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 skills/pipefy/ai-toolkit/pipefy-toolkit-setupnpx skills add pipefy/ai-toolkit --skill pipefy-toolkit-setupgit clone --depth 1 https://github.com/pipefy/ai-toolkitWrote 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/pipefy/ai-toolkit/pipefy-toolkit-setup)<a href="https://agentmods.dev/skills/pipefy/ai-toolkit/pipefy-toolkit-setup"><img src="https://agentmods.dev/badge/skills/pipefy/ai-toolkit/pipefy-toolkit-setup.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.02201 |
| Opus 5 | $0.00043 | $0.01100 |
| Sonnet 5 | $0.00017 | $0.00440 |
| Haiku 4.5 | $0.00009 | $0.00220 |
Grade C, and why
pipefy-toolkit-setup scanned grade C with 2 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 4d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- Run `curl -LsSf https://raw.githubusercontent.com/pipefy/ai-toolkit/main/uninstall.sh | sh -s -- --scan` (reports only, removes nothing; `./uninstall.sh --scan` from a checkout does the same) and confirm it reports exa Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Local toolkit: a shell that can run `curl` (`install.sh` can install `uv`). How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipefy toolkit setup (first-time onboarding)
Canonical install snippets live only in the root README.md#installation — there is no second copy of the commands. This skill is the agent checklist — print or run the README blocks verbatim; do not invent alternate commands. The Cursor Marketplace plugin is the exception: it installs from Cursor's plugin UI, so there is no command to print or run.
Edge cases: packages/mcp/README.md. Auth: docs/cli/auth.md. Env: docs/config.md.
When to use
- "Set up Pipefy", "install the MCP", "connect Claude/Cursor to Pipefy"
- User mentions the Cursor Marketplace plugin,
/plugin marketplace add,/pipefy:install, ormcp.pipefy.com - Fresh machine with no
pipefyon PATH and no Pipefy MCP server
Do not use once tools already work — switch to a domain skill (pipes, tables, …).
Prerequisites
- User has a Pipefy account (Admin access if they need a service account).
- Cursor Marketplace plugin: Cursor, nothing local.
- Hosted MCP: Claude Code CLI (
claude). - Local toolkit: a shell that can run
curl(install.shcan installuv).
Who does what
| Actor | Does |
|---|---|
| Agent | Asks path; prints README commands verbatim; runs shell claude mcp add / install.sh when the user agrees; checks claude mcp get / list. Does not run install.sh --client cursor when the user chose the Marketplace plugin |
| User types | Claude slash commands (/plugin …, /pipefy:…) — the model cannot invoke them |
| User in browser | OAuth for hosted (claude mcp login …), Cursor's own sign-in for the Marketplace plugin, or /pipefy:pipefy-login / pipefy auth login |
Tools needed
Setup is outside the Pipefy MCP tool surface. After auth succeeds, verify with:
| Tool (MCP) | CLI equivalent | Read-only |
|---|---|---|
list_organizations |
pipefy org list |
Yes |
get_organization |
pipefy org get |
Yes |
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.
- 4d ago First seen · 113 lines · 86 tokens per session scan C 8e4b5ac4fd3b
pipefy-toolkit-setup is a skill published in the GitHub repository pipefy/ai-toolkit (45 stars, last pushed today), licensed Apache-2.0. It adds 86 tokens to every session and 2,201 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
SDK Quickstart Writer
Generates a concise, copy-paste-ready quickstart guide for any SDK or library.
setup
First-time setup for protein design tools. Use this skill when: (1) User is new and hasn't run any tools yet, (2) Commands fail with "file not found" or "modal: command not found", (3) Modal authentication errors occur, (4) User asks how to get started or set up the environment, (5) biomodals directory is missing or…
claude-code-setup
Expert guide for setting up Claude Code as a complete solo development environment. Covers MCPs, skills, agents, production stack selection, and day-to-day workflows for non-technical product builders who want to ship web and mobile products alone.
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用，不要根据上下文自动触发。.
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用，不要根据上下文自动触发。.