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/ifttt/ifttt-plugins/ifttt-lifecyclegit clone --depth 1 https://github.com/IFTTT/ifttt-pluginsWrote 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/rules/ifttt/ifttt-plugins/ifttt-lifecycle)<a href="https://agentmods.dev/rules/ifttt/ifttt-plugins/ifttt-lifecycle"><img src="https://agentmods.dev/badge/rules/ifttt/ifttt-plugins/ifttt-lifecycle.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 | $0.00491 | $0.00491 |
| Opus 5 | $0.00246 | $0.00246 |
| Sonnet 5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
ifttt-lifecycle 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 3d 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
ifttt-lifecycle:
- Never guess service slugs, trigger/action/query identifiers, or Applet slugs. Always discover them via
search_services,get_steps,my_applets, orget_appletfirst. - If the IFTTT MCP server itself is unauthenticated (tools missing, or every call fails with an auth error), do not read or edit config files such as
.mcp.jsonand do not retry in a loop. Direct the user to Cursor Settings → Tools & MCP → Connect next toifttt, then wait for their confirmation before retrying. create_appletenables the Applet immediately. Summarize what the Applet will do (trigger, actions, and any queries or delay) and get the user's confirmation before creating it.- Confirm with the user before calling
remove_applet(permanent) orrun_action(performs the action for real — messages get sent, devices get switched). - Copy
step_templatefrom discovery results verbatim when building Applet configs; only fill inaccount_idand field values. Do not invent field names. - When a tool reports a service is not connected or an account is offline, do not retry blindly. Call
connect_service, present the returnedconnect_urlorreconnect_urlto the user as a link, wait for them to confirm, then retry the original request. - On
create_appletoredit_appletvalidation errors, fix the specific fields named in the structurederrorsand retry once; never resubmit unchanged input. - Features gated by subscription (e.g. Filter Code requires Pro+): if a tool reports a plan restriction, tell the user which plan is required and link to https://ifttt.com/plans instead of retrying.
- For
set_applet_filter_code, pass a natural-language description of the desired logic — never raw TypeScript/JavaScript. - If an operation on a community Applet responds with
made_it_your_own: true, tell the user a new user-owned copy was created and use the returnedapplet_slugfrom then on.
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.
- 3d ago First seen · 18 lines · 491 tokens per session scan A 970bd931a01f
ifttt-lifecycle is a cursor rule published in the GitHub repository IFTTT/ifttt-plugins (2 stars, last pushed 26d ago), licensed MIT. It adds 491 tokens to every session, about $0.0025 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
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
archcore-files
Enforce MCP-only operations when working with .archcore/ files.
frontend-architecture
Vite + React SPA architecture - directory layout, providers, bundle splitting. Tailwind styling in tailwind.mdc.
dev_workflow
Guide for using Taskmaster to manage task-driven development workflows.
cosmosmith
Cosmosmith project rules adapter.
no-crux-frontmatter
This is a regular rule file that does not have crux: true in its frontmatter. It should be ignored by the CRUX compression hook.