claude-genkit-plugin: Instructions file for Codex

AGENTS.md

claude-genkit-plugin AGENTS.md is an instructions file for Codex, OpenCode from amitpatole/claude-genkit-plugin. It costs 2,940 tokens per session, scanned A, original, MIT.

Repository instructions documenting two always-running agents: one controls deployment times and another monitors system health and maintenance.

In plain words
What is it for?
Understanding schedule-enforcement workflows, checking deployment-window violations, reviewing health monitoring, and maintaining the related documentation.
Why use it?
They explain the project’s automated deployment rules and help agents work within the approved schedule and monitoring process.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is amitpatole/claude-genkit-plugin's own configuration. It tells Codex and OpenCode how to work on claude-genkit-plugin 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 claude-genkit-plugin configures →

Reuse

Borrowing it

Nothing to install: this file belongs to amitpatole/claude-genkit-plugin. 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/amitpatole/claude-genkit-plugin/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/amitpatole/claude-genkit-plugin

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 claude-genkit-plugin AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/amitpatole/claude-genkit-plugin/agents-md/github.svg)](https://agentmods.dev/instructions/amitpatole/claude-genkit-plugin/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/amitpatole/claude-genkit-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/amitpatole/claude-genkit-plugin/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 claude-genkit-plugin AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/amitpatole/claude-genkit-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/amitpatole/claude-genkit-plugin/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,940 This file is loaded in full into every session.
When invoked 2,940 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 $0.02940 $0.02940
Opus 5.5 $0.01176 $0.01176
Sonnet 5.5 $0.00588 $0.00588
Haiku 4.5 $0.00294 $0.00294

Measured 2mo ago against content hash e7bce61479d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-genkit-plugin 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 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.

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 · 426 lines

How it starts

The opening of the file, as written. The whole thing — 426 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autonomous Agents Documentation

This repository uses autonomous agents that run 24/7 to manage deployments, monitor health, and maintain the codebase.

Overview

Two primary agents operate continuously:

  1. Schedule Enforcement Agent - Ensures all deployments occur during the approved time window
  2. Monitoring & Maintenance Agent - Monitors health, fixes issues, and manages updates

Agent 1: Schedule Enforcement Agent

Purpose

Enforces strict deployment schedules to ensure all pushes, releases, and deployments occur only during the approved time window.

Schedule

  • Runs: Every 5 minutes (24/7)
  • Workflow: .github/workflows/schedule-enforcement-agent.yml

Deployment Window

ALLOWED: 10:00 PM - 8:00 AM EST BLOCKED: 8:00 AM - 10:00 PM EST

Features

  • ✅ Checks all deployment workflows for schedule compliance
  • ✅ Blocks deployments outside the allowed window
  • ✅ Monitors recent workflow runs for violations
  • ✅ Generates violation reports
  • ✅ Provides real-time status updates
  • ✅ Heartbeat monitoring to confirm agent is running

Actions Taken

  1. Pre-deployment Check: Every deployment workflow first checks if current time is within the window
  2. Block on Violation: Exits with error code 1 if deployment attempted outside window
  3. Generate Reports: Creates violation reports in agent-reports/ directory
  4. Status Updates: Updates .github/agent-status/schedule-enforcement.txt every 5 minutes

How It Works

# Check if within deployment window (10 PM - 8 AM EST)
CURRENT_HOUR=$(TZ='America/New_York' date +%H)

# Hours 22-23 (10 PM - 11:59 PM) OR 0-7 (12 AM - 7:59 AM) = ALLOWED
# Hours 8-21 (8 AM - 9:59 PM) = BLOCKED

if [ "$CURRENT_HOUR" -ge 22 ] || [ "$CURRENT_HOUR" -lt 8 ]; then
  echo "✅ Within deployment window - Proceeding"
else
  echo "🚫 BLOCKED: Outside deployment window"
  exit 1
fi

Modified Workflows

All deployment workflows now include schedule enforcement:

  • publish-vscode-extension.yml
  • vscode-extension-ci.yml (publish job)
  • vscode-extension-release.yml

Read the full file on GitHub · 426 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 · 426 lines · 2,940 tokens per session scan A e7bce61479d9

Subscribe to this mod's changes

claude-genkit-plugin AGENTS.md is an instructions file published in the GitHub repository amitpatole/claude-genkit-plugin (10 stars, last pushed 1mo ago), licensed MIT. It adds 2,940 tokens to every session, about $0.0118 per session on Opus 5.5. 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

claude-genkit-plugin AGENTS.md compared with instructions from other repositories

claude-genkit-plugin AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
claude-genkit-plugin AGENTS.mdamitpatole/claude-genkit-pluginInstructions file101mo agoMITA2,940Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode