菜单
Install Caveman as a Claude Code style skill when coding agents need terse, technically accurate responses that reduce output-token waste.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use Vocode to compose transcription, LLM, speech synthesis, and telephony components into reviewable real-time voice-agent workflows.
Use Claude Legal Skill to guide an agent through contract risk review, CUAD-style clause checks, market benchmarks, and lawyer-ready redline suggestions.
Use SWE-ReX when a coding agent needs a consistent runtime interface for local, containerized, or remote shell sessions with command output, exit codes, interactive tools, and parallel execution.
Use Text Extract API when an agent needs to turn PDFs, Office files, or images into Markdown or structured JSON with local OCR, optional Ollama models, PII removal, and queued batch processing.
Route model calls through Helicone, inspect costs, latency, traces, prompts, and evaluations, then review changes before they ship.
Launch an OpenAI-compatible OpenLLM server for a chosen open model, point an agent runtime at it, and compare behavior before production use.
| name | Cut coding-agent response tokens with Caveman mode |
| slug | cut-coding-agent-response-tokens-with-caveman-mode |
| description | Install Caveman as a Claude Code style skill when coding agents need terse, technically accurate responses that reduce output-token waste. |
| github_stars | 78400 |
| verification | listed |
| source | https://github.com/JuliusBrussee/caveman |
| author | Julius Brussee |
| publisher_type | individual |
| category | Developer Tools |
| framework | Claude Code |
| tool_ecosystem | {"github_repo":"JuliusBrussee/caveman","github_stars":78400} |
Install Caveman as a Claude Code style skill when coding agents need terse, technically accurate responses that reduce output-token waste.
Claude Code or compatible coding-agent skill/plugin environment
No source-backed install or usage instructions could be extracted automatically. Review the upstream project before running this skill in a sensitive workflow.
