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-intelligencenpx skills add pipefy/ai-toolkit --skill pipefy-process-intelligencegit clone --depth 1 https://github.com/pipefy/ai-toolkitWhat 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 | $0.00065 | $0.01009 |
| Opus 5 | $0.00032 | $0.00504 |
| Sonnet 5 | $0.00013 | $0.00202 |
| Haiku 4.5 | $0.00006 | $0.00101 |
Grade A, and why
pipefy-process-intelligence 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 2d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Process Intelligence
Analyze existing pipes for improvement opportunities and implement them progressively. Investigate immediately. Diagnose with data. Improve progressively.
When to use
The user asks to analyze or improve an existing process:
- "Analyze my pipe"
- "How can I improve this process?"
- "Is this pipe optimized?"
- "Where are the bottlenecks?"
Not for: designing a new process from scratch → use skills/process-design/.
Prerequisites
- Pipe ID or name is known (or searchable via
search_pipes). - Read access to the pipe's cards and phase data.
Steps — investigation (Round 1)
-
Get pipe structure:
MCP:
get_pipe pipe_id=<id>Capture: phases, field count per phase, automation count.
-
Sample recent cards (last 30–50):
MCP:
get_cards pipe_id=<id> first=50 include_fields=trueLook for: stale cards (no updates), cards stuck in early phases, phases with 0 cards.
-
Check automations:
MCP:
get_automations pipe_id=<id>Look for: phases with no automations (manual handoffs), repeated manual steps.
-
Check AI configuration:
MCP:
get_ai_agents repo_uuid=<PIPE_UUID>Look for: no AI agents despite manual categorization or triage patterns.
Diagnosis framework
| Signal | Opportunity |
|---|---|
| Cards stuck in a phase for >7 days | Add due date field + overdue automation |
| Phase transitions always done by same person | Automate the transition condition |
| Fields never filled in certain phases | Remove or make optional |
| Same comment posted repeatedly | AI agent to auto-post based on trigger |
| No automation between intake and first action | Add "notify assignee" automation on card creation |
| Large field count on start form | Move optional fields to later phases |
| Phases with 0 cards over 90 days | Consider removing or merging phases |
Steps — improvement (Round 2+)
Each round focuses on 1–2 improvements; report results before proceeding.
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.
- 2d ago First seen · 137 lines · 65 tokens per session scan A 8d5b70133bf7
pipefy-process-intelligence is a skill published in the GitHub repository pipefy/ai-toolkit (44 stars, last pushed 6d ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,009 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
github
Manage GitHub via GitHub CLI (gh): repos, issues, pull requests, Actions, releases, secrets/variables, projects, gists, searches, and API access. Auto-activates on: "gh", "github cli", "github issue", "github pr", "pull request", "github actions", "workflow", "run", "github release", "release", "gh api", "github…
notebooklm
Complete API for Google NotebookLM - full programmatic access including features not in the web UI. Create notebooks, add sources, generate all artifact types, download in multiple formats. Activates on explicit /notebooklm or intent like "create a podcast about X".
comet-native
Comet Native 工作流。当用户明确调用 /comet-native、要求启动或恢复 Native change，或入口路由到 Native 时使用。.
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…
file-organizer
Triggered when the user needs to organize project files, analyze directory structure, or generate a project report. Use MCP tools to read file contents and produce a structured organization report. Trigger phrases include "help me organize this project", "look at the directory structure", "generate a project summary".
contract-builder
Convert approved planning artifacts into an execution contract. Invoke when the user wants to start building, asks to move from planning to implementation, or when execution-contract.md is missing or stale.