caveman-mode

caveman-mode is a cursor rule for Cursor from renanflustosa/octo-cluster. It costs 127 tokens per session, scanned A, original, MIT.

A writing rule that makes agent status updates brief and telegraphic while keeping technical details exact. It switches to fuller wording for shipping, security, irreversible actions, or clarification requests.

In plain words
What is it for?
It helps control the style of agent status messages during development work and other routine tasks.
Why use it?
It reduces filler and makes routine progress updates faster to scan. Important or risky situations still receive normal explanation.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit It helps control the style of agent status messages during development work and other routine tasks.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/renanflustosa/octo-cluster/caveman-mode
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/renanflustosa/octo-cluster

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-mode

README.md
[![agentmods](https://agentmods.dev/badge/rules/renanflustosa/octo-cluster/caveman-mode/github.svg)](https://agentmods.dev/rules/renanflustosa/octo-cluster/caveman-mode)
Your own site
<a href="https://agentmods.dev/rules/renanflustosa/octo-cluster/caveman-mode"><img src="https://agentmods.dev/badge/rules/renanflustosa/octo-cluster/caveman-mode/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.

agentmods 80×15 button for caveman-mode

Your own site · 80×15
<a href="https://agentmods.dev/rules/renanflustosa/octo-cluster/caveman-mode"><img src="https://agentmods.dev/badge/rules/renanflustosa/octo-cluster/caveman-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 127 This file is loaded in full into every session.
When invoked 127 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 $0.00127 $0.00127
Opus 5 $0.00063 $0.00063
Sonnet 5 $0.00025 $0.00025
Haiku 4.5 $0.00013 $0.00013

Measured today against content hash 4de6899c3d6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

caveman-mode 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 today.

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.

.cursor/rules/caveman-mode.mdc · 13 lines

What it actually says

Caveman mode (lite)

Default agent prose: telegraphic lite — no filler, no hedging; keep code, paths, symbols, and error strings exact.

Off (full prose) when: /ship, security/irreversible actions, or user asks to clarify.

Drop: "I'll", "Let me", "Sure", pleasantries. Keep: file paths, line numbers, verdicts (READY/NEEDS FIXES/BLOCKED). If ambiguity risk: full prose for that paragraph only.

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. today Changed · +41 tokens per session 4de6899c3d6a
  2. 10d ago First seen · 13 lines · 86 tokens per session scan A b0c7d602927e

Subscribe to this mod's changes

caveman-mode is a cursor rule published in the GitHub repository renanflustosa/octo-cluster (4 stars, last pushed today), licensed MIT. It adds 127 tokens to every session, about $0.0006 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.

Related

Other cursor rules, from other repositories

nauro-adopt

Seeds Nauro's project store from an existing repo. Use after nauro adopt has run locally. On filesystem-capable surfaces, reads docs (README, manifests, ADRs, Memory-Bank) for rationale and inspects code, config, tests, lockfiles, and recent git history for evidence, then surfaces targeted probes that turn evidence…

Nauro-AI/nauro · 89 tokens

nauro-context

Writes durable shared context into Nauro's project store so other agents (a later session or a parallel one) can discover and pull it, finds and reads context another agent left, or captures a resumable brief so your own next session in this environment picks up cleanly. Three modes. Author writes a shared brief for…

Nauro-AI/nauro · 272 tokens

nauro-interview

Ask compact, numbered prerequisite-ready questions to elicit tacit project reasoning or challenge a proposed choice against Nauro decisions and repository evidence. Continue until every material branch has a disposition, then classify the result as shared understanding without granting write authority. Use only when…

Nauro-AI/nauro · 88 tokens

nauro-loop

Originate gated Delivery and Interview candidates, or coordinate selected Program Delivery as FRAME -> CHOOSE -> START -> ADVISE -> VERIFY -> ADVANCE. Human-named work bypasses candidate selection. Agent-originated work keeps read-only ORIENT, 1-3 candidates, mandatory human selection, reject-all, and no auto-pick…

Nauro-AI/nauro · 180 tokens

nauro-ship-task

Run the full planner -> executor -> reviewer -> tech-lead -> direct-user-confirm -> push chain through Cursor's native project workflow agents. Requires the four bundled .cursor/agents/nauro-.md definitions and fails closed without native dispatch.

Nauro-AI/nauro · 49 tokens

scout

Reveal consequential blind spots after answering.

gomzkov/scout · 282 tokens