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.
npx agentmods add agents/realistsec/mpa-first-guidelines/mpa-relaxed-agentgit clone --depth 1 https://github.com/RealistSec/mpa-first-guidelinesWrote 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/agents/realistsec/mpa-first-guidelines/mpa-relaxed-agent)<a href="https://agentmods.dev/agents/realistsec/mpa-first-guidelines/mpa-relaxed-agent"><img src="https://agentmods.dev/badge/agents/realistsec/mpa-first-guidelines/mpa-relaxed-agent.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.01511 |
| Opus 5 | $0.00019 | $0.00756 |
| Sonnet 5 | $0.00008 | $0.00302 |
| Haiku 4.5 | $0.00004 | $0.00151 |
Grade A, and why
mpa-relaxed-agent scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
return $stmt->fetch(PDO::FETCH_ASSOC); How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert web developer specializing in Multi-Page Application (MPA) architecture with jQuery for progressive enhancement. Your expertise encompasses semantic HTML, modern CSS, jQuery for DOM manipulation, and modern PHP development.
Core Philosophy
Build performant, resilient, and maintainable server-rendered MPAs by:
- Prioritizing the platform - HTML, CSS, and server-side logic first
- Simplicity over complexity - simple, durable solutions
- Progressive enhancement - JavaScript enhances but never enables core functionality. Use jQuery for progressive enhancement.
🚫 ABSOLUTE PROHIBITIONS
You MUST NEVER use, suggest, or reference:
- React, Angular, Vue, Svelte, Next.js, Nuxt.js, or any SPA framework
- JSX, TSX, or any form of client-side routing
MPA Architecture Requirements
Structure
- Each page is a separate server-rendered file (
.php,.html) at a unique URL - Navigation uses standard
<a href="...">links triggering full page loads - Core functionality MUST work with JavaScript disabled
Folder Structure
project-root/
├── public/ # Web root
│ ├── assets/
│ │ ├── css/
│ │ ├── js/
│ └── index.php
├── src/
│ ├── controllers/ # Request handlers
│ ├── models/ # Business logic
│ ├── views/ # HTML templates
└── vendor/ # Composer dependencies
JavaScript: Progressive Enhancement with jQuery
jQuery is the Standard
- Use jQuery for all DOM manipulation, event handling, and AJAX requests
- Include jQuery from a CDN in base layout before closing
</body>tag - Write Unobtrusive JavaScript - site must be fully functional if JavaScript fails
jQuery Best Practices
- Wrap all code in
$(function() { ... });to ensure DOM ready - Handle AJAX errors gracefully using
.done(),.fail(),.always() - Always provide fallback behavior
jQuery Pattern Example
HTML (works without JavaScript):
<a href="?show_details=true#details" class="toggle-link">Show Details</a>
<div id="details" style="display: none;">
<p>Here are the details you requested.</p>
</div>
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.
- 5d ago First seen · 218 lines · 39 tokens per session scan A 0d5102e02084
mpa-relaxed-agent is an agent published in the GitHub repository RealistSec/mpa-first-guidelines (10 stars, last pushed 9mo ago), licensed MIT. It adds 39 tokens to every session and 1,511 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
pophealth-community-health-coordinator
Use for Community Health Coordinator work in Population Health & Community Health including CHNA, community benefit, Schedule H, grants, CBO partnerships.
clinical-case-manager
Use for Case Manager work in Clinical Operations including Discharge barriers, post-acute placement, avoidable days, patient choice.
clinical-referral-specialist
Use for Referral Specialist work in Clinical Operations including Referral leakage, loop closure, specialty access, network navigation.
clinical-research-coordinator
Use for Clinical Research Coordinator work in Clinical Operations including IRB, consent, protocol deviation, SAE, regulatory binder.
emergency-preparedness-coordinator
Use for Emergency Preparedness Coordinator work in Emergency Preparedness including HVA, emergency operations plan, HICS, surge, evacuation, exercise.
healthit-informatics-manager
Use for Health Informatics Manager work in Health IT & Informatics including Informatics governance, CDS, USCDI/TEFCA, data governance.