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-statusgit 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-status)<a href="https://agentmods.dev/skills/zapier/zapier-mcp/zapier-status"><img src="https://agentmods.dev/badge/skills/zapier/zapier-mcp/zapier-status/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-status"><img src="https://agentmods.dev/badge/skills/zapier/zapier-mcp/zapier-status.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00066 | $0.01589 |
| Opus 5 | $0.00033 | $0.00794 |
| Sonnet 5 | $0.00013 | $0.00318 |
| Haiku 4.5 | $0.00007 | $0.00159 |
Grade A, and why
zapier-status 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 11d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zapier status
Three modes for monitoring and maintaining a Zapier MCP setup. Determine the mode from context, or ask if unclear.
For how the Zapier MCP server itself works, see docs.zapier.com/mcp.
Mode 1: Health check
Trigger: "check my tools", "zapier status", "is everything working?", or any general status inquiry.
A quick dashboard view of the current state.
Steps
-
Inspect the available Zapier MCP tools. The exact surface depends on the server's configuration — some servers expose meta-tools that report the action inventory, others expose each configured action as its own named tool. Use whichever signal is available.
-
If no Zapier tools are available: report the connection status and suggest running zapier-onboard.
-
If tools are available, build a summary by grouping them by app:
For each app, show:
- App name
- Number of actions
- Action types (infer read vs write from names: find/search/get/list = read, send/create/update/add = write)
- Quick status: working / needs auth / error
Format as a dashboard:
Zapier MCP status
=================
Server: connected
Total actions: 14 across 5 apps
Slack 3 actions (2 read, 1 write) ✓ working
Gmail 3 actions (1 read, 2 write) ✓ working
Google Cal 2 actions (1 read, 1 write) ✓ working
Jira 3 actions (2 read, 1 write) ✓ working
Google Docs 2 actions (1 read, 1 write) ✓ working
-
If any actions appear broken (based on recent errors or auth issues), flag them.
-
End with: "Everything looks good." or "Found [N] issues. Want me to diagnose them?"
Mode 2: Audit
Trigger: "audit my setup", "clean up my tools", "find duplicates", "what should I remove?"
Find inefficiencies: duplicate actions, unused tools, conflicts with native MCP servers.
Steps
-
Get the full inventory by inspecting the available Zapier MCP tools.
-
Check for duplicates within Zapier MCP:
- Multiple actions for the same app that do similar things (e.g., both a "find message" and a "search messages" Slack action)
- Recommend removing the less useful one
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.
- 11d ago First seen · 148 lines · 66 tokens per session scan A 9a1dd67ed0c0
zapier-status is a skill published in the GitHub repository zapier/zapier-mcp (405 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 1,589 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 2026-08-30.
Other skills, from other repositories
codebase-navigator
Deep structural codebase comprehension, AST dependency graph traversal, symbol caller/callee tracing, and monorepo navigation strategies for massive codebases.
root-cause-analysis
Hyper-scale root cause analysis (RCA), bisection, call-tree backtracking, and automated surgical remediation across massive million-file enterprise repositories.
performance-optimization
Profile systems, identify bottlenecks, optimize code and infrastructure for speed, throughput, and resource efficiency.
diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
postmortem
Auto-generates a structured postmortem from a completed campaign. Reads the campaign file, telemetry logs, and feature ledger. Produces a documented analysis of what broke, what the safety systems caught, and what patterns emerged. Can also be invoked manually for any incident.
systematic-debugging
4-phase root cause analysis: observe, hypothesize, verify, fix. Enforces investigation before any code changes. Emergency stop after 2 failed fixes. Prevents shotgun debugging and fix cascades.