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 IFTTT/ifttt-plugins --skill ifttt-build-appletgit 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/skills/ifttt/ifttt-plugins/ifttt-build-applet)<a href="https://agentmods.dev/skills/ifttt/ifttt-plugins/ifttt-build-applet"><img src="https://agentmods.dev/badge/skills/ifttt/ifttt-plugins/ifttt-build-applet/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/ifttt/ifttt-plugins/ifttt-build-applet"><img src="https://agentmods.dev/badge/skills/ifttt/ifttt-plugins/ifttt-build-applet.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00056 | $0.00672 |
| Opus 5 | $0.00028 | $0.00336 |
| Sonnet 5 | $0.00011 | $0.00134 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
ifttt-build-applet 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 10d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build an IFTTT Applet
When to use
- The user describes an automation: "when X happens, do Y"
- The user wants to modify, test, or add logic to an existing Applet
Workflow
- Find the services. Call
search_serviceswith keywords from the user's request to get exact service slugs. Never guess a slug. - Discover the steps. Call
get_stepswith the trigger service and action service(s) to fetch available triggers, queries, and actions with their field definitions, ingredients, and a ready-madestep_template. - Connect missing services. Discovery results include
connectedand aconnect_urlwhen a service isn't connected. Present theconnect_urlto the user, wait for confirmation, then re-run discovery to pick up theiraccount_id. - Fill the templates. Copy
step_templatefrom each chosen step verbatim, then fill inaccount_idand the step's fields. Action and query fields can reference trigger/query ingredients — use them to pass data between steps. - Create. Call
create_appletwithname, an optional but recommendeddescription, thetrigger, andactions(plus optionalqueriesandactions_delayup to 14,145 seconds). The Applet is created and enabled immediately — tell the user this before calling. On success, share the returnedapplet_urlso the user can view it. - Handle validation errors. A failed
create_appletreturns structurederrors. Fix the referenced fields and retry; don't retry unchanged input.
Editing
- Call
get_appletfirst to see the Applet's current configuration, thenedit_appletwith the changed pieces. - Applets can only be edited if the user owns them. Editing a published community Applet the user enabled may create the user's own copy — relay that to the user when it happens.
Filter Code (Pro+ only)
set_applet_filter_codeadds conditional logic between trigger and actions.- Pass a natural-language prompt describing the behavior (e.g. "only run on weekdays") — never pass TypeScript/JavaScript directly; the tool generates the code server-side.
- Pass an empty string to clear existing Filter Code.
- If the response includes
made_it_your_own: true, a new user-owned copy of a community Applet was created — tell the user explicitly and use the newapplet_sluggoing forward.
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.
- 10d ago First seen · 39 lines · 56 tokens per session scan A 6c81b162f2db
ifttt-build-applet is a skill published in the GitHub repository IFTTT/ifttt-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 672 once invoked, about $0.0003 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 skills, from other repositories
jobgpt
Job search automation, auto apply, resume generation, application tracking, salary intelligence, and recruiter outreach using the JobGPT MCP server.
Dispatching Parallel Agents
Concurrent execution of independent subtasks using multi-agent scheduling.
Executing Implementation Plans
Systematic execution of multi-step implementation plans with milestone verification.
Application Form Filler
Fill out job application form fields with context-aware, tailored answers drawn from the candidate's CV and the job description.
telegram-agent
Telegram CLI for AI agents. Use when the user needs to read or search Telegram, send or edit a message, download media, organise Saved Messages, monitor conversations, or automate a Telegram task. Triggers on “check my messages”, “send a message”, “search Telegram”, “read unread”, “listen to chat”, “download from…
drive-wps-ppt
An automation skill for creating and editing presentations in WPS Presentation, a desktop slide-making application, through the WPS automation interface. It also structures project-defense and progress-report content as JSON specifications.