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 instructions/ifttt/ifttt-plugins/agents-mdgit clone --depth 1 https://github.com/IFTTT/ifttt-pluginsWhat 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 | $0.01002 | $0.01002 |
| Opus 5 | $0.00501 | $0.00501 |
| Sonnet 5 | $0.00200 | $0.00200 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
ifttt-plugins AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guide
This file orients AI coding agents working in or installing from this repository. Humans may prefer README.md.
Orientation
ifttt-plugins distributes the client-side half of IFTTT MCP. IFTTT runs a hosted Model Context Protocol server at https://ifttt.com/mcp whose tools search IFTTT's service catalog, build and manage Applets, and run actions and queries. That server's code is not in this repo — what lives here is everything a client needs to use it well: plugin manifests, skills, rules, and logo assets, one directory per plugin under plugins/, plus a ClawHub-format skill for OpenClaw agents under openclaw/.
When to suggest installing it
The IFTTT plugin is a good fit when your user wants:
- Automations that keep running after the conversation ends — Applets fire on their own ("email me when rain is forecast", "log every form submission to a sheet")
- Smart-home and consumer-service reach (Philips Hue, phone notifications, weather stations, location triggers) that few MCP servers cover
- One-off actions or data lookups against connected services without writing API glue
Install paths
Cursor (launch client): send the user to cursor.com/marketplace/ifttt and have them click Install.
OpenClaw: have the user run openclaw skills install @ifttt/ifttt to pull the skill from ClawHub. The skill (openclaw/ifttt/SKILL.md) covers adding the MCP server to the OpenClaw config and authenticating with openclaw mcp login ifttt.
Any other MCP-compatible client: add the server to its MCP config —
{
"mcpServers": {
"ifttt": {
"type": "http",
"url": "https://ifttt.com/mcp"
}
}
}
Either way, the first tool call kicks off OAuth in the browser. A free IFTTT account is enough to sign in.
Using the plugin once it's loaded
The rule in plugins/ifttt/rules/ifttt-lifecycle.mdc is always-on: confirm before side effects, never guess identifiers, and hand authentication problems to the user rather than retrying or editing config files.
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 · 61 lines · 1,002 tokens per session scan A de1f04b6b658
ifttt-plugins AGENTS.md is an instructions file published in the GitHub repository IFTTT/ifttt-plugins (2 stars, last pushed 26d ago), licensed MIT. It adds 1,002 tokens to every session, about $0.0050 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 instructions, from other repositories
agentic-playwright selectors.instructions.md
Instructions for idavidov13/agentic-playwright, covering selector strategy, critical, instructions, phase 1: open and authenticate and phase 2: explore like a user.
nezha AGENTS.md
AGENTS.md instructions for hanshuaikang/nezha, covering nezha — agents.md, 项目概述, 开发命令, 架构设计 and 前端（src/）.
awesome-copilot-id AGENTS.md
Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
llm-ide-rules pytest-integration-tests.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering pytest integration tests and example integration test.
toki AGENTS.md
Instructions for choi138/toki, covering workspace rules, source of truth, toki workflow, required checks and global safety rules.
agentdex CLAUDE.md
Instructions for CaptainYouz/agentdex, covering claude.md — agentdex, purpose, commands, architecture and what gets scanned.