What is havoc-hackathon AGENTS.md?

Project instructions for a hackathon system that runs competitions between multiple AI models, plus supporting agents for the tournament and its maintenance. A hackathon here means a structured contest in which models produce and compare solutions.

Use it to run full or quick AI-model tournaments, compare finalists, maintain ratings, or inspect and improve the tournament’s agent files.

It explains which agents are available and how the tournament and repair workflows are meant to operate. The excerpt does not describe a general-purpose coding tool.

How DUBSOpenHub/havoc-hackathon configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to DUBSOpenHub/havoc-hackathon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/DUBSOpenHub/havoc-hackathon/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/DUBSOpenHub/havoc-hackathon

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dubsopenhub/havoc-hackathon/agents-md/github.svg)](https://agentmods.dev/instructions/dubsopenhub/havoc-hackathon/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/dubsopenhub/havoc-hackathon/agents-md"><img src="https://agentmods.dev/badge/instructions/dubsopenhub/havoc-hackathon/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dubsopenhub/havoc-hackathon/agents-md"><img src="https://agentmods.dev/badge/instructions/dubsopenhub/havoc-hackathon/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 677 This file is loaded in full into every session.

When invoked 677 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00677	$0.00677
Opus 5.5	$0.00271	$0.00271
Sonnet 5.5	$0.00135	$0.00135
Haiku 4.5	$0.00068	$0.00068

Measured 1mo ago against content hash 5fbf27166e5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

havoc-hackathon AGENTS.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sL https://raw.githubusercontent.com/DUBSOpenHub/havoc-hackathon/main/skills/havoc-hackathon/SKILL.md \

AGENTS.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents

Overview

Havoc Hackathon ships two Copilot CLI agents and one skill. The skill (havoc-hackathon) is the primary entry point — it orchestrates full multi-model tournaments. The havoc-hackathon agent is a standalone agent version of the same capability. The grid-medic agent is bundled as a companion for keeping the tournament infrastructure healthy.

Available Agents

havoc-hackathon (Skill)

Purpose: Multi-model AI tournament orchestrator. Dispatches the current selectable GitHub Copilot model roster in elimination heats, scores them with sealed judge panels (judges never know which model wrote what), evolves the best ideas between rounds, synthesizes a final output from all finalists, and maintains persistent ELO ratings across sessions.

Usage: Install via Copilot CLI, then invoke with natural language:

run hackathon                        # Full tournament on whatever you describe
run hackathon express                # Quick single-round version
/skills add DUBSOpenHub/havoc-hackathon  # Instant install

Model: Dispatches to all available models in your Copilot CLI session

Install:

mkdir -p ~/.copilot/skills/havoc-hackathon ~/.copilot/agents && \
  curl -sL https://raw.githubusercontent.com/DUBSOpenHub/havoc-hackathon/main/skills/havoc-hackathon/SKILL.md \
    -o ~/.copilot/skills/havoc-hackathon/SKILL.md

Location: skills/havoc-hackathon/SKILL.md

havoc-hackathon (Agent)

Purpose: Standalone agent version of the tournament orchestrator. Use when you want the Havoc Hackathon capability as a named agent rather than a skill.
Usage: After installing ~/.copilot/agents/havoc-hackathon.agent.md, invoke via the agent selector in Copilot CLI.
Location: agents/havoc-hackathon.agent.md

grid-medic

Purpose: Companion agent bundled with Havoc Hackathon. Self-healing meta-agent that monitors and repairs the .agent.md files in your fleet — including Havoc Hackathon's own agent files. See DUBSOpenHub/grid-medic for full documentation.

Usage:

grid-medic diagnose
grid-medic improve havoc-hackathon

Location: agents/grid-medic.agent.md

Read the full file on GitHub · 51 lines

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.

1mo ago Changed 5fbf27166e5a
2mo ago First seen · 51 lines · 677 tokens per session scan A c18aa0ceb2bc

Subscribe to this mod's changes

havoc-hackathon AGENTS.md is an instructions file published in the GitHub repository DUBSOpenHub/havoc-hackathon (5 stars, last pushed 5d ago), licensed MIT. It adds 677 tokens to every session, about $0.0027 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Orchestration adversarial-ai ai-agents blind-adjudication copilot-cli multi-model

havoc-hackathon AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
havoc-hackathon AGENTS.mdDUBSOpenHub/havoc-hackathon	Instructions file	5	5d ago	MIT	A	677	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

havoc-hackathon: Instructions file for Codex