mrburns AGENTS.md

mrburns AGENTS.md is an instructions file for Codex, OpenCode from arjun-krishna1/mrburns. It costs 1,222 tokens per session, scanned A, original, MIT.

Repository instructions for Mr. Burns, a system that coordinates multiple AI coding agents through shared JSON state files. It assigns executive, planning, and worker roles to different agents.

In plain words
What is it for?
Use it when running or modifying the Burns agent swarm, choosing a tool profile, setting parallel workers, or locating its scripts and prompts.
Why use it?
It explains how the coordinator divides work, which runtime each role uses, and how to control worker counts and execution intervals.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/arjun-krishna1/mrburns/agents-md
Clone the repo
git clone --depth 1 https://github.com/arjun-krishna1/mrburns

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.

agentmods badge for mrburns AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/arjun-krishna1/mrburns/agents-md.svg)](https://agentmods.dev/instructions/arjun-krishna1/mrburns/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/arjun-krishna1/mrburns/agents-md"><img src="https://agentmods.dev/badge/instructions/arjun-krishna1/mrburns/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,222 This file is loaded in full into every session.
When invoked 1,222 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.01222 $0.01222
Opus 5 $0.00611 $0.00611
Sonnet 5 $0.00244 $0.00244
Haiku 4.5 $0.00122 $0.00122

Measured 4d ago against content hash 9252c3730751, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mrburns AGENTS.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 4d 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.

AGENTS.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mr. Burns Agent Instructions

Overview

Mr. Burns is a Burns/Smithers/Homer autonomous coding swarm. It coordinates multiple fresh AI agent sessions through durable JSON state files.

Role Map

  1. Mr. Burns - Executive oversight. Default runtime: Claude Code.
  2. Smithers - Planning and task decomposition. Default runtime: Claude Opus via Claude Code.
  3. Homers - Parallel task execution. Default runtime: Codex with GPT-5.5.

The implementation still uses generic agent types (executive, planner, worker) in state files, but user-facing docs and runtime profiles use the fable names.

Commands

# Run with the default fable role map
./burns.sh

# Force one runtime profile for every role
./burns.sh --tool claude
./burns.sh --tool codex-gpt-5.5

# Run with 8 parallel Homers
./burns.sh --workers 8

# Run Mr. Burns every 5 cycles
./burns.sh --exec-interval 5

# Full options
./burns.sh --tool fable --workers 4 --exec-interval 10 --max-cycles 100

Key Files

Orchestrator

  • burns.sh - Main loop that resolves runtime profiles, spawns agents, and manages cycles.

Prompts

  • prompts/executive.md - Mr. Burns instructions.
  • prompts/planner.md - Smithers instructions.
  • prompts/worker.md - Homer instructions.

State

  • state/project.example.json - Tracked example configuration.
  • state/project.json - Local project goals and runtime config.
  • state/tasks/*.json - Local task queue.
  • state/agents/*.json - Local active agent registry.
  • state/logs/*.log - Local per-agent activity logs.

Runtime state is ignored by git. Do not commit live state/project.json, task queues, logs, or agent registry files unless the user explicitly asks.

Libraries

  • lib/task.sh - Task queue operations.
  • lib/agent.sh - Agent lifecycle helpers.
  • lib/git.sh - Git coordination helpers.

Docs

  • docs/overview.md - Conceptual overview.
  • docs/glossary.md - Terminology.
  • docs/design/architecture.md - Technical architecture.
  • docs/guides/configuration.md - Configuration guide.
  • docs/reference.md - CLI, profile, schema, and signal reference.

Read the full file on GitHub · 180 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.

  1. 4d ago First seen · 180 lines · 1,222 tokens per session scan A 9252c3730751

Subscribe to this mod's changes

mrburns AGENTS.md is an instructions file published in the GitHub repository arjun-krishna1/mrburns (11 stars, last pushed 1mo ago), licensed MIT. It adds 1,222 tokens to every session, about $0.0061 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 2026-08-30.

Related

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).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens