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-process-designnpx skills add pipefy/ai-toolkit --skill pipefy-process-designgit 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-process-design)<a href="https://agentmods.dev/skills/pipefy/ai-toolkit/pipefy-process-design"><img src="https://agentmods.dev/badge/skills/pipefy/ai-toolkit/pipefy-process-design.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 | $0.00089 | $0.01070 |
| Opus 5 | $0.00044 | $0.00535 |
| Sonnet 5 | $0.00018 | $0.00214 |
| Haiku 4.5 | $0.00009 | $0.00107 |
Grade A, and why
pipefy-process-design 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 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.
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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipefy Process Design
This skill activates when the user wants consulting help to design a process — not when they want you to build one. If the user already knows what they want (gave you phases, fields, a spec, or a clear use case), do not use this skill. Execute directly.
When to use vs when to execute
| Signal | Response |
|---|---|
| "Help me design a process for X" | Use this skill — consulting mode. |
| "What's the best structure for Y?" | Use this skill — architecture guidance. |
| "Create a pipe for X" | Skip this skill — route via pipefy-building, then the domain skill. |
| User provides phases, fields, or a spec | Skip this skill — the spec IS the plan. Route via pipefy-building, then build. |
Prerequisites
- Understand the user's industry and use case before advising structure.
- Always search for existing pipes in the org before recommending a new one (
search_pipes).
Discovery phase
-
Research existing org structure:
MCP:
search_pipes name=""(empty search returns all visible pipes) MCP:get_organization organization_id=<id> -
Understand the process intent:
- What triggers a new case? (form submission, email, manual)
- Who are the actors? (submitter, approver, ops team)
- What are the key decision points? (approve/reject, escalate, auto-close)
- What data needs to be tracked? (fields per phase)
- Are there related processes that should be connected? (use relations)
-
Identify the right Pipefy components:
Need Component Workflow stages Pipe + Phases Structured data per stage Phase fields Reference/lookup data Database table Cross-process linkage Pipe relation Automatic actions Automation rule AI-driven processing AI automation or AI agent
Design principles
- Start with the outcome. What does "done" look like for this process?
- Name phases for states, not actions. "Under Review" not "Review It".
- Keep the start form minimal. Only ask for data the requester can provide on day 1.
- Use required fields sparingly. Every required field is a blocker.
- Design for the exception. Add a "Blocked" or "On Hold" phase for edge cases.
- Automate the obvious. If a transition always happens under the same condition, it should be an automation, not a manual step.
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 · 122 lines · 89 tokens per session scan A 4f11b6820b99
pipefy-process-design is a skill published in the GitHub repository pipefy/ai-toolkit (44 stars, last pushed 8d ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,070 once invoked, about $0.0004 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
agentic-workflow-orchestra
Orchestrates AI agent work across planning, implementation, integration, QA, and release. Defines phases, gates, handoff logs, startup checklists, and parallel-safety rules for software projects.
using-ao
Catalog of the AO (Agent Orchestrator) ao CLI: spawning workers, managing sessions and projects, sending messages, controlling the shared browser, previewing pages, and daemon control. Use when using the ao CLI, spawning workers, or managing AO sessions in an AO workspace.
syndic
Gère un parc de copropriétés en France avec vue portfolio consolidée. Couvre administration, comptabilité (décret 2005, plan comptable copro, 5 annexes), assemblées générales (convocation, PV, notification), appels de fonds, travaux, fournisseurs, recouvrement d'impayés et transition de syndic. Maîtrise les majorités…
decision-map
Maps the unresolved architecture, policy, and scope decisions that must be answered before planning can start: one durable decision ticket per question on the issue tracker, typed and blocker-linked under a parent map, with fog-of-war, out-of-scope, a computed frontier, and one decision resolved per invocation.…
to-issues
Decompose a PRD and/or SPEC into implementable, vertically-sliced Issues with real blocking edges, then create them in your chosen platform (GitHub or Local). Use after /prd (and optionally /prd-to-spec) to turn requirements into agent-ready tickets. Triggers on: create issues, to-issues, 创建issue, 拆解issue, 生成卡片, 创建卡片…
setup-matt-pocock-skills
为本仓库配置工程技能——设置其 issue tracker、分诊标签词汇表和领域文档布局。首次使用其他工程技能前运行一次。.