What is emailsRboring AGENTS.md?

A project instruction file for emailsRboring-mcp, a macOS service that places a safety and privacy layer in front of Apple Mail tools. It describes the project’s architecture, commands, invariants, and common pitfalls.

Use it when building, testing, or modifying emailsRboring-mcp, especially its Apple Mail connections, tool permissions, routing, and response redaction.

It gives coding agents the project context needed to change the service without breaking its allowlist, routing, or response-redaction rules. An allowlist is a list of explicitly permitted operations.

How ahmadzafar-code/emailsRboring configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to ahmadzafar-code/emailsRboring. 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/ahmadzafar-code/emailsRboring/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/ahmadzafar-code/emailsRboring

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ahmadzafar-code/emailsrboring/agents-md/github.svg)](https://agentmods.dev/instructions/ahmadzafar-code/emailsrboring/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ahmadzafar-code/emailsrboring/agents-md"><img src="https://agentmods.dev/badge/instructions/ahmadzafar-code/emailsrboring/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ahmadzafar-code/emailsrboring/agents-md"><img src="https://agentmods.dev/badge/instructions/ahmadzafar-code/emailsrboring/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,064 This file is loaded in full into every session.

When invoked 1,064 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.

Model	Per session	Once invoked
Fable 5.1	$0.01064	$0.01064
Opus 5.5	$0.00426	$0.00426
Sonnet 5.5	$0.00213	$0.00213
Haiku 4.5	$0.00106	$0.00106

Measured 2mo ago against content hash fb7456c58071, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

emailsRboring 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 · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Briefing for AI coding agents working on emailsRboring-mcp. Humans: start with README.md; this file holds the build/test commands, invariants, and gotchas an agent needs to change the code safely.

What this is

A redacting policy proxy (one MCP server) that fronts two upstream Apple Mail MCP servers and adds the safety layer:

imdinu/apple-mail-mcp (Python) → read/search. Spawned read-only (serve -r).
sweetrb/apple-mail-mcp (TypeScript) → write/organize/send.

The proxy spawns both as stdio child processes, merges their tools behind a fail-closed allowlist, routes calls, and redacts every response. It is macOS-only (Apple Mail).

Architecture (where things live)

File	Responsibility
`src/index.ts`	Entry point. Low-level `Server` + `StdioServerTransport`; `ListTools`/`CallTool` handlers; loads `emailsRboring.config.json`.
`src/upstreams.ts`	Spawns imdinu + sweetrb via `StdioClientTransport`. Reads `EMAILSRBORING_IMDINU_CMD` / `EMAILSRBORING_SWEETRB_ENTRY`.
`src/allowlist.ts`	The fail-closed allowlist + tool-name normalization (`mail_*`) + annotations + `confirm` injection.
`src/router.ts`	Dispatch, send-gate, draft-forcing, id `String()`, attachment-exfil block, untrusted-content fence.
`src/redact.ts`	The single redaction chokepoint (`redactToolResult`): strips `structuredContent`, masks OTPs/codes, truncates at 25k chars.
`verify.py`	22-check end-to-end verification (surface, redaction, send-gate, exfil).

Build / run / verify

npm install
npm run build            # tsc → build/

# the proxy REQUIRES these env vars (see README for what they point at):
export EMAILSRBORING_IMDINU_CMD=/abs/path/to/apple-mail-mcp
export EMAILSRBORING_SWEETRB_ENTRY=/abs/path/to/sweetrb/build/index.js

node build/index.js      # boots; prints "[emailsRboring] ready — 26 tools"
python3 verify.py        # MUST stay 22/22 ALL GREEN before any commit

npm run build must exit 0 with no any introduced; tsconfig.json is strict.

Read the full file on GitHub · 64 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.

2mo ago First seen · 64 lines · 1,064 tokens per session scan A fb7456c58071

Subscribe to this mod's changes

emailsRboring AGENTS.md is an instructions file published in the GitHub repository ahmadzafar-code/emailsRboring (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,064 tokens to every session, about $0.0043 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.

emailsRboring AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
emailsRboring AGENTS.mdahmadzafar-code/emailsRboring	Instructions file	0	4mo ago	MIT	A	1,064	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

emailsRboring: Instructions file for Codex