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.
curl -O https://raw.githubusercontent.com/amitpatole/claude-genkit-plugin/main/AGENTS.mdgit clone --depth 1 https://github.com/amitpatole/claude-genkit-pluginWrote 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.
[](https://agentmods.dev/instructions/amitpatole/claude-genkit-plugin/agents-md)<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.
<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>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 | $0.02940 | $0.02940 |
| Opus 5.5 | $0.01176 | $0.01176 |
| Sonnet 5.5 | $0.00588 | $0.00588 |
| Haiku 4.5 | $0.00294 | $0.00294 |
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.
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:
- Schedule Enforcement Agent - Ensures all deployments occur during the approved time window
- 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
- Pre-deployment Check: Every deployment workflow first checks if current time is within the window
- Block on Violation: Exits with error code 1 if deployment attempted outside window
- Generate Reports: Creates violation reports in
agent-reports/directory - Status Updates: Updates
.github/agent-status/schedule-enforcement.txtevery 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.ymlvscode-extension-ci.yml(publish job)vscode-extension-release.yml
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.
- 2mo ago First seen · 426 lines · 2,940 tokens per session scan A e7bce61479d9
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.
claude-genkit-plugin AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claude-genkit-plugin AGENTS.mdamitpatole/claude-genkit-plugin | Instructions file | 10 | 1mo ago | MIT | A | 2,940 | 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 |