agent-quotas: Instructions file for Codex

AGENTS.md

agent-quotas AGENTS.md is an instructions file for Codex, OpenCode from Open330/agent-quotas. It costs 2,513 tokens per session, scanned B, original, MIT.

A project setup guide for configuring a Claude quota monitor in an Open330/agent-quotas project.

In plain words
What is it for?
Setting up the quota monitor and creating its hook configuration.
Why use it?
It gives the setup steps and lists the information needed before creating the monitor's hook configuration file.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; reads ~/.codex paths.

This is Open330/agent-quotas's own configuration. It tells Codex and OpenCode how to work on agent-quotas 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-quotas configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Open330/agent-quotas. 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/Open330/agent-quotas/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Open330/agent-quotas

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 agent-quotas AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/open330/agent-quotas/agents-md/github.svg)](https://agentmods.dev/instructions/open330/agent-quotas/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/open330/agent-quotas/agents-md"><img src="https://agentmods.dev/badge/instructions/open330/agent-quotas/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.

agentmods 80×15 button for agent-quotas AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/open330/agent-quotas/agents-md"><img src="https://agentmods.dev/badge/instructions/open330/agent-quotas/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,513 This file is loaded in full into every session.
When invoked 2,513 The same file — it is already loaded in full.
Security scan B 2 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 $0.02513 $0.02513
Opus 5.5 $0.01005 $0.01005
Sonnet 5.5 $0.00503 $0.00503
Haiku 4.5 $0.00251 $0.00251

Measured 2mo ago against content hash 0b023537934d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

agent-quotas AGENTS.md scanned grade B with 2 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 2mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep 'notify' ~/.codex/config.toml 2>/dev/null || echo "(not configured)"

Makes network callslowCapability

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

- `curl` is installed: `command -v curl` should return a path
AGENTS.md · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Quota Monitor — Agent Setup Guide

This guide is for AI agents (Claude Code, Codex CLI, Antigravity, etc.) to set up the quota monitoring hook on a user's machine autonomously.

Prerequisites

Before starting, verify:

  • jq is installed: command -v jq should return a path
  • curl is installed: command -v curl should return a path
  • A quota monitor server is running (ask user if not provided)
  • The user has a Personal Access Token (PAT) issued by the server admin

Setup Steps

Step 1: Gather Configuration from User

Ask the user for:

  1. Server URL: The address where the quota monitor server is running (e.g., http://192.168.1.100:3000 or http://localhost:3000)
  2. Username: A display name for this machine on the dashboard (e.g., MacBook Pro or dev-machine)
  3. Token: A Personal Access Token (PAT) obtained from the server admin panel. The user must request this from their admin.

If the user doesn't have a server running yet, direct them to the Server Setup section at the end.

If the user doesn't have a PAT yet, direct them to request one from the admin via the admin panel (/admin).

Step 2: Create Hook Configuration File

Write the configuration to ~/.claude-quota-hook.json:

{
  "server_url": "USER_PROVIDED_SERVER_URL",
  "username": "USER_PROVIDED_USERNAME",
  "token": "PAT_FROM_ADMIN"
}

Example:

{
  "server_url": "http://192.168.1.100:3000",
  "username": "alice",
  "token": "PAT_abc123xyz"
}

All three fields are required. The token authenticates this client with the server and must be a valid PAT issued by the admin.

Step 3: Locate and Verify Hook Scripts

Hook scripts are located in REPO_PATH/hook/:

Tool Script
Claude Code hook/claude-quota-hook.sh
Codex CLI hook/codex-hook.sh
Antigravity hook/antigravity-hook.sh

Ensure all scripts are executable:

chmod +x REPO_PATH/hook/claude-quota-hook.sh
chmod +x REPO_PATH/hook/codex-hook.sh
chmod +x REPO_PATH/hook/antigravity-hook.sh

Read the full file on GitHub · 317 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. 2mo ago First seen · 317 lines · 2,513 tokens per session scan B 0b023537934d

Subscribe to this mod's changes

agent-quotas AGENTS.md is an instructions file published in the GitHub repository Open330/agent-quotas (1 stars, last pushed 1mo ago), licensed MIT. It adds 2,513 tokens to every session, about $0.0101 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). 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

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 · 9,715 tokens

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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

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).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens