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 gerodp/hermes-productivity-skills --skill emailopsgit clone --depth 1 https://github.com/gerodp/hermes-productivity-skillsWrote 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/gerodp/hermes-productivity-skills/emailops)<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.
<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>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 | $0.00027 | $0.03366 |
| Opus 5 | $0.00014 | $0.01683 |
| Sonnet 5 | $0.00005 | $0.00673 |
| Haiku 4.5 | $0.00003 | $0.00337 |
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.
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
emailops-clionPATH(emailops-cli --versionto verify). It is built from the EmailOps repo with theclicargo feature; symlink the built binary into~/.local/binif needed.- An EmailOps data directory with at least one configured account. Confirm
with
doctorbefore 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.
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.
- 11d ago First seen · 271 lines · 27 tokens per session scan A 5cd0ec39b102
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.
Other skills, from other repositories
reflect
Use Recall Reflect to review AI coding workflow history as a conversation-first timeline and discuss observed patterns before changing behavior. Trigger when the user asks to reflect on a project, review AI coding workflow, inspect workflow friction, discuss repeated corrections, review handoffs, or explore possible…
anyr
Use when reading, searching, creating, or updating Anytype documents (objects, spaces, types, properties, files, chats) from the command line with the configured anyr CLI, including JSON output patterns for scripting.
session-review
When ending a work session and wanting to capture what was accomplished, what was learned, and what to do next. Use when the user says "session review," "what did we do," "wrap up," "summarize session," "weekly review," "retrospective," "what happened today," "debrief," or at natural session endings. Reviews the…
vrchat-group-queries
VRChat groups: announcements, join/leave/peek.
emoji-notes
A local notes system for assigning personal names and aliases to custom or built-in emoji. It can match spoken descriptions, including noisy speech-to-text input, to an emoji ID before sending the emoji.
day-log
Quick timestamped log entry — no conversation, just capture.