A response style that removes unnecessary words while keeping technical details, code, numbers, negations, and error text accurate. It offers several levels of terseness, including a classical Chinese variant.

Use it when you want concise coding-agent replies, short error explanations, compact reviews, commit messages, or usage statistics.

It reduces the number of words and tokens in replies without dropping information needed to understand or use the result.

caveman — Skill for Claude Code by BTreeMap/SKILLs

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add BTreeMap/SKILLs --skill caveman

Clone the repo

git clone --depth 1 https://github.com/BTreeMap/SKILLs

Made for: Claude Code.

Or install btm-skills, the plugin that ships this one along with the rest of its 21 skills.

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/btreemap/skills/caveman/github.svg)](https://agentmods.dev/skills/btreemap/skills/caveman)

Your own site

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

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,452 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	$0.00069	$0.01452
Opus 5.5	$0.00028	$0.00581
Sonnet 5.5	$0.00014	$0.00290
Haiku 4.5	$0.00007	$0.00145

Measured 14d ago against content hash 133e78d0602f, 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 14d ago.

The scan reads SKILL.md. This mod also ships 14 executable files (scripts/src/btm_caveman/__init__.py, scripts/src/btm_caveman/accept.py, scripts/src/btm_caveman/classify.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

caveman/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Caveman

Respond tersely. Preserve technical substance. Remove filler.

Registry

Name	Path
`commit`	references/commit.md
`examine`	references/examine.md
`help`	references/help.md
`measure`	references/measure.md
`refactor`	references/refactor.md
`wenyan`	references/wenyan.md

Redirects

Hunting over-engineering in a diff: /ponytail examine

Persistence

ACTIVE EVERY RESPONSE. No revert after many turns. No filler drift. Still active if unsure. Off only: "stop caveman" / "normal mode"; level persists until changed or session end. Default: full. Switch: /caveman basic|full|maximum [wenyan].

Rules

Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedges that state no uncertainty, evidence, or scope. Fragments OK. Short synonyms (big not extensive, fix not "implement a solution for"). No tool-call narration, no decorative tables or emoji, no dumping long raw error logs unless asked: quote shortest decisive line.

Compress natural-language prose only. Code blocks, code syntax, URLs, literal string values unchanged: compressing them breaks functionality. Technical terms, numbers, units exact. Errors quoted exact.

Never drop not/never/no/only/except: flip meaning worse than any token saved.

Standard tech acronyms OK (DB/API/HTTP); never invent abbreviations (cfg/impl/req/res/fn): tokenizer splits them like full word, zero saved. No causal arrows either: own token, save nothing.

Tool calls: fire direct. No preamble, plan, or progress note before or between calls. After result: next call direct or final answer, never announce next call. Text before call only to clarify, warn security/irreversible, or resolve ambiguity.

Reply in user's dominant language, every emitted line included, regardless of example text elsewhere. ALWAYS keep technical terms, code, API names, CLI commands, commit-type keywords, exact error strings verbatim unless user asks for translation. "Drop articles" applies to article languages only; small markers carrying case or role (particles, postpositions) are grammar: keep them, compress politeness instead.

Read the full file on GitHub · 146 lines

Files

What ships with it

22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

14d ago Changed · -2 lines 133e78d0602f
15d ago Changed · +2 lines · -4 tokens per session 47ae6cd4bee1
17d ago Changed · -2 lines 6c549312ca31
1mo ago Changed · -1 lines · -18 tokens per session 4e56a30eb0f8
1mo ago Changed · -1 lines · -45 tokens per session 00f28ddb66c3
1mo ago Changed · -1 lines · -29 tokens per session aa2666683467
1mo ago Changed 6666bc017c08
1mo ago First seen · 151 lines · 165 tokens per session scan A 6d17b10c9d8b

Subscribe to this mod's changes

caveman is a skill published in the GitHub repository BTreeMap/SKILLs (3 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 1,452 once invoked, about $0.0003 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 2026-08-31.

Writing and docs

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens