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/ash1794/vibe-engineering/scope-guardnpx skills add ash1794/vibe-engineering --skill scope-guardgit clone --depth 1 https://github.com/ash1794/vibe-engineeringWrote 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/ash1794/vibe-engineering/scope-guard)<a href="https://agentmods.dev/skills/ash1794/vibe-engineering/scope-guard"><img src="https://agentmods.dev/badge/skills/ash1794/vibe-engineering/scope-guard.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 5.1 | $0.00031 | $0.00603 |
| Opus 5 | $0.00015 | $0.00302 |
| Sonnet 5 | $0.00006 | $0.00121 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
vibe-scope-guard 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 5d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- vibe-scope-guard — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibe-scope-guard
The best code is the code you don't write. Stay focused on what was asked.
When to Use This Skill
- During any implementation task
- When you notice you're "improving" code that wasn't in the request
- When implementation is taking longer than expected
- When you're about to create an abstraction "for later"
When NOT to Use This Skill
- During brainstorming (ideas should be unconstrained)
- When the user explicitly asks for broad improvements
- When scope expansion is necessary for correctness
Scope Creep Signals
Watch for these patterns:
| Signal | Example | Response |
|---|---|---|
| Unrequested features | "While I'm here, let me add caching" | Stop. Was caching requested? |
| Premature abstraction | "Let me create a generic helper for this" | Is it used more than once? |
| Gold plating | "Let me add comprehensive error messages for every case" | Only at system boundaries |
| Refactoring drive-by | "This function could be cleaner" | Was refactoring requested? |
| Over-engineering | "Let me make this configurable" | Does anyone need configuration? |
| Documentation creep | "Let me add docstrings to all these functions" | Only to functions you changed |
| Test over-expansion | "Let me test every possible input" | Test the boundaries, not every input |
The Rule
Three similar lines of code is better than a premature abstraction.
Before adding anything not explicitly requested, ask:
- Was this requested? → No → Don't do it
- Is it necessary for correctness? → No → Don't do it
- Will it break without this? → No → Don't do it
- Is the user watching time/cost? → Yes → Definitely don't do it
Steps
When you detect scope creep:
- Stop — Don't commit the extra work
- Acknowledge — "I notice I'm adding [X] which wasn't requested"
- Offer — "Would you like me to also [X], or should I stay focused on [original task]?"
- If declined — Revert the extra work, continue with original scope
- If accepted — Proceed, but track it separately
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.
- 5d ago First seen · 69 lines · 31 tokens per session scan A 7682bea04b6d
vibe-scope-guard is a skill published in the GitHub repository ash1794/vibe-engineering (10 stars, last pushed 3mo ago), licensed MIT. It adds 31 tokens to every session and 603 once invoked, about $0.0002 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
wechat-article-writer
公众号/自媒体全流程。根据用户表述自动匹配：撰写文章、封面图、正文插图、风格提取。支持多种写作风格。当用户提到写公众号、技术博客、公众号封面、正文插图、步骤图、演示图、流程示意、分析写作风格、克隆文风、模仿爆款、提取风格时使用。详见 reference 目录。.
prepare-release
Prepare a new release by collecting commits, generating bilingual release notes, updating version files, and creating a release branch. Use when asked to prepare/create a release, bump version, or run /prepare-release.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
cherry-assistant-guide
从当前安装包查询 Cherry Studio 产品信息并排查运行问题。当用户询问功能、路由、快捷键、Provider、语言、Agent、频道、定时任务、Code CLI、当前版本，或报告运行错误、连接失败、配置异常并需要诊断时触发。.
cherry-electron-dev
Develop, fix, and profile Cherry Studio in a tracked Electron instance. Use for everyday implementation, UI and interaction work, bug fixing, runtime debugging, DevTools inspection, lag or jank investigation, CPU and memory monitoring, leak checks, and startup-performance analysis; reuse a verified workspace instance…
issue-reporter
只在用户明确要求提交 GitHub Issue、GitHub Bug Report 或 GitHub Feature Request 时使用。用户只说“提交问题”“提交反馈”“上报 bug”“这是个 bug”或描述功能建议但未点名 GitHub 时不得触发，必须改用 cherry-studio-feedback 并默认提交飞书。.