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-onboardgit 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-onboard)<a href="https://agentmods.dev/skills/zapier/zapier-mcp/zapier-onboard"><img src="https://agentmods.dev/badge/skills/zapier/zapier-mcp/zapier-onboard/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-onboard"><img src="https://agentmods.dev/badge/skills/zapier/zapier-mcp/zapier-onboard.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 Agent Snooping · line 179 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
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 | $0.00092 | $0.02382 |
| Opus 5 | $0.00046 | $0.01191 |
| Sonnet 5 | $0.00018 | $0.00476 |
| Haiku 4.5 | $0.00009 | $0.00238 |
Grade A, and why
zapier-onboard 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 12d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zapier onboard
Introduce Zapier MCP, get the user authenticated, then guide them through the appropriate setup flow.
For how the Zapier MCP server itself works, see docs.zapier.com/mcp.
Step 1: Introduction
Start by describing what Zapier MCP can do for the user, then get them authenticated.
Pitch
"Zapier MCP connects your AI assistant to 9,000+ apps — Slack, Gmail, Google Calendar, Jira, Notion, HubSpot, and thousands more. Once set up, you can search across your tools, take actions, and automate workflows, all through natural conversation. It's personalized to your workflow — you pick the apps and actions that matter to you, and your AI learns to use them."
Check connection
Check if any Zapier MCP tools are available:
-
Tools are available: The user is already authenticated. Give a shorter version of the pitch — "You've got Zapier MCP installed and connected. Let me check what you have set up." — then proceed to Step 2.
-
No Zapier tools available at all: The server is installed but needs authentication. First, attempt to authenticate directly in the chat by calling
mcp_authon the Zapier MCP server. If that succeeds, re-check available tools and proceed to Step 2.If
mcp_authfails or is unavailable, fall back to manual instructions based on their client:- In Cursor: "Let's get you connected. Go to Settings > Cursor Settings > Tools & MCP and click Connect next to the Zapier MCP server. You can also press Cmd+Shift+P and search for 'MCP' to get there quickly."
- In Claude Desktop: "Let's get you connected. Go to Customize > Connectors > Zapier and click Connect."
- In other clients: "Let's get you connected. Find the Zapier MCP server in your client's MCP settings and click Connect. This will redirect you to mcp.zapier.com to sign in."
Detect which client is in use from the environment or conversation context. If unclear, give the generic instructions.
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.
- 12d ago First seen · 196 lines · 92 tokens per session scan A 6670bf36edd7
zapier-onboard is a skill published in the GitHub repository zapier/zapier-mcp (405 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 2,382 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
code-quality
This skill should be used when implementing code quality standards, setting up linting/testing/security scans, enforcing coverage thresholds, or establishing CI/CD guardrails.
pr-review
Comprehensive code review for pull requests using parallel multi-agent analysis. Audits CLAUDE.md compliance, checks for bugs, analyzes git history, reviews comments, and filters by confidence score. Use when reviewing a GitHub PR, mentions "code review", "review this PR", or "/code-review".
ralph-loop
Self-diagnosing, self-correcting agent loop for Build phase. Defines DoD checking, inner/outer loop retry logic, circuit breakers, and sentinel health checks.
playwright
Browser automation and end-to-end testing with Playwright. Use when building/testing frontends, automating user workflows, taking screenshots, validating UI state, filling forms, testing across browsers, or mentions "playwright", "E2E test", "browser automation", "screenshot".
enterprise-test-suites
Comprehensive testing matrix spanning Unit, Integration, E2E (Playwright), Contract (Pact), Chaos/Fault-Injection, Mutation, Load/Stress (k6), and Security Fuzz testing.
architecture
This skill should be used when the user asks to "design a system", "architecture", "ADR", "system design", "tech stack", "choose between approaches", "coupling", "service granularity", "blueprint", "component design", "API contract", "schema design", "trade-offs", or discusses "monolith", "microservices", "fitness…