openwork-remote-mcp-app-example: Instructions file for Codex

AGENTS.md

openwork-remote-mcp-app-example AGENTS.md is an instructions file for Codex, OpenCode from reachjalil/openwork-remote-mcp-app-example. It costs 664 tokens per session, scanned A, original, MIT.

Instructions for developing and checking OpenWork MCP Apps in a public monorepo, a repository that contains multiple related projects. MCP Apps are applications that connect AI tools with interfaces or services through the MCP standard.

In plain words
What is it for?
Use them when adding or changing examples, shared runtime code, interface elements, test data, browser behavior, or the MCP server, then verify the project with its pnpm commands.
Why use it?
They explain how to start the project, where to edit its apps and shared packages, and which checks must pass before changes are accepted.

Instructions file for CodexOpenCode

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

This is reachjalil/openwork-remote-mcp-app-example's own configuration. It tells Codex and OpenCode how to work on openwork-remote-mcp-app-example 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 openwork-remote-mcp-app-example configures →

Reuse

Borrowing it

Nothing to install: this file belongs to reachjalil/openwork-remote-mcp-app-example. 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/reachjalil/openwork-remote-mcp-app-example/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/reachjalil/openwork-remote-mcp-app-example

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 openwork-remote-mcp-app-example AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/reachjalil/openwork-remote-mcp-app-example/agents-md/github.svg)](https://agentmods.dev/instructions/reachjalil/openwork-remote-mcp-app-example/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/reachjalil/openwork-remote-mcp-app-example/agents-md"><img src="https://agentmods.dev/badge/instructions/reachjalil/openwork-remote-mcp-app-example/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 openwork-remote-mcp-app-example AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/reachjalil/openwork-remote-mcp-app-example/agents-md"><img src="https://agentmods.dev/badge/instructions/reachjalil/openwork-remote-mcp-app-example/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 664 This file is loaded in full into every session.
When invoked 664 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 $0.00664 $0.00664
Opus 5.5 $0.00266 $0.00266
Sonnet 5.5 $0.00133 $0.00133
Haiku 4.5 $0.00066 $0.00066

Measured 2mo ago against content hash 1a24155c316c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openwork-remote-mcp-app-example 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 · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent guide for the OpenWork MCP App examples

This is a public, forkable monorepo of independently authored standard MCP Apps. Agents may add examples, change interfaces, fixtures, and native tools while preserving the protocol and security boundaries below.

Start and verify

pnpm install
pnpm dev
pnpm start:mcp
pnpm verify
  • pnpm dev builds every App and opens the multi-App local host at http://localhost:5173/.
  • pnpm start:mcp exposes the real stateless Streamable HTTP server at http://127.0.0.1:8787/mcp.
  • pnpm verify type-checks, builds all self-contained resources, enforces portability/size limits, and tests tools, resources, UI metadata, gateway calls, and result fields.

Editing surfaces

  • Add or change an App in apps/<example>/src.
  • Share handshake/tool-call logic through packages/mcp-app-runtime.
  • Share UI elements through packages/example-ui.
  • Change deterministic local/server data in fixtures/mock-data.json.
  • Change browser-host behavior in playground.
  • Change the standard MCP server in scripts/mcp-server.mjs.
  • Add generated targets in scripts/build-examples.mjs.
  • Never hand-edit docs; regenerate it with pnpm build and commit source and output together.

Contract invariants

  1. Expose ordinary MCP tools and resources. Do not add an OpenWork-specific HTML manifest, iframe protocol, or wrapper-tool protocol.
  2. Every launch tool attaches one exact resource through _meta.ui.resourceUri; each ui:// URI must be immutable/versioned and readable as text/html;profile=mcp-app.
  3. Apps call only app-visible tools on the MCP server that served their UI.
  4. For OpenWork URL imports, read the exact capability-search and execution tool names from launch structuredContent.serverTools; never guess them or embed an installation ID.
  5. Search and execution use ordinary MCP tools/call and results. Programs remain server-side durable resources; do not reintroduce per-App run_program_* tools.
  6. Preserve authorization, annotations, confirmation requirements, and audit behavior. The UI must never receive credentials or directly contact unrelated MCP servers.
  7. React and Vite are authoring choices. The compiled HTML is the runtime MCP App resource; do not call this React SSR.
  8. Fixture records, credentials, connection IDs, and provider secrets must never enter a compiled resource.
  9. A static URL App must remain useful in launch-only mode or clearly explain that its gateway is unavailable.
  10. Keep OpenWork-generated UI authoring separate. This repo demonstrates external authoring, native MCP Apps, URL import, and capability use—not source submission to OpenWork.

Read the full file on GitHub · 45 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 · 45 lines · 664 tokens per session scan A 1a24155c316c

Subscribe to this mod's changes

openwork-remote-mcp-app-example AGENTS.md is an instructions file published in the GitHub repository reachjalil/openwork-remote-mcp-app-example (0 stars, last pushed 2mo ago), licensed MIT. It adds 664 tokens to every session, about $0.0027 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 2026-08-31.

Related

openwork-remote-mcp-app-example AGENTS.md compared with instructions from other repositories

openwork-remote-mcp-app-example AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
openwork-remote-mcp-app-example AGENTS.mdreachjalil/openwork-remote-mcp-app-exampleInstructions file02mo agoMITA664Codex, 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