Talk Normal
hexiecs/talk-normal
Installs an always-on set of rules into your agent's workspace config that cuts filler, hedging and padded closings from its replies.
Cuts the agent's replies down to bare fragments for the whole session, one word where one will do and no repeated facts, while code and error strings stay exact.
Install Ultracave Maximum Compression Mode
$ npx skills add JuliusBrussee/caveman --skill ultracave -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install JuliusBrussee/caveman ultracave --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/ultracave .claude/skills/ultracave && 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 "ultracave" agent skill from https://github.com/JuliusBrussee/caveman/tree/main/skills/ultracave into .claude/skills/ultracave/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ultracave", 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/ultracaveType 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 ultracave -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install JuliusBrussee/caveman ultracave --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/ultracave .agents/skills/ultracave && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ultracave" agent skill from https://github.com/JuliusBrussee/caveman/tree/main/skills/ultracave into .agents/skills/ultracave/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ultracave", 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 ultracave -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install JuliusBrussee/caveman ultracave --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/ultracave .cursor/skills/ultracave && 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 "ultracave" agent skill from https://github.com/JuliusBrussee/caveman/tree/main/skills/ultracave into .cursor/skills/ultracave/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ultracave", 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/ultracave--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 ultracave -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install JuliusBrussee/caveman ultracave --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/ultracave .gemini/skills/ultracave && 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 "ultracave" agent skill from https://github.com/JuliusBrussee/caveman/tree/main/skills/ultracave into .gemini/skills/ultracave/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ultracave", 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 ultracaveInstalls 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 ultracave -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/ultracave .github/skills/ultracave && 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 "ultracave" agent skill from https://github.com/JuliusBrussee/caveman/tree/main/skills/ultracave into .github/skills/ultracave/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ultracave", 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 ultracave -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 ultracave --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/ultracave .opencode/skills/ultracave && 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 "ultracave" agent skill from https://github.com/JuliusBrussee/caveman/tree/main/skills/ultracave into .opencode/skills/ultracave/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ultracave", 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
ultracave- GitHub stars
- 111k
- Used in
- 1 other repo
- Token cost
- ~629 tokens
- SKILL.md length
- 330 words
- Files
- 2
- Skills in repo
- 18
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Cuts the agent's replies down to bare fragments for the whole session, one word where one will do and no repeated facts, while code and error strings stay exact.
- Works in 6 steps: Fragments → One word when one word is enough → Each fact once → …
- You want the shortest possible agent replies during a long working session
- SKILL.md covers Persistence, Floor, Rules and When to break the rules, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Ultracave is the most compressed level of the caveman reply style, switched on with /ultracave or /caveman ultra. Replies lose articles, linking verbs and connectives wherever the order stays clear, a single word replaces a full sentence when it is enough, and no fact is stated twice or summed up after a list. The mode persists until you say stop caveman or normal mode.
Some things are never cut: code, commands, paths, API names and error strings stay verbatim, along with negations, numbers, units and the language you write in. The agent should not invent abbreviations or use arrows. It goes back to plain prose for security warnings, steps that cannot be undone and need confirmation, fragments open to two readings, or a confused user, and for anything written outside chat, such as commits, docs, issues or code comments.
When your agent uses it
- You want the shortest possible agent replies during a long working session
- Skimming status answers where only the key facts matter
Example prompts
- “/ultracave Can this migration run twice safely?”
- “/caveman ultra What is wrong with this null check?”
Workflow steps
6 steps, taken from the step headings in SKILL.md.
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
Ultracave Maximum Compression Mode loads about 629 tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 330 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). 330 words, ~629 tokens.
Download SKILL.mdSave it as
.claude/skills/ultracave/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- ultracave
- description
- Caveman at maximum compression: fragments, one word when one word is enough, each fact once. Invoke only with /ultracave or /caveman ultra. Stays on until "stop caveman" or "normal mode".
- disable-model-invocation
- true
ultracave
Respond terse like smart caveman. All technical substance stay. Only fluff die. Then cut again.
Ultracave is caveman with the grammar stripped. Payload only.
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: code, commands, paths, API names, error strings (verbatim). not/never/no/only/except. Numbers and units. The user's language. One term per thing. No invented abbreviations, no arrows. Existing comments in files you edit: never delete or shorten unless asked.
Rules
1. Fragments
Drop articles, copulas, connectives when order stays clear.
Bad: "The component re-renders because an inline object prop creates a new reference each render."
Good: "Inline object prop, new ref, re-render. useMemo."
2. One word when one word is enough
Bad: "Yes, that should work, though you'll want a null check first." Good: "Yes. Null check first."
3. Each fact once
No restating, no summary after a list. Code change: changed lines plus context, not the whole file.
Good: "Pool reuses open DB connections. No per-request handshake."
4. Cut conjunctions only when order survives
Bad: "Migrate table drop column backup first." Good: "Back up first. Then migrate: drops column."
5. Tool runs
One line in, one line out. Nothing between calls unless direction changes, confirmation needed, or a security or irreversible step is ahead.
6. Never perform
No prefix, no announcement, no mangled verbs for flavor. Fragment not shorter than the sentence? Use the sentence.
When to break the rules
Plain prose, then resume: security warning. Irreversible action, confirm first. Any fragment 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
Two readings? Full sentence. Negations present? Payload verbatim? Flavor word? Cut.
© 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/ultracave of JuliusBrussee/caveman.
- SKILL.md
- README.md
Open the folder on GitHubat commit 2e08b91
Used in 1 other repository
We found 2 copies 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
Ultracave Maximum Compression Mode 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 |
|---|---|---|---|---|---|---|
| Ultracave Maximum Compression Mode this skillJuliusBrussee/caveman | 111k | 1 repos | ~629 | Automated safety check: Pass | Apache-2.0 | |
| Talk Normalhexiecs/talk-normal | 1.9k | — | ~784 | Automated safety check: Pass | MIT | |
| Talk Normalhexiecs/talk-normal | 1.9k | — | ~931 | Automated safety check: Pass | MIT | |
| Writing Quotationmathbullet/skills | 173 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 38k | 7 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Workflow Schema Tuningbreaking-brake/cc-wf-studio | 5.4k | — | ~1.3k | Automated safety check: Pass | Custom licence |
Similar skills
Talk Normal
hexiecs/talk-normal
Installs a set of rules into AGENTS.md that strips filler, hedging and padded closings from your agent's replies, in English and Chinese.
Writing Quotation
mathbullet/skills
Formatting rules for quoting external sources (papers, articles, web pages, prompt templates) inside a Markdown document.
- Official
Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
Workflow Schema Tuning
breaking-brake/cc-wf-studio
Guides edits to cc-wf-studio's workflow schema so AI agents generate better workflows, treating schema text as prompt engineering rather than validation.
Agentforce Generate
SalesforceAIResearch/agentforce-adlc
Build, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script.
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 Ultracave Maximum Compression Mode
What does Ultracave Maximum Compression Mode do?
Cuts the agent's replies down to bare fragments for the whole session, one word where one will do and no repeated facts, while code and error strings stay exact. Ultracave is the most compressed level of the caveman reply style, switched on with /ultracave or /caveman ultra. Replies lose articles, linking verbs and connectives wherever the order stays clear, a single word replaces a full sentence when it is enough, and no fact is stated twice or summed up after a list.
When should I use Ultracave Maximum Compression Mode?
Ultracave Maximum Compression Mode fits situations like: you want the shortest possible agent replies during a long working session; skimming status answers where only the key facts matter.
How do I install Ultracave Maximum Compression Mode in Claude Code?
Run `npx skills add JuliusBrussee/caveman --skill ultracave -a claude-code`. Or copy the skill folder (skills/ultracave in JuliusBrussee/caveman) into .claude/skills/ultracave in your project. Claude Code loads it when a task matches its description.
How do I install Ultracave Maximum Compression Mode in Codex?
Run `npx skills add JuliusBrussee/caveman --skill ultracave -a codex`. Or copy the skill folder (skills/ultracave in JuliusBrussee/caveman) into .agents/skills/ultracave in your project. Codex loads it when a task matches its description.
Can I use Ultracave Maximum Compression Mode 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 ultracave -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ultracave, .gemini/skills/ultracave, .github/skills/ultracave and .opencode/skills/ultracave in your project.
What does Ultracave Maximum Compression Mode need to run?
SKILL.md names no scripts, command-line tools or credentials: Ultracave Maximum Compression Mode is instructions for the agent only.
Does Ultracave Maximum Compression Mode 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 Ultracave Maximum Compression Mode 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 Ultracave Maximum Compression Mode use?
Ultracave Maximum Compression Mode 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 Ultracave Maximum Compression Mode use?
About 629 tokens (SKILL.md is roughly 2.5k 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 Ultracave Maximum Compression Mode?
Skills that share tags, products or a category with Ultracave Maximum Compression Mode: Talk Normal (hexiecs/talk-normal, 1.9k stars), Talk Normal (hexiecs/talk-normal, 1.9k stars), Writing Quotation (mathbullet/skills, 173 stars) and Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Ultracave Maximum Compression Mode?
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.