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/xkloveme/cloud-mcp/agents-mdgit clone --depth 1 https://github.com/xkloveme/cloud-mcpWrote 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/xkloveme/cloud-mcp/agents-md)<a href="https://agentmods.dev/instructions/xkloveme/cloud-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/xkloveme/cloud-mcp/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 | $0.02314 | $0.02314 |
| Opus 5 | $0.01157 | $0.01157 |
| Sonnet 5 | $0.00463 | $0.00463 |
| Haiku 4.5 | $0.00231 | $0.00231 |
Grade A, and why
cloud-mcp 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
MCP App template: React widgets + Python MCP server. Build once, run on Claude, ChatGPT, VS Code, Goose, and other MCP hosts.
Quick Start (Follow These Steps)
1. Setup and Verify
./setup.sh # Installs deps, builds, runs tests — must pass before continuing
2. Understand the Framework
Read in this order:
README.md— What MCP Apps are, why this template existsdocs/widget-development.md— Hook APIs and widget patterns
3. Review Examples (By Complexity)
Start with simpler examples and progress to advanced ones as needed:
| Complexity | Widget | Description | Key Concepts |
|---|---|---|---|
| Beginner | list |
Simple list display | Basic props, theme support |
| Beginner | qr |
QR code generator | Single input, canvas rendering |
| Intermediate | carousel |
Image slideshow | State management, navigation |
| Intermediate | gallery |
Image grid | Grid layout, responsive design |
| Intermediate | dashboard |
Stats cards | Multiple data types, layout |
| Advanced | scenario-modeler |
Interactive charts | Chart.js, complex data |
| Advanced | solar-system |
3D visualization | Three.js, animation loops |
| Advanced | map |
Interactive maps | External APIs (Leaflet), geocoding |
Recommended starting point: Examine the carousel widget:
- Frontend:
src/carousel/index.tsx(entry) +src/carousel/App.tsx(component) - Server:
server/widgets/carousel.py— exportsWIDGET,INPUT_MODEL,handle()
4. Create Your App
./create_new_app.sh --name my_app # Start fresh
./create_new_app.sh --name my_app --keep carousel # Keep carousel as reference
Verify tests still pass after running the script.
5. Development Loop
For each widget you build:
# 1. Create src/my-widget/index.tsx + src/my-widget/App.tsx
# 2. Create server/widgets/my_widget.py (auto-discovered)
# 3. Build and test:
pnpm run build && pnpm run test
# 4. Visual verification:
pnpm run ui-test --tool show_my_widget
# 5. Check screenshot: /tmp/ui-test/screenshot.png
# 6. Iterate until tests pass and widget renders correctly
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 First seen · 272 lines · 2,314 tokens per session scan A 38443db778a8
cloud-mcp AGENTS.md is an instructions file published in the GitHub repository xkloveme/cloud-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 2,314 tokens to every session, about $0.0116 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 2026-08-31.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.