Compress agent replies into short phrases while preserving technical details, negations, numbers, and exact commands. Use it to reduce repeated explanations and keep chat responses brief until you explicitly turn the mode off.
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".
ultracave removes unnecessary explanation and repetition from agent replies, conveying the main points in short phrases. It preserves code, commands, paths, API names, and error messages exactly as written. Negations, numbers, and units also remain intact. Each piece of information appears once. When explaining code changes, it shows the changed lines with the context needed to understand them.
Use it when you want less text in chat while retaining the technical content. It suits sessions where you want consistently short replies, without long introductions or summaries at the end of answers.
/ultracave or /caveman ultra./caveman status.stop caveman or normal mode.The mode starts only through an explicit command and stays active until you turn it off. It returns to ordinary prose when compressed wording could be ambiguous, when asking you questions, or when giving safety warnings. This style generally does not apply to content saved outside chat, such as code or documents.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.
The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 20, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Respond terse like smart caveman. All technical substance stay. Only fluff die. Then cut again.
Ultracave is caveman with the grammar stripped. Payload only.
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).
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.
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."
Bad: "Yes, that should work, though you'll want a null check first." Good: "Yes. Null check first."
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."
Bad: "Migrate table drop column backup first." Good: "Back up first. Then migrate: drops column."
One line in, one line out. Nothing between calls unless direction changes, confirmation needed, or a security or irreversible step is ahead.
No prefix, no announcement, no mangled verbs for flavor. Fragment not shorter than the sentence? Use the sentence.
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.
Two readings? Full sentence. Negations present? Payload verbatim? Flavor word? Cut.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Delegate code lookup, small edits, and diff reviews to three specialized subagents. Their compact, structured results help conserve the main agent's context, with guidance on when to delegate and when to keep work in the main conversation.
Make agent replies shorter and easier to scan by putting answers first and removing filler. Preserves technical details, exact commands, numbers, and essential conditions while keeping the user's chosen language.
Create short commit messages using Conventional Commits, a format that labels the type of change. Emphasize intent, keep the subject concise, and include explanatory text when breaking changes, security fixes, data migrations, or reversions require context.
Compress memory files and task lists into shorter wording to reduce input tokens. Keeps code and document structure intact, saves a readable backup separately, and sends the text to the configured model provider.
Find LLM workflows in a codebase and label them by the job they perform, so Caveman Cloud can separate spending by workflow. Present a labeling proposal for approval, apply focused code changes, and check an affected execution path.
Review Caveman Cloud spending, latency, errors, and potential improvements using current reports and traces, or individual execution records. Produce findings tied to time windows and trace IDs, while keeping measured costs, estimated opportunities, and verified savings separate.