Borrowing it
Nothing to install: this file belongs to kikostefanov-lab/Arena4Ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kikostefanov-lab/Arena4Ai/main/CLAUDE.mdgit clone --depth 1 https://github.com/kikostefanov-lab/Arena4AiWrote 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/instructions/kikostefanov-lab/arena4ai/claude-md)<a href="https://agentmods.dev/instructions/kikostefanov-lab/arena4ai/claude-md"><img src="https://agentmods.dev/badge/instructions/kikostefanov-lab/arena4ai/claude-md/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/instructions/kikostefanov-lab/arena4ai/claude-md"><img src="https://agentmods.dev/badge/instructions/kikostefanov-lab/arena4ai/claude-md.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 | $0.06660 | $0.06660 |
| Opus 5.5 | $0.02664 | $0.02664 |
| Sonnet 5.5 | $0.01332 | $0.01332 |
| Haiku 4.5 | $0.00666 | $0.00666 |
Grade A, and why
Arena4Ai CLAUDE.md 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 20d 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 — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
Arena4Ai — competitive AI orchestration platform. Two (or more) AI agents race to solve a structured brief, then a cross-judge scores their deliverables. Supports Claude, Codex, and Gemini.
Running the Stack
Prerequisites (one-time setup)
# Uses local Homebrew PostgreSQL — Docker NOT required for dev
createdb arena
cp .env.example packages/web/.env.local
# Run all migrations
DATABASE_URL=postgresql://localhost/arena npm run db:migrate --workspace=packages/orchestrator
Set NEXT_PUBLIC_WS_URL=ws://localhost:3000 in packages/web/.env.local.
Running
# API server (port 3000)
DATABASE_URL=postgresql://localhost/arena \
npx tsx packages/orchestrator/src/cli.ts serve --port 3000
# Web UI (port 3001) — separate terminal
cd packages/web && npm run dev
# Single competition (no sandbox, dev mode) — DATABASE_URL required to appear in dashboard
DATABASE_URL=postgresql://localhost/arena npx tsx packages/orchestrator/src/cli.ts run briefs/fizzbuzz-cli.yml \
--team-a claude:architect --team-b gemini:speedrunner \
--skip-sandbox --log-dir /tmp/arena-logs --time-limit 120000
# With live AI commentary
npx tsx packages/orchestrator/src/cli.ts run briefs/fizzbuzz-cli.yml \
--team-a claude:architect --team-b claude:speedrunner \
--skip-sandbox --commentary
# With specific model variants
DATABASE_URL=postgresql://localhost/arena npx tsx packages/orchestrator/src/cli.ts run briefs/fizzbuzz-cli.yml \
--team-a claude:architect --model-a claude-opus-5 \
--team-b codex:speedrunner --model-b gpt-5.1-codex-max \
--skip-sandbox --time-limit 120000
# Round-robin tournament (all pairs compete)
npx tsx packages/orchestrator/src/cli.ts tournament run briefs/fizzbuzz-cli.yml \
--teams claude:architect,claude:speedrunner,codex:standard \
--models claude-opus-5,claude-sonnet-5,gpt-5.3-codex \
--skip-sandbox
# Re-evaluate completed competitions (stages: judge | presentation | synthesis | all)
# Archives the previous results to results_history before overwriting.
DATABASE_URL=postgresql://localhost/arena \
npx tsx packages/orchestrator/src/cli.ts re-evaluate --all --stage judge
# Seed quality signals from existing competitions
DATABASE_URL=postgresql://localhost/arena \
npx tsx packages/orchestrator/src/cli.ts seed-quality-signals
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.
- 20d ago Changed · -103 lines · -2,026 tokens per session adb53121300a
- 2mo ago First seen · 481 lines · 8,686 tokens per session scan A 080e055eaa8f
Arena4Ai CLAUDE.md is an instructions file published in the GitHub repository kikostefanov-lab/Arena4Ai (2 stars, last pushed 21d ago), licensed Apache-2.0. It adds 6,660 tokens to every session, about $0.0266 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.