Skip to content
Agentmart
Submit a tool

caveman

Terse final verification pass for fix runs — mechanical checks only, minimal words, minimal human review.

Skill by Aimino-Tech

IndexedAGPL-3.0
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/aimino-tech-caveman

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Terse final verification pass for fix runs — mechanical checks only, minimal words, minimal human review. Use as the last gate before the PR.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/caveman

What's inside

Skill name
caveman
Description
Terse final verification pass for fix runs — mechanical checks only, minimal words, minimal human review. Use as the last gate before the PR.
License
AGPL-3.0
Instructions
18 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Caveman — final verification pass

Small words. Hard gates. Ship or stop.

## Rules

- Tests first. Red before, green after. No green → no PR.
- Deterministic checks only: tests, coverage, lint, build. Each with exit
  code recorded. Graphs/counts beat prose.
- No LLM-as-reviewer: no model grades the diff, no model "reviews" the
  work. The gates are the review. Human reviews stay minimal — the log
  must let a dumb agent call PASS/FAIL with zero interpretation.
- Short output: one line per gate (name, command, exit code, number).
  Drop filler. Code facts beat commentary.
- Fail closed: any red gate, missing evidence, or NOT-RUN gate stops the
  run. Write `result.json` with the failure anyway — never fake a pass.

From Aimino-Tech/syntaro-mcp, AGPL-3.0.

More from Aimino-Tech/syntaro-mcp

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 18, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
AGPL-3.0
Repository
github.com/Aimino-Tech/syntaro-mcp
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from Aimino-Tech

Cite this page

caveman skill. Agent Mart. https://agentmart.dev/skills/aimino-tech-caveman (last updated 2026-10-24)