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 pipefy/ai-toolkit --skill pipefy-ai-agentsgit 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-ai-agents)<a href="https://agentmods.dev/skills/pipefy/ai-toolkit/pipefy-ai-agents"><img src="https://agentmods.dev/badge/skills/pipefy/ai-toolkit/pipefy-ai-agents/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/pipefy/ai-toolkit/pipefy-ai-agents"><img src="https://agentmods.dev/badge/skills/pipefy/ai-toolkit/pipefy-ai-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 209 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00084 | $0.07022 |
| Opus 5 | $0.00042 | $0.03511 |
| Sonnet 5 | $0.00017 | $0.01404 |
| Haiku 4.5 | $0.00008 | $0.00702 |
Grade A, and why
pipefy-ai-agents 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 9d 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 — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agents
Conversational AI agents attached to pipes. Each agent has an agent-level instruction and 1–5 behaviors, each with its own trigger event, prompt, and actions. 7 MCP tools.
For traditional automations and AI automations (prompt-driven), see skills/automations/pipefy-automations/SKILL.md.
Tools
| Tool (MCP) | CLI | Read-only | Purpose |
|---|---|---|---|
get_ai_agents |
pipefy agent list |
Yes | List AI agents for a pipe (repo_uuid = pipe UUID, not numeric id). |
get_ai_agent |
pipefy agent get |
Yes | Full agent config including behaviors. |
create_ai_agent |
pipefy agent create |
No | Create a new conversational agent (active by default; active=false / --inactive to start disabled). |
update_ai_agent |
pipefy agent update |
No | Full-replace (not patch). Always send complete behaviors. Preserves disabled state. |
delete_ai_agent |
pipefy agent delete |
No | (Two-step destructive)1 |
toggle_ai_agent_status |
pipefy agent toggle |
No | Explicit activate/deactivate (e.g. --inactive). |
validate_ai_agent_behaviors |
pipefy agent validate-behaviors |
Yes | Pre-flight check before create/update. |
The read tools (get_ai_agents, get_ai_agent, validate_ai_agent_behaviors) and the write tools (create/update/delete/toggle) are all remote-safe: available under the hosted (profile=remote) surface. create_ai_knowledge_base_document, create_llm_provider, and update_llm_provider take a local file and are local profile only — withheld on the hosted server.
Execution logs live in skills/observability/ (get_ai_agent_logs, get_ai_agent_log_details).
Active lifecycle
- Agents are active by default. Create-active clears the API default disabled shell via the configure update (omits
disabledAt). Create-inactive (active=false/--inactive) setsdisabled_atexplicitly on create and the chained update. - Routine
update_ai_agent/pipefy agent updatepreserves disabled state — it does not intentionally reactivate. Prefer passingdisabled_atfrom a priorget_ai_agent(disabledAt) /pipefy agent update --disabled-atto skip the preserve re-read; when omitted, the SDK re-reads and re-sends. - Explicit activate/deactivate:
toggle_ai_agent_status/pipefy agent toggle(--active/--inactive). - After create/update, confirm status from the response
disabled_at/activefields when present. To re-read viaget_ai_agent/pipefy agent get, use agentdisabledAt(null means active) — get does not expose write-envelopedisabled_at/active, andbehaviors[].activeis not agent enablement. Never assume inactive without that confirmation. An agent with no active behavior is disabled by the API regardless of the create/update enablement flags.
Footnotes
-
MCP two-step: echo
confirmation_tokenfrom the preview withconfirm=true. CLI:--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.
- 9d ago First seen · 339 lines · 84 tokens per session scan A 071ed2b00d41
pipefy-ai-agents is a skill published in the GitHub repository pipefy/ai-toolkit (45 stars, last pushed today), licensed Apache-2.0. It adds 84 tokens to every session and 7,022 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
frontmcp-deployment
Use when deploying, building for production, packaging, or shipping a FrontMCP server. Covers build targets (node, cli SEA binary, browser, embeddable SDK, mcpb archive for Claude Desktop, serverless) and deploying to Vercel (with Vercel KV), AWS Lambda (API Gateway, SAM, CDK), Cloudflare Workers (KV, D1, Durable…
wjx-mcp-use
A guide for using Wenjuanxing, a Chinese online questionnaire platform, through connected tools. It covers creating and editing surveys, reading responses, analyzing data, managing contacts, and generating sign-in links.
wjx-survey-ppt
Instructions for turning Wenjuanxing questionnaire responses into a presentation report. Wenjuanxing, also called 问卷星, is a platform for creating surveys and collecting answers.
mcp-server-chart
Auto-generated skill for mcp-server-chart tools via OneKey Gateway.
firecrawl-mcp
Auto-generated skill for firecrawl-mcp tools via OneKey Gateway.
github
Auto-generated skill for github tools via OneKey Gateway.