track-opens

track-opens is a skill for Claude Code from Creativestefan/mailbridge-mcp. It costs 69 tokens per session (484 once invoked), scanned A, original, MIT.

A guide for checking whether recipients returned an email read receipt, which is an optional confirmation that an email was opened.

In plain words
What is it for?
Requesting a receipt when sending or replying, then checking the inbox for returned confirmations.
Why use it?
It clarifies that no receipt does not prove an email was unread, because the recipient's email app may not support receipts or the recipient may decline.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the mailbridge plugin — 8 skills, 1 MCP server shipped together

Good fit Requesting a receipt when sending or replying, then checking the inbox for returned confirmations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/creativestefan/mailbridge-mcp/track-opens
Install

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.

Any agent
npx skills add Creativestefan/mailbridge-mcp --skill track-opens
Clone the repo
git clone --depth 1 https://github.com/Creativestefan/mailbridge-mcp

Made for: Claude Code.

Or install mailbridge, the plugin that ships this one along with the rest of its 8 skills, 1 MCP server.

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 track-opens

README.md
[![agentmods](https://agentmods.dev/badge/skills/creativestefan/mailbridge-mcp/track-opens.svg)](https://agentmods.dev/skills/creativestefan/mailbridge-mcp/track-opens)
Your own site
<a href="https://agentmods.dev/skills/creativestefan/mailbridge-mcp/track-opens"><img src="https://agentmods.dev/badge/skills/creativestefan/mailbridge-mcp/track-opens.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 484 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00069 $0.00484
Opus 5 $0.00034 $0.00242
Sonnet 5 $0.00014 $0.00097
Haiku 4.5 $0.00007 $0.00048

Measured 7d ago against content hash 14c6eee46f1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

track-opens 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 7d 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.

skills/track-opens/SKILL.md · 43 lines

What it actually says

Use the mailbridge MCP read-receipt tools to track whether sent emails have been opened.

How It Works (and its honest limits)

Mailbridge uses read-receipt headers (RFC 8098 / MDN), not tracking pixels. When you send with a receipt requested, the recipient's email app may prompt them to confirm they read it. If they agree, their app emails back a machine-readable confirmation, which Mailbridge detects by scanning the inbox.

Always set expectations clearly — never imply this is reliable like a messaging "read" tick:

  • It only works if the recipient's client supports receipts and they choose to send one.
  • Many clients (notably Gmail web) ignore the request entirely.
  • No receipt does NOT mean the email was unread. Say this explicitly whenever reporting an "awaiting" status.

Requesting a Receipt When Sending

When the user wants to track an email, pass request_receipt: true to send_email or reply_to_email (see the send-email skill). Confirm with the honesty caveat above.

Checking Opens

When the user asks whether an email was opened:

  1. Call check_email_opens (optional folder, default INBOX). It scans for new confirmations, updates the local record, and returns a summary.
  2. Present results plainly:
    ✅ Opened: "Subject" — by [email protected] at [time]
    … Awaiting: "Subject" — sent to [email protected] on [date]
    
  3. For anything still awaiting, add: "No confirmation yet — but remember, that doesn't necessarily mean it hasn't been read."

To show current status without re-scanning the inbox, call list_tracked_emails.

No Account Connected

If any tool returns "No email account connected", offer to call open_setup.

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. 7d ago First seen · 43 lines · 69 tokens per session scan A 14c6eee46f1e

Subscribe to this mod's changes

track-opens is a skill published in the GitHub repository Creativestefan/mailbridge-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 484 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens