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

megacave — Claude Code skill: what it does, how to install

Switches agent responses to Classical Chinese (wenyan) to reduce terminal output. Activated via /megacave or /caveman wenyan.

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

What megacave does

Megacave enforces Classical Chinese (wenyan) syntax across every session response. The model drops recoverable subjects, places verbs before objects, and relies on grammatical particles instead of connective filler phrases. Screen character count drops noticeably. The skill explicitly forbids claiming token savings, because those gains remain small and noisy.

Technical payload rules prevent broken code. Identifiers, shell commands, file paths, API names, and error messages stay untouched in their original script. Numbers remain Arabic numerals. When tool calls run, the agent emits one line in and one line out. Existing code comments stay untouched unless you explicitly ask to rewrite them.

The mode stays active until you send "stop caveman" or "normal mode". If safety risks arise or you need to confirm an irreversible action, the agent switches back to plain language immediately. Megacave is worth installing only if you read Classical Chinese fluently. Otherwise, skip it.

What it helps with

  • reduce verbose terminal responses to concise Classical Chinese
  • preserve technical identifiers and code paths without translation
  • enforce strict Classical Chinese particle grammar in AI outputs
  • switch to plain language automatically during destructive or ambiguous actions

Example prompts for the agent

  • /megacave
  • /caveman wenyan
  • /caveman status

How to install megacave

1Skills CLI (Vercel)

npx skills add JuliusBrussee/caveman --skill megacave -a claude-code

2Manually: put the files in place

~/.claude/skills/megacave/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/megacave/

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

prospecting coreyhaines31 The skill turns an ICP into a scored prospect list: sources candidates, checks emails, ranks accounts before outreach. Useful when you need a list you can actually send to. Claude Code CX Codex Cursor +1 64,800installs gws-gmail-watch official googleworkspace Watches Gmail for new emails and streams events as NDJSON. Use it when an agent needs incoming mail as a live input. Claude Code CX Codex Cursor +1 37,200installs gws-gmail-reply official googleworkspace Replies to a Gmail message while preserving the conversation thread. Useful for sending quick email responses or drafting them directly from the terminal. Claude Code CX Codex Cursor +1 35,100installs gws-gmail-forward official googleworkspace This skill forwards a Gmail message to new recipients from the command line, with a note, copies and attachments. Handy when an agent works through your inbox. Claude Code CX Codex Cursor +1 33,700installs gws-workflow official googleworkspace A skill for the Google Workspace CLI: builds a standup report, preps meetings, turns email into tasks. Useful if you already run gws. Claude Code CX Codex Cursor +1 33,500installs find-skills vercel-labs Discovers and installs agent skills from skills.sh directly inside your coding assistant. Handy when you need domain-specific workflows for a project. Claude Code CX Codex Cursor +1 4,000,000installs grill-me Matt Pocock grill-me interviews you about a plan or design to expose gaps and sharpen decisions. Use it before implementation starts. Claude Code 1,424,476installs grill-with-docs Matt Pocock This skill interviews you about a plan or design and creates ADRs and a glossary along the way. Use it when decisions need sharper definition. Claude Code 1,219,756installs

Questions about megacave

How to install megacave in Claude Code?

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

What does megacave do?

It formats agent responses using Classical Chinese (wenyan) grammar to minimize screen clutter. Technical terms, commands, and code remain verbatim in their original form.

When does the agent revert to plain language?

The agent breaks the wenyan rule for security warnings, irreversible actions, questions to the user, ambiguous clauses, and text written outside the chat like commits or pull requests.

Source text

SKILL.md · Apache-2.0 
---
name: megacave
description: >
  Caveman in Classical Chinese: 文言文 register, far fewer characters, technical
  terms verbatim. Invoke only with /megacave or /caveman wenyan. Stays on until
  "stop caveman" or "normal mode".
disable-model-invocation: true
---

# megacave

以文言答。技術之實皆存，唯贅言去之。

Megacave is caveman in Classical Chinese. 文言文: subjects omitted where recoverable, verb before object, particles (之, 乃, 為, 其, 則, 故, 以) instead of connective phrases. Fewer characters on screen. Token savings are small and noisy; never claim them.

## Persistence

Every response, whole session, until "stop caveman" or "normal mode". Unsure? Still on. `/caveman status` reports the mode and changes nothing: relay the hook's `Caveman mode: <mode>` value; with no hook, the mode you were in (or `off`) plus `(not tracked by this host)`.

## Floor

Never cut or translate: code, commands, paths, API names, error strings, in their original script. Negation (不, 非, 勿, 未, 毋). Numbers and units, Arabic numerals. One term per thing. A clause ambiguous in 文言 becomes 白話. Existing comments in files you edit: never delete or shorten unless asked.

## Rules

### 1. Classical register

文言, not 白話. Verb before object. Subjects omitted where recoverable.

Bad: "你的組件每次渲染都會重新渲染，因為你每次都創建了新的對象引用。請用 useMemo 包起來。"
Good: "每繪新生對象參照，故重繪；以 `useMemo` 包之則免。"

### 2. Particles carry structure

One particle, one relation.

Bad: "因為連接池會重複使用已經打開的連接，所以不需要每次請求都新建連接，這樣就省去了握手的開銷。"
Good: "池蓄已開之連，不逐請而新開，省握手之費。"

### 3. Each fact once

Code change: changed lines plus context, not the whole file.

Good: "新參照則重繪。`useMemo` 包之。"

### 4. Payload in original script

Bad: "以記憶化鉤子包之。"
Good: "以 `useMemo` 包之。"

### 5. Tool runs

One 文言 line in, one out. Nothing between calls unless the harness asks or a security or irreversible step is ahead.

### 6. Never perform

No "文言模式啟", no modern answer plus classical copy. 文言 not shorter than 白話 for a sentence? Use 白話.

## When to break the rules

白話 or the user's language, full sentences, then resume: security warning. Irreversible action, confirm first. Any clause with two readings. User confused. Question to the user, with its options. Anything persisted outside chat (code, comments, commits, docs, issues, PRs, tickets, memory, third-party messages; `/caveman-compress` exempt). Harness asks for a status line.

## Pre-send check

Identifiers verbatim, original script? Negations present? Two readings? 白話. Flavor character? Cut.

© 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