Verification Before Completion
jnMetaCode/superpowers-zh
Chinese-language rule that bars an agent from claiming work is done, fixed or passing until it has run a verification command and read the output.
“Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.”
Install Verify and Stop
$ npx skills add JuliusBrussee/caveman --skill verify-and-stop -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install JuliusBrussee/caveman verify-and-stop --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/JuliusBrussee/caveman.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/verify-and-stop .claude/skills/verify-and-stop && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "verify-and-stop" agent skill from https://github.com/JuliusBrussee/caveman/tree/main/skills/verify-and-stop into .claude/skills/verify-and-stop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-and-stop", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/JuliusBrussee/caveman/tree/main/skills/verify-and-stopType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add JuliusBrussee/caveman --skill verify-and-stop -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install JuliusBrussee/caveman verify-and-stop --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JuliusBrussee/caveman.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/verify-and-stop .agents/skills/verify-and-stop && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "verify-and-stop" agent skill from https://github.com/JuliusBrussee/caveman/tree/main/skills/verify-and-stop into .agents/skills/verify-and-stop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-and-stop", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add JuliusBrussee/caveman --skill verify-and-stop -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install JuliusBrussee/caveman verify-and-stop --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JuliusBrussee/caveman.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/verify-and-stop .cursor/skills/verify-and-stop && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "verify-and-stop" agent skill from https://github.com/JuliusBrussee/caveman/tree/main/skills/verify-and-stop into .cursor/skills/verify-and-stop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-and-stop", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/JuliusBrussee/caveman.git --path skills/verify-and-stop--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add JuliusBrussee/caveman --skill verify-and-stop -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install JuliusBrussee/caveman verify-and-stop --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JuliusBrussee/caveman.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/verify-and-stop .gemini/skills/verify-and-stop && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "verify-and-stop" agent skill from https://github.com/JuliusBrussee/caveman/tree/main/skills/verify-and-stop into .gemini/skills/verify-and-stop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-and-stop", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install JuliusBrussee/caveman verify-and-stopInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add JuliusBrussee/caveman --skill verify-and-stop -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/JuliusBrussee/caveman.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/verify-and-stop .github/skills/verify-and-stop && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "verify-and-stop" agent skill from https://github.com/JuliusBrussee/caveman/tree/main/skills/verify-and-stop into .github/skills/verify-and-stop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-and-stop", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add JuliusBrussee/caveman --skill verify-and-stop -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install JuliusBrussee/caveman verify-and-stop --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JuliusBrussee/caveman.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/verify-and-stop .opencode/skills/verify-and-stop && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "verify-and-stop" agent skill from https://github.com/JuliusBrussee/caveman/tree/main/skills/verify-and-stop into .opencode/skills/verify-and-stop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-and-stop", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
verify-and-stop- GitHub stars
- 111k
- Used in
- 1 other repo
- Token cost
- ~176 tokens
- SKILL.md length
- 66 words
- Files
- 2
- Skills in repo
- 18
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
About this skill
Verify and Stop is a skill in JuliusBrussee/caveman (111k stars). Its SKILL.md is about 176 tokens, with 1 other file in the folder, and copies of it appear in 1 other owners' repositories. Licence: Apache-2.0.
What it can do on your machine
Read from SKILL.md and the folder at commit 2e08b91. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Verify and Stop loads about 176 tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 66 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from JuliusBrussee/caveman at commit 2e08b91, republished under its Apache-2.0 licence (© JuliusBrussee). 66 words, ~176 tokens.
Download SKILL.mdSave it as
.claude/skills/verify-and-stop/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- 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. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in skills/verify-and-stop of JuliusBrussee/caveman.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 2e08b91
Used in 1 other repository
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in JuliusBrussee/caveman, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Verify and Stop next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Verify and Stop this skillJuliusBrussee/caveman | 111k | 1 repos | ~176 | Automated safety check: Pass | Apache-2.0 | |
| Verification Before CompletionjnMetaCode/superpowers-zh | 8.3k | — | ~443 | Automated safety check: Pass | MIT | |
| Iteration Progress Auditprime-radiant-inc/iterative-development | 181 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| QA Verdict JudgeQ00/ouroboros | 6.2k | — | ~2.3k | Automated safety check: Pass | MIT | |
| Verify Before CompletionYeachan-Heo/oh-my-claudecode | 40k | — | ~277 | Automated safety check: Pass | MIT | |
| Nucleus Result Package Builderprotect-my-hair/nucleus-marketplace | 164 | — | ~414 | Automated safety check: Pass | MIT |
Similar skills
Iteration Progress Audit
prime-radiant-inc/iterative-development
Checks the quality of behavior evidence after each iteration in three tiers, using two auditor subagents in parallel to review the same work and find gaps.
QA Verdict Judge
Q00/ouroboros
Gives a fast single-pass quality verdict on any artifact, with a score from 0 to 1, PASS, REVISE or FAIL, and suggestions for what to change.
Verify Before Completion
Yeachan-Heo/oh-my-claudecode
Has the agent prove that a feature, fix or refactor works, using existing tests first, then narrow commands and manual checks, and report only what was actually verified.
Nucleus Result Package Builder
protect-my-hair/nucleus-marketplace
Builds the result.json file for a Nucleus V2 workflow run from its context, gates, blockers and step status, and exits non-zero when the run is blocked.
Procoder Commit Gate
azrtydxb/procoder
Applies Procoder's senior-developer discipline in a repository: run the commit gate, format through the binary and work through specs, plans and todos.
More from JuliusBrussee/caveman
All 18 skills in this repoCaveman Workflow Labeler
JuliusBrussee/caveman
Finds every LLM workflow in a repository, proposes a labeling table and, once you agree, wires labels so Caveman Cloud groups spend per workflow.
Caveman Evidence Review
JuliusBrussee/caveman
Read-only review of Caveman Cloud data to explain where LLM spend goes: cost, score, workflows, traces, latency, errors, routing and verified savings.
Caveman Experiment Manager
JuliusBrussee/caveman
Reads the state and results of Caveman Cloud experiments and reports one recommendation or a block, without changing an experiment's lifecycle itself.
Caveman Optimization Evaluator
JuliusBrussee/caveman
Turns a Caveman report-only optimization observation into one minimal code change and a paired baseline evaluation, after the operator picks which to pursue.
Caveman Gateway Setup
JuliusBrussee/caveman
Routes every LLM call in a repository through the Caveman Cloud gateway in record mode, so requests and costs are measured without changing behavior.
Caveman Help Card
JuliusBrussee/caveman
Quick-reference card for the three caveman skills and their commands. Trigger: /caveman-help or "caveman help".
Related
Categories
Questions about Verify and Stop
How do I install Verify and Stop in Claude Code?
Run `npx skills add JuliusBrussee/caveman --skill verify-and-stop -a claude-code`. Or copy the skill folder (skills/verify-and-stop in JuliusBrussee/caveman) into .claude/skills/verify-and-stop in your project. Claude Code loads it when a task matches its description.
How do I install Verify and Stop in Codex?
Run `npx skills add JuliusBrussee/caveman --skill verify-and-stop -a codex`. Or copy the skill folder (skills/verify-and-stop in JuliusBrussee/caveman) into .agents/skills/verify-and-stop in your project. Codex loads it when a task matches its description.
Can I use Verify and Stop in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JuliusBrussee/caveman --skill verify-and-stop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/verify-and-stop, .gemini/skills/verify-and-stop, .github/skills/verify-and-stop and .opencode/skills/verify-and-stop in your project.
What does Verify and Stop need to run?
SKILL.md names no scripts, command-line tools or credentials: Verify and Stop is instructions for the agent only.
Does Verify and Stop access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Verify and Stop safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Verify and Stop use?
Verify and Stop is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Verify and Stop use?
About 176 tokens (SKILL.md is roughly 704 characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Verify and Stop?
Skills that share tags, products or a category with Verify and Stop: Verification Before Completion (jnMetaCode/superpowers-zh, 8.3k stars), Iteration Progress Audit (prime-radiant-inc/iterative-development, 181 stars), QA Verdict Judge (Q00/ouroboros, 6.2k stars) and Verify Before Completion (Yeachan-Heo/oh-my-claudecode, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Verify and Stop?
JuliusBrussee (a GitHub user) maintains it in JuliusBrussee/caveman, which has 110,815 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 9, 2026.
Source: JuliusBrussee/caveman on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.