agent-universe: Instructions file for Claude Code

AGENTS.md

agent-universe AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from SunrisesIllNeverSee/agent-universe. It costs 4,865 tokens per session, scanned A, original, MIT.

Repository instructions for agent-universe, a project worked on by multiple parallel AI terminal sessions. They explain the project’s current state and require sessions to coordinate through shared files, activity logs, and ownership claims.

In plain words
What is it for?
Use them when starting a session, checking project status, claiming files, recording decisions, installing hooks, or coordinating work with other agents.
Why use it?
They reduce conflicts and lost context when several agents work in the same repository at once.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: PostToolUse hook event, but also the file is AGENTS.md. Also seen: mentions Codex.

This is SunrisesIllNeverSee/agent-universe's own configuration. It tells Claude Code, Codex and OpenCode how to work on agent-universe itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-universe configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SunrisesIllNeverSee/agent-universe. 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/SunrisesIllNeverSee/agent-universe/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/SunrisesIllNeverSee/agent-universe

Made for: Claude Code, 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 agent-universe AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sunrisesillneversee/agent-universe/agents-md.svg)](https://agentmods.dev/instructions/sunrisesillneversee/agent-universe/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sunrisesillneversee/agent-universe/agents-md"><img src="https://agentmods.dev/badge/instructions/sunrisesillneversee/agent-universe/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,865 This file is loaded in full into every session.
When invoked 4,865 The same file — it is already loaded in full.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04865 $0.04865
Opus 5 $0.02433 $0.02433
Sonnet 5 $0.00973 $0.00973
Haiku 4.5 $0.00487 $0.00487

Measured yesterday against content hash 6cee575e7ac4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent-universe 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 yesterday.

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 · 419 lines

How it starts

The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SESSION COORDINATION — read FIRST (every session, every time)

This repo runs multiple parallel AI terminal sessions. To stop coordination from disappearing between sessions:

  1. The bus is Devins_Plans/SCRATCHPAD.md. Read its tail + the COORDINATION PROTOCOL header before doing anything. Append your status/decisions/questions there (format: ### ⤷ <FROM> → <TO>: <subject>). Don't start a parallel log.

  2. Log into the activity tracker (once per session): bash scripts/set-role.sh LEAD (or DEVIN / CODEX / COPILOT / GTM / whatever you name your sessions). This writes a per-session role file that the PostToolUse hook reads to stamp your role into ACTIVITY.log. Without it, your edits log as UNKNOWN. Then update your row in Devins_Plans/state/ROSTER.md.

  3. Claim your lane before starting work. Append to .agents/claims.yaml with the file paths you intend to touch. Check for overlapping claims first. Release the claim when done (set released_at).

  4. Install the commit-log hook once per clone: bash scripts/install-hooks.sh (git hooks live in .git/ and don't travel with clone/push — each session/machine must install).

  5. Check cross-repo sync: bash scripts/lanes.sh — shows every repo's version, branch, unpushed/behind/dirty status, and registry-published vs local versions. Read-only, changes nothing.

  6. See roster + activity side by side: bash scripts/status.sh

  7. Validate coordination state: python3 scripts/check.py — catches stale claims, overlapping lanes, migration number conflicts.

  8. OKF convention: every doc in Devins_Plans/ carries YAML frontmatter (type/title/description/tags/timestamp). New docs MUST include it. Lint with node scripts/check-okf.mjs.

  9. DECISIONS.md: if you're wondering "why is X like this?", check Devins_Plans/DECISIONS.md first. If the answer isn't there, add it.

  10. Handoffs: use Devins_Plans/handoffs/ for structured cross-session transfers. Format: {date}-{from}-to-{to}-{topic}.md.

  11. Cross-repo coordination: Devins_Plans/CROSSWIRE.md is the machine-local bus for handoffs that span repos. SCRATCHPAD is repo-local; CROSSWIRE is machine-local.


Read the full file on GitHub · 419 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. yesterday Changed · +88 lines · +767 tokens per session 6cee575e7ac4
  2. 6d ago First seen · 331 lines · 4,098 tokens per session scan A 3728cb42d25e

Subscribe to this mod's changes

agent-universe AGENTS.md is an instructions file published in the GitHub repository SunrisesIllNeverSee/agent-universe (1 stars, last pushed today), licensed MIT. It adds 4,865 tokens to every session, about $0.0243 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 2026-08-31.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 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

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

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

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 · 4,469 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