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 zapier/zapier-mcp --skill zapier-demogit clone --depth 1 https://github.com/zapier/zapier-mcpWrote 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/zapier/zapier-mcp/zapier-demo)<a href="https://agentmods.dev/skills/zapier/zapier-mcp/zapier-demo"><img src="https://agentmods.dev/badge/skills/zapier/zapier-mcp/zapier-demo/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/zapier/zapier-mcp/zapier-demo"><img src="https://agentmods.dev/badge/skills/zapier/zapier-mcp/zapier-demo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 182 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00121 | $0.02664 |
| Opus 5.5 | $0.00048 | $0.01066 |
| Sonnet 5.5 | $0.00024 | $0.00533 |
| Haiku 4.5 | $0.00012 | $0.00266 |
Grade A, and why
zapier-demo 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 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.
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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zapier demo
Walk a new user through the smallest possible first win — one app, one read action, one prompt that actually runs. The whole flow should feel quick: a few minutes from "I'm curious" to "oh, that worked."
This is the natural next step after zapier-onboard for users who want to see Zapier work before configuring a full toolkit.
When to use vs. other skills
- zapier-demo (this skill) — one app, one action, immediate demo. Fastest path to "oh, this works."
- zapier-onboard — pitch + connect + diagnose. Run this first if the server isn't connected yet.
- zapier-explore — role-tailored expansion. Run this after demo to set up a full toolkit for the user's role.
- zapier-status — health checks and audits on an existing setup.
If the user says "show me," lean here. If they haven't connected the server yet, route to zapier-onboard first.
Step 1: Confirm the server is connected
Inspect available Zapier MCP tools. If none exist, the server isn't authenticated yet — authenticate first via mcp_auth or the client's MCP settings (same pattern as zapier-onboard's connection step). Don't continue until at least the configuration tools are available.
Once connected, set the tone:
"Let's get one Zapier action working so you can see this in action. We'll pick one app, enable one thing, and try it — should take just a couple minutes."
Step 2: Ask what app to start with
Lead with concrete popular options — most people find it easier to react to a list than to come up with one cold:
"Which app do you want to try first? A few popular ones to pick from:
- Gmail — find or draft emails
- Slack — find messages and ping channels
- Google Sheets — look up rows in a sheet
- Google Calendar — check your schedule
- HubSpot — find contacts and deals
- Jira — look up tickets
- Notion — find pages
Or name something else — Zapier supports 9,000+ apps."
Confirm support and pull app details
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 · 183 lines · 121 tokens per session scan A 11813724c0c9
zapier-demo is a skill published in the GitHub repository zapier/zapier-mcp (449 stars, last pushed 3d ago), licensed MIT. It adds 121 tokens to every session and 2,664 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
learn
Knowledge compiler. Extracts patterns, decisions, and anti-patterns from completed campaigns and evolve cycles, then compiles them into structured wiki pages that integrate with existing knowledge rather than appending isolated files. Implements flush→compile→lint pipeline. Auto-triggered by /postmortem and /evolve…
explain
Explain jig vocabulary and artifacts in plain language. Three modes: term mode defines one lexicon term; artifact mode walks through a spec or ADR and its linked references; passage mode explains pasted jig output. Output is ephemeral (chat-only). Auto-triggers when you say explain this term, walk me through this…
economics
Runtime subject skill payload for economics subject activation.
platform-help
A reference skill for the 1C platform and BSL, the programming language used to build 1C business applications. It helps clarify the platform’s object model, APIs, versions, and compatibility.
calculate-yonsei-graduation-progress
Read the student's authorized Underwood credit-progress table and calculate advisory Yonsei graduation progress from official entry-year, college, and major requirements. Use when a student asks what graduation requirements are complete, what credits or required courses remain, or whether a planned course can fill a…
normalize-yonsei-courses
Query authorized Yonsei Underwood handbook rows directly, then normalize them or fallback screenshot, PDF, spreadsheet, pasted table, export, or JSON into stable course-planning data. Use when course data has Korean or English fields, campus aliases, Korean weekday/time strings, mixed section identifiers, or needs…