Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

verify-and-stop — Claude Code skill: what it does, how to install

Proves existing work meets acceptance criteria without expanding scope. Useful for validation tasks and last-mile checks.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add JuliusBrussee/caveman --skill verify-and-stop -a claude-code
Open on GitHub

What verify-and-stop does

The skill translates acceptance conditions into the smallest sufficient proof set. It runs focused checks before broader gates and reuses valid results when the repository state matches. The skill requires reporting pass, fail, unavailable, and blocked states explicitly.

The agent does not edit product code unless the verification prompt asks for fixes. Adding cleanups or extra tests after criteria pass is forbidden. Work halts as soon as acceptance proof is collected. The output lists only commands and unresolved risks.

Install it if your assistant tends to write unnecessary code instead of running tests and stopping.

What it helps with

  • verify acceptance criteria without editing codebase
  • prevent cleanup and scope creep after tests pass
  • run focused verification steps before heavy test gates
  • document run commands and unresolved risks

Example prompts for the agent

  • Verify acceptance conditions for this branch and stop without making changes
  • Run completion checks for the task and report command results

How to install verify-and-stop

1Skills CLI (Vercel)

npx skills add JuliusBrussee/caveman --skill verify-and-stop -a claude-code

2Manually: put the files in place

~/.claude/skills/verify-and-stop/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/verify-and-stop/

From the same set22

The whole set →
caveman JuliusBrussee Cuts filler and polite greetings from agent responses while keeping technical facts and code exact. Stays active until turned off. Claude Code CX Codex Cursor +1 591,500installs caveman-commit JuliusBrussee Generates terse Conventional Commits messages focused strictly on intent. Ideal for keeping git history clean without boilerplate or AI signatures. Claude Code CX Codex Cursor +1 414,700installs caveman-review JuliusBrussee Generates terse, single-line code review comments with exact line numbers, problems, and fixes. Eliminates conversational filler in pull request reviews. Claude Code CX Codex Cursor +1 410,700installs caveman-compress JuliusBrussee Rewrites CLAUDE.md and todo files into terse caveman-speak so the model reads fewer input tokens. The source gets overwritten; a readable backup stays out of tree. Claude Code CX Codex Cursor +1 410,300installs caveman-help JuliusBrussee A quick reference for Caveman modes and commands in Claude Code and other supported hosts. Use it when you need to control response style or find related skills. Claude Code CX Codex Cursor +1 401,800installs cavecrew JuliusBrussee cavecrew delegates code searches, small edits, and diff reviews to three subagents. Use it when keeping the main agent's context lean matters. Claude Code CX Codex Cursor +1 357,900installs caveman-stats JuliusBrussee Displays recorded output and cache-read tokens for Claude Code sessions or points to host native usage stats. Useful for tracking raw token consumption. Claude Code CX Codex Cursor +1 356,700installs caveman-explore JuliusBrussee A read-only skill locates relevant files and line ranges in a repository. Use it for cold-start orientation or broad searches. Claude Code CX Codex Cursor +1 106,500installs

Similar

ponytail-audit DietrichGebert It audits a repository and ranks bugs, risks, and redundant code in a one-shot report. Use it when you need a review without code changes. Claude Code CX Codex Cursor +1 44,800installs code-review-and-quality addyosmani Five review axes and a limit on diff size, so an agent checks a change before merge instead of after. Claude Code CX Codex Cursor +1 72,500installs improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. Claude Code 1,163,035installs design-taste-frontend Leonxlnx This skill directs the design of public pages and work screens, then checks the result in a browser through screenshots. Use it when an interface feels generic or unfinished. Claude Code CX Codex Cursor +1 673,100installs tdd Matt Pocock Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. Claude Code 1,141,062installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs agent-browser vercel-labs A CLI skill for browser control: it opens pages, fills forms, clicks buttons, and tests web apps. Use it when an agent needs to act inside a website. Claude Code CX Codex Cursor +1 1,200,000installs prototype Matt Pocock Creates throwaway prototypes for checking state logic or exploring UI before committing the decision to the main codebase. Claude Code 986,201installs

Questions about verify-and-stop

How to install verify-and-stop in Claude Code?

Run npx skills add JuliusBrussee/caveman --skill verify-and-stop -a claude-code in your terminal. You can also place the file at ~/.claude/skills/verify-and-stop/SKILL.md.

What does verify-and-stop do?

It runs the minimal proof set to verify acceptance conditions and stops immediately. It prevents agents from refactoring or adding unrelated tests after checks pass.

Does verify-and-stop modify project files?

No. It explicitly forbids editing product code unless you requested fixes in the prompt.

Source text

SKILL.md · Apache-2.0 
---
name: verify-and-stop
description: Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.
---

# Verify and stop

Translate acceptance conditions into smallest sufficient proof set.

- Reuse still-current results with matching repository state.
- Run focused checks before wider gates.
- Distinguish pass, fail, unavailable, and blocked exactly.
- Do not edit product code unless verification request includes fixes.
- Do not add polish, cleanup, or unrelated tests after criteria pass.

Stop immediately when acceptance proof is complete. Report commands, results, and unresolved risk only.

© JuliusBrussee · Apache-2.0 · JuliusBrussee/caveman

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor