What is event-driven-gmail-watches?

A set of temporary Gmail email watches for sending messages and waiting for matching replies.

Use it to send an email and wait for replies, watch an existing thread or correspondent, handle multiple replies, and close the watch when finished.

It avoids repeatedly checking the inbox and ensures replies are matched to the correct conversation or people.

event-driven-gmail-watches — Skill for Claude Code and Codex by dudu11

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 dudu1111685/hermes_mcps --skill event-driven-gmail-watches

Clone the repo

git clone --depth 1 https://github.com/dudu1111685/hermes_mcps

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dudu1111685/hermes_mcps/event-driven-gmail-watches/github.svg)](https://agentmods.dev/skills/dudu1111685/hermes_mcps/event-driven-gmail-watches)

Your own site

<a href="https://agentmods.dev/skills/dudu1111685/hermes_mcps/event-driven-gmail-watches"><img src="https://agentmods.dev/badge/skills/dudu1111685/hermes_mcps/event-driven-gmail-watches/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dudu1111685/hermes_mcps/event-driven-gmail-watches"><img src="https://agentmods.dev/badge/skills/dudu1111685/hermes_mcps/event-driven-gmail-watches.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 644 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.

Model	Per session	Once invoked
Fable 5.1	$0.00025	$0.00644
Opus 5	$0.00013	$0.00322
Sonnet 5	$0.00005	$0.00129
Haiku 4.5	$0.00003	$0.00064

Measured 10d ago against content hash d98b50bed997, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

event-driven-gmail-watches 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 10d 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/event-driven-gmail-watches/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Event-Driven Gmail Watches

Use the gmail_watch MCP for temporary Gmail workflows without minute-level inbox polling.

Modes

Send only: gmail_send — no watch.
Send and wait: gmail_send_and_watch — creates the logical watch before sending, then binds it to Gmail's returned thread ID.
Watch only: gmail_watch — sends nothing.
Stop: gmail_close_watch — closes only the logical watch; it does not call Gmail users.stop.

Matching

Choose one boundary:

matchMode=thread + exact gmailThreadId: only that Gmail thread.
matchMode=correspondent + exact email addresses and direction=from|to|either: messages involving those addresses, including new threads.

Never match by display name alone. When both thread and correspondent context exist, the thread is the hard boundary.

Multi-message behavior

A watch stays active after every matching email. People may reply in several messages. The wake event includes watch_control with the exact gmail_close_watch call. Continue listening by doing nothing; close only when the sender appears finished and the objective is clear. Do not leave completed watches running.

Accounts

Each MCP instance is pinned to one existing authenticated gws account through GMAIL_GWS_XDG_CONFIG_HOME and GMAIL_ACCOUNT_ID. Always verify gmail_profile before first use on a new deployment. Account mismatches fail closed.

Infrastructure

The mailbox-level Gmail users.watch and Pub/Sub subscription are persistent infrastructure. The worker maintains the Gmail History cursor and renewal state in GMAIL_WATCH_STORE. Logical watch closure never stops the mailbox-level watch.

Required environment:

GMAIL_ACCOUNT_ID=shlomo-primary
GMAIL_GWS_BIN=/home/user/.npm-global/bin/gws
GMAIL_GWS_XDG_CONFIG_HOME=/home/user/.config   # omit for default account
GMAIL_WATCH_STORE=/home/user/.hermes/gmail-watch-state.json
GMAIL_WATCH_DEFAULT_WAKE_URL=http://127.0.0.1:8644/webhooks/gmail-watch
GMAIL_WATCH_DEFAULT_WAKE_SECRET=<route secret>
GMAIL_PUBSUB_PROJECT=<Google Cloud project>
# or GMAIL_PUBSUB_SUBSCRIPTION=projects/.../subscriptions/...
GMAIL_PUBSUB_TOPIC=projects/.../topics/...

Read the full file on GitHub · 64 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.

10d ago First seen · 64 lines · 25 tokens per session scan A d98b50bed997

Subscribe to this mod's changes

event-driven-gmail-watches is a skill published in the GitHub repository dudu1111685/hermes_mcps (5 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 644 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.

Productivity

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…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

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.

pinchtab/pinchtab · 52 tokens

event-driven-gmail-watches