Use when newly discovered work, technical debt, refactors, audits, optimizations, or reviewer suggestions threaten to expand the user-authorized task.
Scanned 9/6/2026
Install to Claude Code
npx -y skills add ihabkhaled/AI-Psychiatry --skill scope-guard --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Scope Guard?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ihabkhaled-scope-guard)More formats (shields.io, HTML) on the badges page.
---
name: scope-guard
description: Use when newly discovered work, technical debt, refactors, audits, optimizations, or reviewer suggestions threaten to expand the user-authorized task.
---
# Scope Guard
## Core principle
Detect, classify, park, and continue; finding work is not authorization to adopt it.
## Procedure
1. State the discovery and its evidence.
2. Classify it as blocker, required, optional, or unrelated.
3. Allow blocker or required work to interrupt only to the minimum needed extent.
4. Record optional or unrelated work with impact and future action.
5. Close the side branch and restore one active item.
6. Escalate to the user only when scope must materially change.
## Required output
Classification, evidence, disposition, and the resumed parent action.
## Limits
WIP 1; optional exploration becomes zero near completion.
## Common mistakes
Do not label all defects required or lose useful discoveries instead of parking them.
## Stop condition
Stop when no unapproved branch is active and the next action serves the locked DoD.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.