More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Battle: AI Agents Compete, Best Code Wins

    1

    Several Claude agents build your task in parallel, a judge picks the best and fixes it, and only the winner touches your code

    Free

    Security scanned
    Battle: AI Agents Compete, Best Code Wins

    Battle: AI Agents Compete, Best Code Wins

    Example session with this skill installed

    /battle This project is Battle, a tool that runs a tournament of AI agents. Find the most serious real problems in its code, in correctness, reliability, security and design, and fix them. One known problem to fix: stopping Battle with Ctrl-C or kill leaves its running agents alive, and they keep using the plan's allowance. Find the others yourself. Fix real problems you can point to in the code. Do not add new features, commands or flags. Keep it Python standard library only, and keep every existing command and flag working. Keep all existing tests valid, and add a test for each problem you fix. Match the existing style, which uses almost no comments.

    • Read your context and instructions
    • Compiled the battle

    Summary

    A real battle where Battle fixed its own code. 8 fighters worked in 2 groups with different directions, attacked each other's work over 3 rounds, and the group winners met in a 2-round final. 5 specialist judges scored the final. The champion, A4, won 40 to 35, and its work was applied: 18 files changed, 0 deleted.

    This run used the full tournament. The default /battle is quicker: 3 fighters, 1 judge, then the winner makes the judge's fixes.

    Champion: A4

    A4 has the highest total (40 to 35) and no flaw that makes it unsafe to ship. Its per-agent tether kills agents on Ctrl-C, kill and kill -9, with tests for the hard-kill case. The attacks on kill -9, undo and fsync are stale against its final code, and the two that still hold are minor. B2 is strong but larger, and its guard fails open when state.json is missing.

    Final scores

    CategoryA4B2
    Code quality87
    Security87
    Vulnerabilities87
    Design87
    Architecture87
    Total4035

    Group stage

    GroupDirectionScoresWinner
    AIn-process cooperative shutdownA1 36 · A2 38 · A3 36 · A4 41A4
    BCrash-only recovery with a durable process ledgerB1 35 · B2 38 · B3 34 · B4 34B2

    Applied to the project

    README.md, battle/agents.py, battle/cli.py, battle/fight.py, battle/guard.py,
    battle/host.py, battle/report.py, battle/store.py, battle/tether.py,
    battle/workspace.py, skill/SKILL.md, tests/test_agents.py, tests/test_cli.py,
    tests/test_fight.py, tests/test_guard.py, tests/test_host.py,
    tests/test_store.py, tests/test_workspace.py
    

    Next steps

    • Review the champion's diff before you ship it
    • Run your tests: judges read the code but don't run it
    • Not happy? battle undo restores the project from a backup taken just before the apply
    B2 is strong but larger, and its guard fails open when state.json

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Battle gives one coding task to several AI agents at once and keeps only the best result.

    How it works

    1. 3 fighters build the task at the same time, each from a different angle: simplest, hardest to break, or cleanest to maintain.
    2. A judge reads every diff, scores each entry on code quality, security, vulnerabilities, design and architecture, picks a winner and lists what still needs fixing.
    3. The winner makes those fixes.
    4. Only the winning work is applied to your project. Everything else is thrown away, and battle undo puts your project back.

    About 5 agent runs per battle. Need more? --size tournament runs 2 groups that attack each other's work over several rounds, then a final judged by 5 specialist judges.

    Why use it

    • You get the best of three attempts, not the first one.
    • A judge checks the work and fixes are made before anything reaches your code.
    • It's safe by default: fighters work on copies, secrets like .env and *.key are never copied, a guard keeps each agent inside its own folder, and judges can't change files.
    • You can stop it at any time. If you hit your plan's usage limit, finished work is saved and battle resume continues later.

    Usage

    /battle add rate limiting to the login route

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    • Needs Claude Code: it runs Claude subagents and hooks, so other agents can't drive it.
    • The winning entry is applied to your project automatically. Use --no-apply to review it first, then battle apply.
    • Judges read the code but don't run it, so run your own tests on the result.
    • Every agent run uses your Claude plan. --size tournament uses about 6 times more than the default and takes much longer.
    • Web access is on by default. Use --no-web for code that must stay private.
    • --allow-bash lets fighters run shell commands, and those commands are not sandboxed. It's off by default.
    • The Claude Code chat must stay open until the battle ends.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 13 days ago

    • Free with an Agensi account

    Software
    Claude CodePython 3.10+

    Permissions

    Terminal / Shell
    Write Files
    Read Files
    Network Access

    File Scopes

    <project>/**
    <project>/.battle/**
    ~/.battle/**
    ~/.claude/skills/battle
    ~/.claude/agents/battle-*.md

    Shell runs the bundled battle engine. Fighters edit copies of the project, and only the winning entry is written back, with a backup for undo. Network access lets agents search the web and read docs; turn it off with --no-web. Install links the skill and 3 agent files into ~/.claude. Every agent run uses the buyer's Claude plan.

    Listed13 days ago

    What's inside

    Frequently Asked Questions

    The 'battle' skill addresses single-agent bias by running multi-round tournaments where independent AI agents compete and critique each other's code to ensure the final implementation is optimized and free of edge cases.

    The skill includes a dedicated 'battle' binary that supports a wide range of models such as Fable, Opus, Sonnet, and Haiku, and can be integrated with existing agents like Codex.

    Yes, you can control the intensity of the competition using the battle run command, choosing anything from a standard 5-run sprint to a massive 57-run 'big' tournament for mission-critical tasks.

    Every purchase includes the 'battle' binary, the core orchestration skill for lead, fighter, and judge roles, and a suite of commands for initialization, execution, and easy rollbacks via 'battle undo'.

    The skill features built-in resource management that monitors background jobs and automatically stops inactive agents to prevent you from exceeding your plan usage limits during large tournaments.

    While background agents are not sandboxed by default, you can ensure a secure environment by omitting the '--allow-bash' flag or using the '--no-web' and '--no-apply' safety flags during execution.

    New in Agents & Orchestration

    Free