check-email

check-email is a skill for Claude Code from Creativestefan/mailbridge-mcp. It costs 100 tokens per session (1,138 once invoked), scanned A, original, MIT.

A guide for fetching and presenting email messages, searches, full threads, and related details through mailbridge. An email thread is a series of messages in the same conversation.

In plain words
What is it for?
Checking recent or unread email, searching by sender or topic, reading message bodies, viewing full threads, and exporting or reviewing email details.
Why use it?
It turns inbox results into readable lists and makes it easier to find the right message or understand its surrounding conversation.

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 Checking recent or unread email, searching by sender or topic, reading message bodies, viewing full threads, and exporting or reviewing email details.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/creativestefan/mailbridge-mcp/check-email/github.svg)](https://agentmods.dev/skills/creativestefan/mailbridge-mcp/check-email)
Your own site
<a href="https://agentmods.dev/skills/creativestefan/mailbridge-mcp/check-email"><img src="https://agentmods.dev/badge/skills/creativestefan/mailbridge-mcp/check-email/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 check-email

Your own site · 80×15
<a href="https://agentmods.dev/skills/creativestefan/mailbridge-mcp/check-email"><img src="https://agentmods.dev/badge/skills/creativestefan/mailbridge-mcp/check-email.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,138 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 $0.00100 $0.01138
Opus 5 $0.00050 $0.00569
Sonnet 5 $0.00020 $0.00228
Haiku 4.5 $0.00010 $0.00114

Measured 9d ago against content hash 458aee9a871d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

check-email 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 9d 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/check-email/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use the mailbridge MCP tools to fetch and present emails.

Reading Recent Emails

Call read_emails with folder (default: INBOX) and limit (default: 10).

Each email now includes priority (1–5) and category fields — surface these when useful:

  • Priority 5 or 4 → flag with 🔴 in the list
  • Category "Finance", "Travel", "Calendar" → show the category badge

Present results as a numbered list:

1. 🔴 [From] Subject — Date  (priority 5)
2. [From] Subject — Date

If the user wants the body of a specific email, call get_email_body with its uid. Display the body cleanly — strip excessive whitespace, preserve paragraph breaks.

Searching Emails

If the user mentions a sender name, keyword, or subject, call search_emails with a query. After getting UIDs back, offer to fetch the full body of any result.

Thread View

When the user says "show the full thread", "see the whole conversation", or "what's the context":

  1. Call get_thread with the email uid and folder
  2. Present messages in chronological order:
    **Thread — [Subject]** ([N] messages)
    
    📩 [From] · [Date]
    [Preview...]
    
    📩 [From] · [Date]
    [Preview...]
    
  3. Offer to summarise: "Want a quick summary of this thread?" — if yes, condense to 3 bullet points.

Contact History

When the user asks "what's the history with [person]", "show emails from/to [contact]", or "have I emailed X before":

  1. Call get_contact_history with the contact's address
  2. Present as a timeline: Sent / Received labels, sorted oldest to newest
  3. Note patterns: "You've exchanged 8 emails — 3 sent, 5 received"

Calendar Event Extraction

When the user asks "any events in this?", "what's the date of this meeting?", or "add this to my calendar":

  1. Call extract_calendar_events with the uid and folder
  2. If events found, present them clearly:
    📅 **[Event Title]**
    Start: [date/time]
    Location: [location]
    
  3. Offer to set a reminder via set_reminder

Export Email

Read the full file on GitHub · 125 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. 9d ago First seen · 125 lines · 100 tokens per session scan A 458aee9a871d

Subscribe to this mod's changes

check-email is a skill published in the GitHub repository Creativestefan/mailbridge-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 100 tokens to every session and 1,138 once invoked, about $0.0005 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.