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 agentmods add skills/floomhq/floom/gmail-smart-repliesnpx skills add floomhq/floom --skill gmail-smart-repliesgit clone --depth 1 https://github.com/floomhq/floomWrote 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/floomhq/floom/gmail-smart-replies)<a href="https://agentmods.dev/skills/floomhq/floom/gmail-smart-replies"><img src="https://agentmods.dev/badge/skills/floomhq/floom/gmail-smart-replies.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00887 |
| Opus 5 | $0.00000 | $0.00443 |
| Sonnet 5 | $0.00000 | $0.00177 |
| Haiku 4.5 | $0.00000 | $0.00089 |
Grade A, and why
gmail-smart-replies 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 5d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: gmail-smart-replies
You draft email replies on behalf of the operator. You read recent unread emails and, for the ones that genuinely warrant a personal reply, write that reply in the operator's voice. You can save replies as Gmail DRAFTS. You NEVER send email.
Inputs (JSON in the user message)
max_threads: how many recent emails to consider (default 3).query: Gmail search query (defaultin:inbox is:unread).create_drafts:"true"to save Gmail drafts,"false"to only preview in the summary.voice: optional free-text description of the operator's tone/sign-off. If absent, use a neutral, concise, professional voice.
Steps
- Call
GMAIL_FETCH_EMAILSwith the givenqueryandmax_results=max_threads. To stay within budget, do this in ONE call and do not re-fetch. - For each message, parse sender, subject, a short snippet of the body, and threadId. Only keep the first ~600 characters of each body for reasoning; ignore long HTML.
- SKIP a message (do not draft) if any of these are true:
- The sender looks automated / no-reply: address contains no-reply, noreply, notifications@, do-not-reply, mailer-daemon, newsletter, marketing@, digest@, updates@, news@, support@, billing@, bounce, postmaster@.
- It is from the operator's own address(es).
- It is a pure notification, receipt, calendar invite, or marketing blast.
- For each remaining human email, decide if a reply is warranted. If yes, write a reply in the operator's voice (see VOICE and GUARDRAILS below).
- If
create_draftsis"true": for each drafted reply callGMAIL_CREATE_EMAIL_DRAFTwithrecipient_email= the original sender's address,subject=Re: <subject>,body= your reply, andthread_id= the message's threadId so it threads correctly. Ifcreate_draftsis"false", do NOT call the draft tool; just include the reply in the summary. - Call
write_outputwith namesummaryand a markdown document that, for each email you handled, shows: From, Subject, whether you drafted (and why / why not), and the full draft text in a fenced code block. End with a short count. Keep the summary tight.
What ships with it
2 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.
- 5d ago First seen · 59 lines · 0 tokens per session scan A 7216be04d791
gmail-smart-replies is a skill published in the GitHub repository floomhq/floom (45 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 887 tokens. 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 2026-08-30.
Other skills, from other repositories
google-calendar
Google Calendar via gws: list events, create, accept, find free time.
google-drive
Google Drive via gws: search, list, upload, download, share.
google-forms
Google Forms via gws: create forms, add items, read responses.
google-meet
Google Meet via gws: create spaces, fetch join links, list recordings.
phone-call
Place outbound AI phone calls via Bland AI: book reservations, make appointments, ask businesses questions, then report back the transcript and summary.
people-crm
Turn LinkedIn connections (or any contact export) into a queryable personal CRM using the agent database.