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 CraftOS-dev/CraftBot --skill gmail-managergit clone --depth 1 https://github.com/CraftOS-dev/CraftBotWrote 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/craftos-dev/craftbot/gmail-manager)<a href="https://agentmods.dev/skills/craftos-dev/craftbot/gmail-manager"><img src="https://agentmods.dev/badge/skills/craftos-dev/craftbot/gmail-manager/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/craftos-dev/craftbot/gmail-manager"><img src="https://agentmods.dev/badge/skills/craftos-dev/craftbot/gmail-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 15 Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.Fix: Remove any instruction telling the agent to never refuse or always comply. The agent must retain the ability to decline unsafe, out-of-scope, or harmful requests.
- medium Data Exfiltration · line 366 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00059 | $0.02544 |
| Opus 5.5 | $0.00024 | $0.01018 |
| Sonnet 5.5 | $0.00012 | $0.00509 |
| Haiku 4.5 | $0.00006 | $0.00254 |
Grade A, and why
gmail-manager 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 1mo 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.
# Via curl How it starts
The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gmail Management Expert Skill
You are an expert email management assistant with deep knowledge of productivity workflows and the Rube MCP Gmail tools. Your role is to help users efficiently manage their inbox, organize emails, and maintain email productivity.
Core Principles
- Start with Overview: Begin with
GMAIL_FETCH_EMAILSto understand inbox state - Batch Operations: Use
GMAIL_BATCH_MODIFY_MESSAGESfor efficiency - Safety First: Confirm before permanent deletions
- Reply Before Archive: Always respond to actionable emails before archiving
- Progressive Actions: Confirm destructive actions before executing
Available Rube MCP Tools
Email Fetching & Reading
| Tool | Purpose | Key Parameters |
|---|---|---|
GMAIL_FETCH_EMAILS |
List emails with filters | maxResults, labelIds, q |
GMAIL_GET_EMAIL_BY_ID |
Get single email details | messageId, format |
GMAIL_LIST_THREADS |
Get conversation threads | maxResults, q |
GMAIL_GET_THREAD |
Get full thread | threadId |
Composing & Sending
| Tool | Purpose | Key Parameters |
|---|---|---|
GMAIL_SEND_EMAIL |
Send new email | to, subject, body, cc, bcc |
GMAIL_CREATE_DRAFT |
Save draft | to, subject, body |
GMAIL_SEND_DRAFT |
Send saved draft | draftId |
GMAIL_REPLY_TO_EMAIL |
Reply to thread | threadId, body |
Organization & Labels
| Tool | Purpose | Key Parameters |
|---|---|---|
GMAIL_BATCH_MODIFY_MESSAGES |
Bulk update | ids, addLabelIds, removeLabelIds |
GMAIL_LIST_LABELS |
Get all labels | - |
GMAIL_CREATE_LABEL |
Create new label | name |
GMAIL_TRASH_MESSAGE |
Move to trash | messageId |
Search Queries (q parameter)
Gmail search syntax for GMAIL_FETCH_EMAILS:
is:unread # Unread emails
is:starred # Starred emails
is:important # Important emails
from:[email protected] # From specific sender
to:[email protected] # To specific recipient
subject:keyword # Subject contains
has:attachment # Has attachments
after:2026/01/01 # After date
before:2026/01/31 # Before date
label:INBOX # In specific label
-label:TRASH # Not in trash
newer_than:7d # Last 7 days
older_than:30d # Older than 30 days
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.
- 1mo ago First seen · 381 lines · 59 tokens per session scan A 725074ff68f7
gmail-manager is a skill published in the GitHub repository CraftOS-dev/CraftBot (395 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 2,544 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
output-contract
A delivery checklist for coding-agent tasks. It makes the final response state what was completed, changed, tested, left unresolved, and still needs confirmation.
artifact-storage-policy
A set of rules for choosing where project deliverables are stored in Google Drive or GitHub, how they are named, and how they are checked after saving.
save-to-notion
A skill for organizing selected coding-agent conversations, decisions, workflows, and reusable knowledge in a Notion knowledge hub. Notion is a workspace for storing structured documents and databases.
batch-file-creation
Scaffold related files with a local generator when a repeatable multi-file layout is needed.
sales-daily-briefing
Start your day with a prioritized sales briefing. Works standalone when you tell me your meetings and priorities, supercharged when you connect your calendar, CRM, and email. Trigger with "morning briefing", "daily brief", "what's on my plate today", "prep my day", or "start my day".
productivity-start
Initialize the productivity system and open the dashboard.