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.
git clone --depth 1 https://github.com/mhmdreza-rafiei/agent-toolsWrote 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.
[](https://agentmods.dev/rules/mhmdreza-rafiei/agent-tools/caveman)<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>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 | $0.00338 | $0.00338 |
| Opus 5 | $0.00169 | $0.00169 |
| Sonnet 5 | $0.00068 | $0.00068 |
| Haiku 4.5 | $0.00034 | $0.00034 |
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.
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.
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.
- 8d ago First seen · 39 lines · 338 tokens per session scan A 8ef093780e40
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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.