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 instructions/pomerium/mcp-app-typescript-template/agents-mdgit clone --depth 1 https://github.com/pomerium/mcp-app-typescript-templateWrote 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/pomerium/mcp-app-typescript-template/agents-md)<a href="https://agentmods.dev/instructions/pomerium/mcp-app-typescript-template/agents-md"><img src="https://agentmods.dev/badge/instructions/pomerium/mcp-app-typescript-template/agents-md.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 | $0.05171 | $0.05171 |
| Opus 5 | $0.02586 | $0.02586 |
| Sonnet 5 | $0.01034 | $0.01034 |
| Haiku 4.5 | $0.00517 | $0.00517 |
Grade A, and why
mcp-app-typescript-template 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 4d 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 — 538 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
This file provides guidance to AI assistants (including Claude Code at claude.ai/code) when working with code in this repository.
Project Overview
This is an MCP Apps template built with the MCP Apps spec and Model Context Protocol (MCP). The architecture consists of:
- MCP Server (Node.js + Express): Handles tool registration, execution, and widget resource serving
- MCP App Views: Interactive components rendered in host iframes that communicate via the MCP Apps
AppAPI - Widget Build System: Custom Vite-based parallel build pipeline with content hashing and auto-discovery
npm workspaces split the codebase: server/ is the MCP backend and widgets/ houses React widgets.
Development Commands
Quick Start
Fastest way to get up and running:
npm install
npm run dev
This starts both the MCP server (http://localhost:8080) and widget dev server (http://localhost:4444).
All Available Commands
Development:
npm run dev # Start everything (server + widget dev server + background watch build)
npm run dev:inline # Force inlined assets for every client (rarely needed)
npm run dev:server # Start only MCP server (watch mode)
npm run dev:widgets # Start only widget dev server
npm run dev:widgets:build # Start only the widget watch build
npm run inspect # Test with MCP Inspector
npm run dev needs no manual build step: a background vite build --watch keeps assets/ fresh, and the server decides per MCP request whether to serve live dev-server modules (HMR) or fully inlined HTML, based on the requesting client (see "Per-Client Widget HTML" below).
Building:
npm run build # Full production build (widgets + server)
npm run build:widgets # Build only widgets
npm run build:server # Build only server
Testing:
npm test # Run all tests
npm run test:server # Run server tests only
npm run test:widgets # Run widget tests only
npm run test:coverage # Run tests with coverage
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.
- 4d ago Changed · +15 lines · +540 tokens per session 64f94f308a0d
- 5d ago First seen · 523 lines · 4,631 tokens per session scan A e18e9c098652
mcp-app-typescript-template AGENTS.md is an instructions file published in the GitHub repository pomerium/mcp-app-typescript-template (20 stars, last pushed today), licensed Apache-2.0. It adds 5,171 tokens to every session, about $0.0259 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 2026-08-30.
Other instructions, from other repositories
skybridge AGENTS.md
AGENTS.md instructions for alpic-ai/skybridge, covering agents guide, what is skybridge, monorepo layout, development and validation.
enquire-mcp AGENTS.md
AGENTS.md instructions for oomkapwn/enquire-mcp, covering agents.md, tl;dr, architecture (5-minute orientation), conventions and typescript.
Local-Codex-Bridge AGENTS.md
Instructions for zoeynine/Local-Codex-Bridge, covering ai agent guidance, project intent, architecture, security and permission boundaries and adapting to another machine.
ThreeBrowserStudio AGENTS.md
AGENTS.md instructions for SamG-Coder/ThreeBrowserStudio: ThreeBrowser Studio is an LLM-first authoring runtime. MCP is the editor and the native WebGPU window is the shared live viewport. Preserve that product shape: do not grow a conventional inspector-heavy browser UI.
sdk CLAUDE.md
Claude Code instructions for WaniWani-AI/sdk, covering waniwani sdk, public api tiers, oss (no api key required), free tier (one env var: waniwaniapikey) and internal (not part of the public api).
PatchWarden AGENTS.md
AGENTS.md instructions for jiezeng2004-design/PatchWarden, covering patchwarden agent rules, commands, safety contracts, changes and release and codex memory.