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
- Socket pass
- Snyk pass
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 | $0.00080 | $0.06298 |
| Opus 5.5 | $0.00032 | $0.02519 |
| Sonnet 5.5 | $0.00016 | $0.01260 |
| Haiku 4.5 | $0.00008 | $0.00630 |
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 3d 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 — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agents
Read only the reference for your active surface: MCP or CLI. The workflows below use shared operation names and arguments.
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.
For traditional automations and AI automations (prompt-driven), see pipefy-automations.
Tools
| Operation | Read-only | Purpose |
|---|---|---|
get_ai_agents |
Yes | List AI agents for a pipe (repo_uuid = pipe UUID, not numeric id). |
get_ai_agent |
Yes | Full agent config including behaviors. |
create_ai_agent |
No | Create a new conversational agent (active by default; active=false to start disabled). |
update_ai_agent |
No | Full-replace (not patch). Always send complete behaviors. Preserves disabled state. |
delete_ai_agent |
No | Destructive; review and approve first. |
toggle_ai_agent_status |
No | Explicit activate/deactivate. |
validate_ai_agent_behaviors |
Yes | Pre-flight check before create/update. |
Execution logs live in pipefy-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) setsdisabled_atexplicitly on create and the chained update. - Routine
update_ai_agentpreserves disabled state — it does not intentionally reactivate. Prefer passingdisabled_atfrom a priorget_ai_agent(disabledAt) to skip the preserve re-read; when omitted, the SDK re-reads and re-sends. - Explicit activate/deactivate:
toggle_ai_agent_status. - After create/update, check the response's
disabled_atandactive(activeis true whendisabled_atis null). Onget_ai_agent,disabledAtnull means active;behaviors[].activeis not agent enablement. An agent with no active behavior is disabled by the API regardless of enablement flags.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago Changed c3394ab43283
- 14d ago Changed 95ce46d59eb5
- 17d ago Changed · +3 lines · -4 tokens per session 53850e970840
- 1mo 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 (51 stars, last pushed yesterday), licensed Apache-2.0. It adds 80 tokens to every session and 6,298 once invoked, about $0.0003 per session on Opus 5.5. 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
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.
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.
excel-image-embed
A spreadsheet tool that downloads image links from selected Excel cells and embeds the images into a new .xlsx workbook. It keeps the original image resolution and lays out multiple images proportionally.
qrgenid
A Windows-only tool that reads an Excel workbook and creates batches of QR codes. Each QR code contains a URL, with its ID shown as text below it, and the results include an updated workbook and image files.
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.