apple-rag-mcp: Instructions file for Codex

AGENTS.md

apple-rag-mcp AGENTS.md is an instructions file for Codex, OpenCode from BingoWon/apple-rag-mcp. It costs 1,060 tokens per session, scanned A, original, MIT.

Project instructions for the apple-rag-mcp service, including its deployment and release process. They explain how changes reach a Cloudflare Worker through GitHub and when package versions must be updated.

In plain words
What is it for?
Following the repository's commit, push, version-bump, release, deployment, and MCP compatibility procedures.
Why use it?
They prevent changes from being left only on a developer's computer or deployed through the wrong process. They also keep release versions and compatibility work aligned with the project's rules.

Instructions file for CodexOpenCode

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

This is BingoWon/apple-rag-mcp's own configuration. It tells Codex and OpenCode how to work on apple-rag-mcp 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 apple-rag-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to BingoWon/apple-rag-mcp. 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/BingoWon/apple-rag-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/BingoWon/apple-rag-mcp

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 apple-rag-mcp AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bingowon/apple-rag-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bingowon/apple-rag-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,060 This file is loaded in full into every session.
When invoked 1,060 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 $0.01060 $0.01060
Opus 5.5 $0.00424 $0.00424
Sonnet 5.5 $0.00212 $0.00212
Haiku 4.5 $0.00106 $0.00106

Measured today against content hash 733f5e5ee860, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

apple-rag-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 today.

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 · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Deployment

This project does not require a manual deployment. Committing to main and pushing to GitHub is the deployment step: Cloudflare Workers automatically pulls that commit and deploys the Worker. Do not run wrangler deploy for a normal code change.

Every code change must therefore be committed to main and pushed to GitHub promptly. A change that exists only in the local working tree is not deployed and does not affect https://mcp.apple-rag.com.

The manual pnpm build && wrangler deploy procedure in ops/README.md is not the normal release path.

Releases

Every code change ships with a release. A change to worker/, src/, skills/, or public/ bumps package.json and server.json to the same new version, and the bump is pushed to main in the same change. CI success on main then creates the vX.Y.Z GitHub release.

  • Patch bump for fixes and small changes; minor bump for new user-facing capabilities.
  • Documentation-only changes may skip the bump.
  • Never push a version that already has a tag; the workflow skips it and no release is created.

MCP Protocol Compatibility

Do not make the production MCP endpoint 2026-07-28-only. Current clients, including Cursor 3.24, still open Streamable HTTP with the legacy initialize handshake. The server must keep legacy: "stateless" in worker/mcp/protocol-handler.ts so those clients work beside the modern per-request protocol.

The full incident, the rejected shortcut, and the compatibility rule are recorded in ops/incidents/2026-10-19-cursor-mcp-protocol.md. Read it before changing protocol negotiation, client installation instructions, or claims about client support.

Responding To User Feedback

  • Work from the verbatim original message. If it was not pasted into the conversation, ask for it before drafting a reply; do not answer a paraphrase.
  • Reply in the language the reporter used.
  • Keep it short, warm, and professional. Thank the reporter, then explain the cause in one or two plain sentences. Skip protocol and implementation detail.
  • Give one concrete next step. For MCP connection issues that step is a reload of the server in the client's MCP settings. Do not tell people to change tokens or configuration.
  • Do not claim a fix is in effect until the production endpoint has actually been checked. A local change is not a fix.
  • When drafting a reply for review, offer two or three short versions instead of one.

Read the full file on GitHub · 69 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. today Changed · +23 tokens per session 733f5e5ee860
  2. yesterday Changed · +29 lines · +406 tokens per session 103928b3c2e6
  3. 2d ago First seen · 40 lines · 631 tokens per session scan A d4399cc11bd7

Subscribe to this mod's changes

apple-rag-mcp AGENTS.md is an instructions file published in the GitHub repository BingoWon/apple-rag-mcp (121 stars, last pushed yesterday), licensed MIT. It adds 1,060 tokens to every session, about $0.0042 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 2026-10-20.

Related

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).

microsoft/vscode · 9,649 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,384 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens