auto",enabled_adapters = ["git-stats"] - 选 b →
data_collection = "manual",enabled_adapters = []
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.
- 3d ago First seen · 327 lines · 93 tokens per session scan A 44c6b25b4ffb
vibe-init is a skill published in the GitHub repository chentao326/vibe-code (2 stars, last pushed 3mo ago), licensed MIT. It adds 93 tokens to every session and 3,285 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…