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 skills add ash1794/vibe-engineering --skill vibe-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/vibe-scope-guard)<a href="https://agentmods.dev/skills/ash1794/vibe-engineering/vibe-scope-guard"><img src="https://agentmods.dev/badge/skills/ash1794/vibe-engineering/vibe-scope-guard/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/ash1794/vibe-engineering/vibe-scope-guard"><img src="https://agentmods.dev/badge/skills/ash1794/vibe-engineering/vibe-scope-guard.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00048 | $0.00619 |
| Opus 5.5 | $0.00019 | $0.00248 |
| Sonnet 5.5 | $0.00010 | $0.00124 |
| Haiku 4.5 | $0.00005 | $0.00062 |
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 23d 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 — 65 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. Frontier coding models tend to over-build: extra configurability, defensive layers, helpers "for later." Stay 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 the diff is noticeably larger than the request implies
- 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 the extra work is necessary for correctness (a bug in the code path you're changing)
Scope Creep Signals
| Signal | Example | Response |
|---|---|---|
| Unrequested features | "While I'm here, let me add caching" | Was caching requested? |
| Premature abstraction | "Let me create a generic helper for this" | Is there a second caller today? |
| Gold plating | "Comprehensive error messages for every case" | Only at system boundaries |
| Drive-by refactor | "This function could be cleaner" | Not in this change |
| Over-engineering | "Let me make this configurable" | Does anyone need to configure it? |
| Defensive sprawl | Validation and fallbacks for states that can't occur | Trust internal invariants; validate at the boundary |
| Documentation creep | "Docstrings on all these functions" | Only on what you changed |
| Test over-expansion | "Test every possible input" | Test boundaries and behaviors, not permutations |
The Rule
Three similar lines of code are better than a premature abstraction.
Before adding anything not explicitly requested:
- Was it requested? → No →
- Is it required for the requested change to be correct? → No →
- Don't add it. Mention it as a suggestion in the summary if it's worth the user's attention.
Steps
When you detect scope creep:
- Stop — Don't commit the extra work
- Revert it if it's already written
- Note it: "Also noticed: [X]. Not changed; want a follow-up?"
- If the user accepts — do it as a separate, clearly labeled change
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.
- 23d ago First seen · 65 lines · 48 tokens per session scan A 898935793bc1
vibe-scope-guard is a skill published in the GitHub repository ash1794/vibe-engineering (164 stars, last pushed 11d ago), licensed MIT. It adds 48 tokens to every session and 619 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 2026-09-26.
Other skills, from other repositories
contract-testing-flywheel
Generate a structured onboarding backlog — in Jira, GitHub Issues/Projects, Azure DevOps, or as a manual markdown export — that drives a development team from zero to publishing both consumer and provider contract tests. Use when the user invokes /contract-testing-flywheel or asks to "kick off contract testing for a…
cherry-regression-test
Run Cherry Studio critical-path system regression tasks through the repository-owned Playwright E2E workflow. Use for full regression, release acceptance, development-branch system validation, or a named cherry-regression-test task on GitHub-hosted macOS and Windows runners.
agent-notes
Use when deciding whether a Cherry Studio change needs an Agent Note, authoring or reviewing a Spec, recording a durable bug-fix decision, moving a note between proposed/implemented/rejected, or checking supersession and stacked Spec approval.
create-request
Create, update, or scan per-task request tickets for progress tracking. These are date-prefixed non-lifecycle docs under requests/, NOT feature-level requirements (use /req-analyze for those). Use when: tracking task progress, updating completion status, scanning incomplete requests, checking request status dashboard.…
req-analyze
A requirements-analysis tool that breaks a problem into needs, stakeholders, and priorities before a technical solution is chosen.
feature-verify
Feature verification (READ-ONLY, P0-P5). Use when: verifying feature behavior after deployment, validating API responses, diagnosing production issues, post-deploy smoke test. Not for: modifying data (use feature-dev), code review (use codex-review-fast), writing tests (use codex-test-gen), security audit (use…