emailops

emailops is a skill for Claude Code, Codex from gerodp/hermes-productivity-skills. It costs 27 tokens per session (3,366 once invoked), scanned A, original, MIT.

A command-line interface for reading, searching, discussing, drafting, composing, and sending email from a local EmailOps mailbox. EmailOps is a local email client whose messages are stored in SQLite, with local AI available for chat, classification, and search.

In plain words
What is it for?
Use it to find messages, ask questions about your mailbox, create drafts, send email, and connect Gmail or Outlook accounts through OAuth.
Why use it?
It lets an agent work with email without opening the desktop app and provides one predictable JSON response format for success and failure.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to find messages, ask questions about your mailbox, create drafts, send email, and connect Gmail or Outlook accounts through OAuth.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gerodp/hermes-productivity-skills/emailops
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 gerodp/hermes-productivity-skills --skill emailops
Clone the repo
git clone --depth 1 https://github.com/gerodp/hermes-productivity-skills

Made for: Claude Code, Codex.

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 emailops

README.md
[![agentmods](https://agentmods.dev/badge/skills/gerodp/hermes-productivity-skills/emailops/github.svg)](https://agentmods.dev/skills/gerodp/hermes-productivity-skills/emailops)
Your own site
<a href="https://agentmods.dev/skills/gerodp/hermes-productivity-skills/emailops"><img src="https://agentmods.dev/badge/skills/gerodp/hermes-productivity-skills/emailops/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 emailops

Your own site · 80×15
<a href="https://agentmods.dev/skills/gerodp/hermes-productivity-skills/emailops"><img src="https://agentmods.dev/badge/skills/gerodp/hermes-productivity-skills/emailops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,366 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 $0.00027 $0.03366
Opus 5 $0.00014 $0.01683
Sonnet 5 $0.00005 $0.00673
Haiku 4.5 $0.00003 $0.00337

Measured 11d ago against content hash 5cd0ec39b102, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

emailops 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 11d 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.

email/emailops/SKILL.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EmailOps CLI

emailops-cli is the headless front-end for EmailOps, a privacy-first, AI-native email client. AI runs locally by default (embedded llama.cpp); email data lives in a local SQLite database. This skill lets the agent read, search, chat with, and compose / draft / send mail without opening the desktop app.

It complements the himalaya skill: Himalaya speaks raw IMAP/SMTP, while emailops-cli adds Gmail/Outlook OAuth accounts plus local AI — semantic chat over your mail, classification, and embeddings.

The agent contract: always pass --json

Every command supports --json, which prints exactly one stable envelope to stdout (logs always go to stderr). Parse this single shape regardless of success or failure — never scrape the human-readable output:

{ "ok": true,  "data": { /* result */ }, "error": null }                                  // success
{ "ok": false, "data": null, "error": { "code": "not_found", "params": {}, "message": "" } } // failure

Add --quiet to suppress the stderr app-log stream when you only want the envelope.

Exit codes (branch on these, not on text)

Code Meaning Code Meaning
0 ok 5 network / sync
2 invalid input 6 AI
3 not found 130 cancelled
4 auth 1 otherwise

Prerequisites

  1. emailops-cli on PATH (emailops-cli --version to verify). It is built from the EmailOps repo with the cli cargo feature; symlink the built binary into ~/.local/bin if needed.
  2. An EmailOps data directory with at least one configured account. Confirm with doctor before anything else.

When to use

Use whenever the user asks about their own email: searching messages, asking "what did X say about Y?", listing accounts, reading a specific message, or checking mailbox health. Also use it to write mail — save or edit a draft, review existing drafts, or send a message. Prefer the cheap read paths (doctor, accounts, emails, show, search) over chat unless the question genuinely needs the local LLM.

Read the full file on GitHub · 271 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. 11d ago First seen · 271 lines · 27 tokens per session scan A 5cd0ec39b102

Subscribe to this mod's changes

emailops is a skill published in the GitHub repository gerodp/hermes-productivity-skills (3 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 3,366 once invoked, about $0.0001 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.