ultracave
Caveman at maximum compression: fragments, one word when one word is enough, each fact once.
Skill by JuliusBrussee
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/juliusbrussee-ultracave
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.
About
Use cases: documents, prompt-engineering
Reviews
Write a reviewNo 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/ultracave
What's inside
- Skill 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".
- License
- Apache-2.0
- Instructions
- 56 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# 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.
From JuliusBrussee/caveman, Apache-2.0.
More from JuliusBrussee/caveman
- 0.888score
caveman-compress
JuliusBrussee
Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-learn
JuliusBrussee
Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-manage
JuliusBrussee
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-optimize
JuliusBrussee
Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-evidence-review
JuliusBrussee
Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.882score
cavecrew
JuliusBrussee
When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline…
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.882score
megacave
JuliusBrussee
Caveman in Classical Chinese: 文言文 register, far fewer characters, technical terms verbatim.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.882score
caveman-commit
JuliusBrussee
Write a Conventional Commits message compressed to intent only.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.882score
caveman-review
JuliusBrussee
Compressed code review - one line per finding with location, problem and fix.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.882score
caveman-setup
JuliusBrussee
Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.882score
caveman-explore
JuliusBrussee
Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.882score
caveman-discover
JuliusBrussee
Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket.
SkillAFreshness: A★ 114.8KClaude Code +9
Signals
- Stars
- 114,786
- Forks
- 6,616
- Open issues
- 64
- Last commit (this folder)
- Oct 6, 2026 (21 days ago)
- Last release
- Oct 13, 2026 (13 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/JuliusBrussee/caveman
- Website
- docs.caveman.so/caveman
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from JuliusBrussee
- 0.888score
caveman-compress
JuliusBrussee
Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-evidence-review
JuliusBrussee
Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-optimize
JuliusBrussee
Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-manage
JuliusBrussee
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-learn
JuliusBrussee
Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.882score
cavecrew
JuliusBrussee
When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline…
SkillAFreshness: A★ 114.8KClaude Code +9
Cite this page
ultracave skill. Agent Mart. https://agentmart.dev/skills/juliusbrussee-ultracave (last updated 2026-10-24)