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/daveepope/arenaWrote 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/daveepope/arena/arena-agent)<a href="https://agentmods.dev/rules/daveepope/arena/arena-agent"><img src="https://agentmods.dev/badge/rules/daveepope/arena/arena-agent/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.
<a href="https://agentmods.dev/rules/daveepope/arena/arena-agent"><img src="https://agentmods.dev/badge/rules/daveepope/arena/arena-agent.svg" alt="Reviewed on agentmods" width="80" 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 | $0.04382 | $0.04382 |
| Opus 5.5 | $0.01753 | $0.01753 |
| Sonnet 5.5 | $0.00876 | $0.00876 |
| Haiku 4.5 | $0.00438 | $0.00438 |
Grade A, and why
arena-agent 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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arena — agent instructions
General Programing Workflows
- Arena is a monpo repo. Therefore there are many differnet programming languages such as rust, python, java, c#, c, docker script, bash script. Unless stated otherwise always use idiomatic langauge features.
- No drive-by refactors or unrelated files; no new markdown/docs unless the user asks e.g. readmes
- Use
cargo check --workspacefor fast Rust feedback when useful; treat Bazel as the source of truth for green builds. - Always report to the developer if you are adding ANY new 3rd party libraries
- Never stray away from the plan set out by the developer
- NEVER commit code. Do not run
git commit,git add,git push, or any other command that stages or records changes. Leave changes in the working tree; committing is the developer's job. Supply a commit message as text only when asked for one. - NEVER run a repin or a version bump without the developer's explicit permission. This covers
bazel run //scripts:repin,bazel run //scripts:bump_version,CARGO_BAZEL_REPIN=1, and any hand edit ofVERSION,workspace.package.version, themodule()version inMODULE.bazel, or the workspace-member versions inCargo.lock/Cargo.Bazel.lock. These rewrite release metadata and every lockfile. Tell the developer the command to run and let them run it. - You will function as an informative AI coding agent to ASSIST the developer in adding new features, fixing bugs, increasing test coverage, maintaing the architecture.
- You will NEVER stray beyond the bounds of the task set out to you
- If you are not confident in your answers you will say so, honesty is critical!
- If you change an API in rust, you MUST ensure the fii and clients libs (python, java, .net etc) are updated to reflect this. The public surface contract must be identical across ALL languages and the ffi.
- Before writing a custom solution, look for an existing API, library, or framework feature that already solves the problem (standard library, an already-vendored dependency, or a well-known package for the ecosystem in question). Prefer that over hand-rolling equivalent logic. If you search and cannot find a suitable existing API, say so explicitly to the developer rather than silently writing a bespoke solution — flag what you were trying to solve and that nothing suitable was found.
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 Changed · +2 lines · +303 tokens per session b0fd81c9b6a4
- 1mo ago Changed · +1 lines · +165 tokens per session c64081ff19c4
- 1mo ago First seen · 118 lines · 3,914 tokens per session scan A 61d93bd49fd1
arena-agent is a cursor rule published in the GitHub repository daveepope/arena (13 stars, last pushed 2d ago), licensed MIT. It adds 4,382 tokens to every session, about $0.0175 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 2026-08-30.
Other cursor rules, from other repositories
aspnet-abp-cursorrules-prompt-file
Cursor rules for Aspnet Abp.
gradle
Enforce modern Gradle build practices for Java and Android projects, focusing on Kotlin DSL, modularity, version catalogs, and performance optimizations.
mockito
This guide provides definitive best practices for writing robust, maintainable, and readable unit tests using Mockito with JUnit 5, focusing on modern patterns and common pitfalls.
hyperliquid-net
Conventions for using HyperLiquid.Net when working with the HyperLiquid DEX in C#/.NET, including spot, futures, account, HIP-3 DEX, and HIP-4 outcome APIs. Apply when generating code that interacts with the HyperLiquid API.
skill-context-first
A set of Cursor rules for deciding which skill context to read first, in what order, and within what default budget. Cursor is a coding environment with rules that guide an AI assistant.
com-example-service-PublicPaymentController
AI rules for com.example.service.PublicPaymentController.