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 desirecore/market --skill mail-operationsgit clone --depth 1 https://github.com/desirecore/marketWrote 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/desirecore/market/mail-operations)<a href="https://agentmods.dev/skills/desirecore/market/mail-operations"><img src="https://agentmods.dev/badge/skills/desirecore/market/mail-operations/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/desirecore/market/mail-operations"><img src="https://agentmods.dev/badge/skills/desirecore/market/mail-operations.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 | $0.00151 | $0.07745 |
| Opus 5.5 | $0.00060 | $0.03098 |
| Sonnet 5.5 | $0.00030 | $0.01549 |
| Haiku 4.5 | $0.00015 | $0.00775 |
Grade A, and why
mail-operations scanned grade A with 1 finding 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 17d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Do not connect to the port directly**: do not `curl` `https://127.0.0.1:62000`. The port is allocated dynamically starting at 62000 (when several DesireCore instances run, 62000 may belong to another instance), and i How it starts
The opening of the file, as written. The whole thing — 476 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mail-operations Skill
L0: One-line Summary
Send and receive email, search, manage labels, and run automation rules via a local REST API; supports Gmail / Outlook / IMAP.
L1: Overview and Use Cases
Capability
mail-operations is a Procedural Skill that operates email systems through DesireCore's local REST API (called via the built-in MailOperations tool). It supports three mailbox types—Gmail (OAuth2), Outlook (MSAL), and IMAP/SMTP (QQ, 163, Yahoo, etc.)—covering send/receive, search, label management, attachment download, draft management, and automation rules.
Use Cases
- The user wants to view the inbox, send, or reply to email
- The user wants to search for specific emails or manage email labels/categories
- The user wants to download attachments or manage drafts
- The user wants to set up auto-reply rules or trigger an Agent to handle email
Core Value
- Unified interface: three mailbox types are operated through a unified API, lowering complexity
- Local and secure: all operations go through the local API; no need to expose credentials
- Smart integration: supports automation rules and Agent-based email handling
L2: Detailed Specification
How to Access the Email Service
Users can reach the email management interface via:
- Click the third icon (folder icon) in the left navigation rail to open the Resource Explorer
- On the Resource Explorer home page, find and click the "Emails" card to enter email management
If a user doesn't know how to open the email page, guide them through the steps above. They can also click "Open Resource Explorer" from the top-right corner of the chat interface, then select the Emails card.
API Basics
- How to call: use the built-in
MailOperationstool. Its parameters arepath(a relative path starting with/api/, with query parameters appended directly to it),method(defaultGET),body(a JSON object), andsave_to(only for attachment downloads, see section 6). The tool locates the local Mail Service and attaches the access credential automatically; the Agent neither needs nor can supply a token. - Path form: the endpoints below omit the
/apiprefix; add it when calling. For example,/imap/messages?email=me%40example.com&limit=20becomespath: "/api/imap/messages?email=me%40example.com&limit=20". The only exception is the health check/ping(no/api). - Do not connect to the port directly: do not
curlhttps://127.0.0.1:62000. The port is allocated dynamically starting at 62000 (when several DesireCore instances run, 62000 may belong to another instance), and in strict capability mode direct requests without the credential always return 401. - Parameter location: GET / DELETE parameters always go in the query string; for POST / PUT follow the tables below. The
emailof endpoints such asmessages/fetch, mark as read/unread, Outlook single-message operations, and IMAP draft send must be in the query string; putting it in the body returns 400Missing email parameter. For/sync, bothproviderandemailmust be in the query string:providerin the body returns 400Invalid provider, andemailalone in the body raises no parameter error but the sync does not take effect. - Content-Type:
application/json(set automatically by the tool whenbodyis passed) - Response format: success
{"code": 1, "msg": "Success", "result": ...}, failure{"code": 0, "msg": "error message"}; some errors also carry a stable error code fielderror(e.g.smtp_unverified)
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 17d ago Changed · +9 lines ff5839b3f315
- 24d ago Changed · +41 lines 5641ed24576c
- 1mo ago Changed · +1 lines e697a19b4abc
- 1mo ago First seen · 425 lines · 151 tokens per session scan A fdc44f9e9cac
mail-operations is a skill published in the GitHub repository desirecore/market (2 stars, last pushed 2d ago), licensed MIT. It adds 151 tokens to every session and 7,745 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
mailbox
A command-line email tool for reading, searching, sending, and managing messages in Gmail, QQ, 163, Outlook, and other IMAP/SMTP accounts.
Run the external email CLI through exec for real IMAP/SMTP/Notmuch mailboxes. Use when the user explicitly wants a real terminal email workflow instead of the built-in benchmark email surfaces.
imap-smtp-email
Read, search, and manage email via IMAP protocol. Send email via SMTP. Supports Gmail, Outlook, 163.com, 126.com, QQ Mail, and any standard IMAP/SMTP server with multi-account support.
c-email
Read, send, search, and label email via gog (Gmail CLI) or himalaya (IMAP). Supports inbox management, drafting replies, thread viewing, and label/folder operations across Gmail and standard IMAP accounts.
email-manager
Read, search, send, and manage email via IMAP/SMTP or API (Gmail, Outlook).
inbox-review
Morning inbox workflow -- multi-account scan, thread grouping, priority classification, draft replies.