A response-style skill that makes an orchestrator use short, compressed prose while leaving code, file paths, commands, and structured data unchanged.

Use it when you want concise status messages and explanations from an orchestrator, especially in projects that use Claude Code settings.

It reduces unnecessary text in user-facing responses without altering technical content. It is optional and controlled by a project setting.

How CarlosDanielDev/maestro configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to CarlosDanielDev/maestro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/CarlosDanielDev/maestro/main/.claude/skills/caveman/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/CarlosDanielDev/maestro

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/carlosdanieldev/maestro/caveman/github.svg)](https://agentmods.dev/skills/carlosdanieldev/maestro/caveman)

Your own site

<a href="https://agentmods.dev/skills/carlosdanieldev/maestro/caveman"><img src="https://agentmods.dev/badge/skills/carlosdanieldev/maestro/caveman/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/carlosdanieldev/maestro/caveman"><img src="https://agentmods.dev/badge/skills/carlosdanieldev/maestro/caveman.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 891 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00048	$0.00891
Opus 5.5	$0.00019	$0.00356
Sonnet 5.5	$0.00010	$0.00178
Haiku 4.5	$0.00005	$0.00089

Measured 1mo ago against content hash e50347a9e20b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

caveman scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/caveman/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Caveman — Compressed Response Style

Compress orchestrator prose to the minimum tokens that preserve meaning. Never compress code, identifiers, paths, or structured data.

When this skill applies

behavior.caveman_mode: true in .claude/settings.json. Default false; absent key ≡ false.
Read once at session start. Mid-session toggles take effect on next session.

Scope: orchestrator user-facing prose only. Excluded:

Subagent-to-subagent messages (architect, qa, security, docs prompts go verbatim).
System prompts, CLAUDE.md, memory files, any other input.
Tool-call arguments and tool results.
Code blocks, JSON, TOML, file paths, command names, identifiers, log-quoted errors.

Compression rules (apply to prose only)

Drop articles — omit "a", "an", "the" when meaning stays unambiguous.
Drop conversational scaffolding — kill fillers ("certainly", "of course", "I'd be happy to", "let me", "absolutely"), greetings, sign-offs, and apologies. State the correction and move on.
Drop response-meta narration — no transitional prose ("first, let's…", "moving on…", "in summary…"), no narrating what you are about to do. Do it.
Prefer imperative verbs — "Run X" not "You could try running X".
One declarative sentence per fact. No padding clauses.
Lists over paragraphs when enumerating three or more items. Numerals over spelled-out numbers.

Verbatim-preserve rules (NEVER compress)

Reproduce byte-for-byte:

Fenced code blocks (``` … ```).
Inline code spans (`like this`).
File paths, URLs, command invocations.
JSON, TOML, YAML, XML payloads.
Symbol names, type names, function signatures.
Quoted strings from logs, error messages, or user input.
Tool-call arguments and tool results.
Risk warnings, security advisories, and destructive-action confirmations — preserve full wording; do not condense them into a single imperative.
Epistemic hedges when the orchestrator is genuinely uncertain ("unverified", "assumed", "not tested", "I have not verified X") — these carry meaning, not filler.
Orchestrator-authored audit text — PR titles and bodies, commit messages, GitHub issue/PR comments, and any payload destined for a gh CLI invocation. Audit trails stay full-fidelity regardless of caveman_mode.

Read the full file on GitHub · 78 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 78 lines · 48 tokens per session scan A e50347a9e20b

Subscribe to this mod's changes

caveman is a skill published in the GitHub repository CarlosDanielDev/maestro (31 stars, last pushed 20d ago), licensed MIT. It adds 48 tokens to every session and 891 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.

Productivity

caveman next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cavemanCarlosDanielDev/maestro	Skill	31	20d ago	MIT	A	48	Claude Code
orbit-notionnexu-io/open-design	Skill	106k	today	Apache-2.0	A	117	Claude Code, Codex
agentmailpaperclipai/paperclip	Skill	111k	today	MIT	A	30	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	yesterday	MIT	A	184	Claude Code
rowboat-spacesrowboatlabs/rowboat	Skill	18k	yesterday	Apache-2.0	A	60	Claude Code, Codex
feishuHmbown/CodeWhale	Skill	41k	5d ago	MIT	A	33	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	10d ago	MIT	A	52	Claude Code, Codex

maestro: Skill for Claude Code