超压缩通信模式。通过去掉废话、冠词和客套语,在保持完整技术准确性的同时削减约 75% token 用量. An agent skill from ProgrammerAnthony/Expert-Coding-Harness.

MITAuto-check passed

Install Caveman

skills CLI
$ npx skills add ProgrammerAnthony/Expert-Coding-Harness --skill caveman -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ProgrammerAnthony/Expert-Coding-Harness caveman --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ProgrammerAnthony/Expert-Coding-Harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/caveman .claude/skills/caveman && rm -rf skills-src

Use ~/.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/

Facts

Skill name
caveman
GitHub stars
235
Token cost
~217 tokens
SKILL.md length
45 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

超压缩通信模式。通过去掉废话、冠词和客套语,在保持完整技术准确性的同时削减约 75% token 用量. An agent skill from ProgrammerAnthony/Expert-Coding-Harness.

  • SKILL.md covers 持久性, 规则 and 自动清晰例外
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Caveman is an agent skill from ProgrammerAnthony/Expert-Coding-Harness. 超压缩通信模式。通过去掉废话、冠词和客套语,在保持完整技术准确性的同时削减约 75% token 用量。 当用户说"caveman 模式"、"简洁模式"、"少废话"、"省 token"、"简短点"或调用 /caveman 时触发。

Its SKILL.md is about 220 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: 生产级 AI Agent 技能集,辅助AI Harness应用于企业开发,覆盖代码审查、代码安全审计、TDD、需求工程、实施计划与子代理编排、架构设计、调试、前端开发与技能创建全流程。 The licence is MIT.

Example prompts

  • “caveman 模式”
  • “省 token”
  • “/caveman”

What it can do on your machine

Read from SKILL.md and the folder at commit ab0b827. 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

Caveman loads about 217 tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 45 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~217

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 ProgrammerAnthony/Expert-Coding-Harness at commit ab0b827, republished under its MIT licence (© ProgrammerAnthony). 45 words, ~217 tokens.

Download SKILL.mdSave it as .claude/skills/caveman/SKILL.md (or your agent's skills folder).
name
caveman
description
超压缩通信模式。通过去掉废话、冠词和客套语,在保持完整技术准确性的同时削减约 75% token 用量。 当用户说"caveman 模式"、"简洁模式"、"少废话"、"省 token"、"简短点"或调用 /caveman 时触发。

用极简语言回答,像聪明穴居人。所有技术内容保留。只有废话死掉。

持久性

一旦触发,每个回复都保持激活。多轮后不自动恢复。不确定时仍保持激活。只有用户说"stop caveman"或"正常模式"才关闭。

规则

删除:冠词(a/an/the)、废话(just/really/basically/actually/simply)、客套(sure/certainly/of course/happy to)、犹豫措辞。碎片句可以。短同义词(big 不用 extensive,fix 不用"implement a solution for")。缩写常见术语(DB/auth/config/req/res/fn/impl)。去掉连词。用箭头表因果关系(X → Y)。一个词够用就一个词。

技术术语保持原样。代码块不变。报错原样引用。

模式:[thing] [action] [reason]. [next step].

不好:"好的!很高兴帮你处理这个问题。你遇到的问题很可能是因为……"
好:"auth 中间件有 bug。token 过期检查用了 < 不是 <=。修法:"

自动清晰例外

临时退出 caveman 模式处理:安全警告、不可逆操作确认、多步骤序列(碎片顺序可能产生歧义)、用户要求澄清或重复提问。处理完恢复 caveman 模式。

示例——破坏性操作:

警告: 此操作将永久删除 users 表的所有行,无法撤销。

sql
DROP TABLE users;

caveman 恢复。先确认有备份。

© ProgrammerAnthony, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/caveman of ProgrammerAnthony/Expert-Coding-Harness.

Open the folder on GitHubat commit ab0b827

Compare with similar skills

Caveman 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.

Caveman compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Caveman this skillProgrammerAnthony/Expert-Coding-Harness235—~217Automated safety check: PassMIT
Caveman ModeJuliusBrussee/caveman110k—~1kAutomated safety check: PassApache-2.0
Caveman Experiment ManagerJuliusBrussee/caveman110k1 repos~975Automated safety check: PassApache-2.0
Caveman Optimization EvaluatorJuliusBrussee/caveman110k1 repos~1.2kAutomated safety check: PassApache-2.0
Caveman Gateway SetupJuliusBrussee/caveman110k1 repos~2.6kAutomated safety check: WarnApache-2.0
Caveman Workflow LabelerJuliusBrussee/caveman110k1 repos~1.3kAutomated safety check: PassApache-2.0

Similar skills

  • Caveman Mode

    JuliusBrussee/caveman

    Switches the agent to a terse reply style that gives the answer first, drops filler, and keeps every technical fact, command and number exact.

    110k GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • 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.

    110k GitHub starsUsed in 1 repo~975 tokens
    AI & LLM EngineeringAuto-check passed
  • 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.

    110k GitHub starsUsed in 1 repo~1.2k tokens
    AI & LLM EngineeringAuto-check passed
  • 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.

    110k GitHub starsUsed in 1 repo~2.6k tokens
    DevOps & CloudAuto-check: warnings
  • Caveman 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.

    110k GitHub starsUsed in 1 repo~1.3k tokens
    AI & LLM EngineeringAuto-check passed
  • Caveman Learn Token Fixes

    JuliusBrussee/caveman

    Acts on a Caveman learn report: reviews ranked token sinks, applies cost-lowering edits one at a time with your consent, and reports what each fix returned.

    110k GitHub stars~2.8k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from ProgrammerAnthony/Expert-Coding-Harness

All 23 skills in this repo
  • Architecture Advisor

    ProgrammerAnthony/Expert-Coding-Harness

    A skill your agent uses when 用户需要设计新系统架构、评审或优化已有系统架构、选择技术方案时。触发场景:架构分析、架构设计、系统设计、architecture、架构优化、系统架构、架构评审、架构咨询、技术方案、技术设计、如何组织代码结构、模块划分、服务拆分、数据库选型、微服务设计。

    235 GitHub stars~673 tokensUpdated 4 mo ago
    Auto-check passed
  • Code Review Expert

    ProgrammerAnthony/Expert-Coding-Harness

    A skill your agent uses when 用户要求审查代码、评估代码质量、提交 PR 前检查、发现代码有潜在问题时。触发场景:代码审查、code review、审查代码、review、检查代码、代码检查、代码质量、代码评审、这段代码有问题吗、帮我看看代码、合并前检查。

    235 GitHub stars~806 tokensUpdated 4 mo ago
    Auto-check passed
  • Code Security Audit

    ProgrammerAnthony/Expert-Coding-Harness

    A skill your agent uses when 用户需要对代码进行安全审计、发现安全漏洞、上线前安全评估、检查代码是否存在安全风险时。触发场景:代码安全审计、安全审计、白盒审计、安全扫描、漏洞检测、漏洞挖掘、SQL注入、命令注入、XSS、SSRF、反序列化、认证绕过、越权、代码安全检查、security audit、code…

    235 GitHub stars~1.6k tokensUpdated 4 mo ago
    Auto-check passed
  • Debug Expert

    ProgrammerAnthony/Expert-Coding-Harness

    A skill your agent uses when 程序出现错误、异常、崩溃,或行为与预期不符,或测试失败,或无法定位问题根因时。触发场景:调试、debug、报错、错误、异常、bug、问题排查、故障排查、不工作、崩溃、无法运行、出错了、为什么不生效、运行报错、跑不起来、程序挂了。

    235 GitHub stars~986 tokensUpdated 4 mo ago
    Auto-check passed
  • Frontend Code Review

    ProgrammerAnthony/Expert-Coding-Harness

    A skill your agent uses when 用户需要审查前端代码(React/Vue/Next.js/TypeScript/Tailwind等)、检查代码质量、性能问题、可维护性、安全漏洞、最佳实践落地时。触发场景:前端代码评审、前端代码优化、React/Vue代码检查、TypeScript代码审查、前端性能优化、前端安全审计、前端代码规范检查。

    235 GitHub stars~614 tokensUpdated 4 mo ago
    Auto-check passed
  • Frontend Performance Optimization

    ProgrammerAnthony/Expert-Coding-Harness

    A skill your agent uses when 用户需要优化前端性能、提升页面加载速度、减少白屏时间、优化交互流畅度、进行性能排查时。触发场景:前端性能优化、页面加载慢、白屏时间长、卡顿、LCP/FID/CLS指标优化、前端性能分析、打包体积优化。

    235 GitHub stars~701 tokensUpdated 4 mo ago
    Auto-check passed

Questions about Caveman

What does Caveman do?

超压缩通信模式。通过去掉废话、冠词和客套语,在保持完整技术准确性的同时削减约 75% token 用量. An agent skill from ProgrammerAnthony/Expert-Coding-Harness. Caveman is an agent skill from ProgrammerAnthony/Expert-Coding-Harness.

How do I install Caveman in Claude Code?

Run `npx skills add ProgrammerAnthony/Expert-Coding-Harness --skill caveman -a claude-code`. Or copy the skill folder (skills/caveman in ProgrammerAnthony/Expert-Coding-Harness) into .claude/skills/caveman in your project. Claude Code loads it when a task matches its description.

How do I install Caveman in Codex?

Run `npx skills add ProgrammerAnthony/Expert-Coding-Harness --skill caveman -a codex`. Or copy the skill folder (skills/caveman in ProgrammerAnthony/Expert-Coding-Harness) into .agents/skills/caveman in your project. Codex loads it when a task matches its description.

Can I use Caveman 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 ProgrammerAnthony/Expert-Coding-Harness --skill caveman -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/caveman, .gemini/skills/caveman, .github/skills/caveman and .opencode/skills/caveman in your project.

What does Caveman need to run?

SKILL.md names no scripts, command-line tools or credentials: Caveman is instructions for the agent only.

Does Caveman 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 Caveman 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 Caveman use?

Caveman is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Caveman use?

About 217 tokens (SKILL.md is roughly 868 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 Caveman?

Skills that share tags, products or a category with Caveman: Caveman Mode (JuliusBrussee/caveman, 110k stars), Caveman Experiment Manager (JuliusBrussee/caveman, 110k stars), Caveman Optimization Evaluator (JuliusBrussee/caveman, 110k stars) and Caveman Gateway Setup (JuliusBrussee/caveman, 110k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Caveman?

ProgrammerAnthony (a GitHub user) maintains it in ProgrammerAnthony/Expert-Coding-Harness, which has 235 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on May 11, 2026.

Source: ProgrammerAnthony/Expert-Coding-Harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.