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.
npx skills add sasha-id/email-mcp --skill email-managergit clone --depth 1 https://github.com/sasha-id/email-mcpWrote 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.
[](https://agentmods.dev/skills/sasha-id/email-mcp/email-manager)<a href="https://agentmods.dev/skills/sasha-id/email-mcp/email-manager"><img src="https://agentmods.dev/badge/skills/sasha-id/email-mcp/email-manager/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.
<a href="https://agentmods.dev/skills/sasha-id/email-mcp/email-manager"><img src="https://agentmods.dev/badge/skills/sasha-id/email-mcp/email-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00052 | $0.00717 |
| Opus 5.5 | $0.00021 | $0.00287 |
| Sonnet 5.5 | $0.00010 | $0.00143 |
| Haiku 4.5 | $0.00005 | $0.00072 |
Grade A, and why
email-manager 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Email Manager
Orchestrates the email_* MCP tools (email-mcp server). All tools are
account-scoped; message identity is {account, mailbox, uid}.
Ground rules
- Start with
email_list_accountswhen account names are not already known in this conversation. Never guess account names. - Confirm before sending. Show the user recipient(s), subject, and body
before calling
email_send. Same foremail_deletewithpermanent: true— that one is irreversible. Trash-deletes, flag changes, and moves do not need confirmation. - Batch mutations. Collect uids from
email_search, then issue ONEemail_mark/email_move/email_deletecall withuids: [...]— never one call per message. - M365 auth expiry. If a tool fails with "run email_authenticate", call
email_authenticatefor that account, give the user the URL + code, and retry the original call after they confirm login (check with anotheremail_authenticatecall). - Keep output small. Default search limit is 20; raise it only when the
user asks. Use
email_readon selected uids, not on whole result lists.
Workflows
Cross-account triage ("anything new?", "check my email")
email_list_accountsemail_searchper account in parallel with{ seen: false }- Summarize per account: count + one line per notable message (sender, subject). Flag anything urgent-looking.
Read / summarize a thread
email_searchwithsubject/fromto find the messagesemail_readeach relevant uid (newest first, stop when context suffices)- Synthesize; offer to reply.
Reply in-thread
- Locate the message (
email_search, noteaccount,mailbox,uid) - Draft the reply body; show the user
- On approval:
email_sendwithreplyTo: { mailbox, uid }— recipients and "Re:" subject default from the original; threading headers are set automatically.
Bulk archive/cleanup ("archive all newsletters from X")
email_searchwithfrom/subjectfilters (raiselimitif needed)- Show the user the matching list briefly
email_list_foldersto find the archive/target folder- One
email_movewith all uids.
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 · 65 lines · 52 tokens per session scan A 4807c939b07e
email-manager is a skill published in the GitHub repository sasha-id/email-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 717 once invoked, about $0.0002 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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.