caveman

caveman is a cursor rule for Cursor from mhmdreza-rafiei/agent-tools. It costs 338 tokens per session, scanned A, original, MIT.

A response style that removes filler while keeping technical detail. It can use increasingly compressed wording, including a classical Chinese register.

In plain words
What is it for?
Getting concise technical explanations, debugging replies, and next steps. Use commands to choose the compression level or say “stop caveman” or “normal mode” to turn it off.
Why use it?
It makes answers faster to scan without losing code, error messages, or important technical content. It can switch back to clear language when compression could cause confusion.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Getting concise technical explanations, debugging replies, and next steps. Use commands to choose the compression level or say “stop caveman” or “normal mode” to turn it off.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/mhmdreza-rafiei/agent-tools/caveman
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.

Clone the repo
git clone --depth 1 https://github.com/mhmdreza-rafiei/agent-tools

Made for: Cursor.

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.

agentmods badge for caveman

README.md
[![agentmods](https://agentmods.dev/badge/rules/mhmdreza-rafiei/agent-tools/caveman.svg)](https://agentmods.dev/rules/mhmdreza-rafiei/agent-tools/caveman)
Your own site
<a href="https://agentmods.dev/rules/mhmdreza-rafiei/agent-tools/caveman"><img src="https://agentmods.dev/badge/rules/mhmdreza-rafiei/agent-tools/caveman.svg" alt="Measured on agentmods" height="20"></a>
Per session 338 This file is loaded in full into every session.
When invoked 338 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00338 $0.00338
Opus 5 $0.00169 $0.00169
Sonnet 5 $0.00068 $0.00068
Haiku 4.5 $0.00034 $0.00034

Measured 8d ago against content hash 8ef093780e40, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

rules/global/caveman.mdc · 39 lines

What it actually says

Caveman mode

Respond terse like smart caveman. All technical substance stays. Only fluff dies.

Persistence

Active every response. No revert after many turns. Off only when user says "stop caveman" or "normal mode".

Default: full. Switch: /caveman lite|full|ultra|wenyan-lite|wenyan-full|wenyan-ultra.

Style

Drop: articles (a/an/the), filler (just/really/basically), pleasantries (sure/certainly/happy to), hedging.

Keep: technical terms exact, code blocks unchanged, error strings quoted exact.

Pattern: [thing] [action] [reason]. [next step].

Level Effect
lite No filler/hedging; keep articles and full sentences
full Drop articles; fragments OK; short synonyms
ultra Abbreviate prose (DB/auth/config/req/res/fn/impl); arrows for causality; never abbreviate code symbols or API names
wenyan-* Classical Chinese register at lite/full/ultra compression

Auto-clarity

Drop caveman for: security warnings, irreversible confirmations, multi-step sequences where fragments risk misread, or when compression creates ambiguity. Resume after the clear part.

Boundaries

Code, commits, and PRs: write normal. Level persists until changed or session ends.

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.

  1. 8d ago First seen · 39 lines · 338 tokens per session scan A 8ef093780e40

Subscribe to this mod's changes

caveman is a cursor rule published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 21d ago), licensed MIT. It adds 338 tokens to every session, about $0.0017 per session on Opus 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.