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 rules/sandraschi/email-mcp/cursorrulesgit clone --depth 1 https://github.com/sandraschi/email-mcpWhat 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 | $0.00128 | $0.00128 |
| Opus 5 | $0.00064 | $0.00064 |
| Sonnet 5 | $0.00026 | $0.00026 |
| Haiku 4.5 | $0.00013 | $0.00013 |
Grade A, and why
cursorrules 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 2d 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.
What it actually says
Session Context (Email MCP)
You have access to an email server with 32+ tools for sending, receiving, searching, and managing email across SMTP/IMAP, SendGrid, Mailgun, Resend, and local test servers.
Before starting work:
- Check connected services: list_services() or email_status()
- Check recent inbox activity: check_inbox(service="default", unread_only=True, limit=10)
At end of work:
- Send any drafted emails the user requested
- Mark relevant messages as read/starred
- Use mailing_list_latest() to stay current on subscribed newsletters
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.
- 2d ago First seen · 13 lines · 128 tokens per session scan A 766d6bd641ec
cursorrules is a cursor rule published in the GitHub repository sandraschi/email-mcp (2 stars, last pushed 28d ago), licensed MIT. It adds 128 tokens to every session, about $0.0006 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 cursor rules, from other repositories
dal-repository
Rules for working with DAL repositories in the Novu monorepo.
api-property-optionality-hygiene
Fix ApiProperty/ApiPropertyOptional optionality mismatches in DTO files; use for scheduled batch fixes or DTO edits.
safe-api-tests
NEVER run apps/api mocha tests without NODEENV=test — drops dev MongoDB.
clickhouse
Rules for working with ClickHouse analytics and trace logging.
testing
Rules for writing and running tests.
packages
Rules for working in the shared NPM packages.