Windmill

What it does

When your agent uses it

• Working with GOATs Windmill instance — running
• Syncing analytics tools
• Inspecting job execution
• Adding a new tool

Example prompts

• “/windmill”

Requirements

• Python 3
• A credential in WINDMILL_TOKEN

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Frontend calls the processes service API to start a tool
2. 2processes creates a job in customer.job and submits it to Windmill
3. 3Windmill runs the generated Python script, which imports from goatlib.tools
4. 4The tool class (BaseToolRunner subclass) reads input from DuckLake, processes, writes output to DuckLake
5. 5Job status is tracked in customer.job (pending → running → finished/failed)

What it can do on your machine

Read from SKILL.md and the folder at commit a181bf4. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • uv
  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • WINDMILL_TOKEN

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Windmill loads about 910 tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 305 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~57

When it runs · the whole SKILL.md, loaded when a task matches

~910

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:12

  - **URL / Web UI**: `WINDMILL_URL` in `.env` (local dev: http://localhost:8110)

• NoteMentions a .env fileSKILL.md:14

  - **Token**: `WINDMILL_TOKEN` in `.env` — never hardcode it

• NoteMentions a .env fileSKILL.md:63

  set -a && source .env && set +a

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from plan4better/goat at commit a181bf4, republished under its GPL-3.0 licence (© plan4better). 305 words, ~910 tokens.

name

windmill

description

Use when working with GOAT's Windmill instance — running or syncing analytics tools, inspecting job execution, adding a new tool, or checking which f/goat/tools/* scripts exist. Use the Windmill MCP tools for API calls.

uv run python -c "
from itertools import groupby
from goatlib.tools.registry import TOOL_REGISTRY
for cat, items in groupby(sorted(TOOL_REGISTRY, key=lambda t: t.category), key=lambda t: t.category):
    print(f'## {cat}')
    for t in items:
        flags = [f for f, on in (('hidden', t.toolbox_hidden), ('beta', t.beta), (f'worker={t.worker_tag}', t.worker_tag != 'tools')) if on]
        print(f\"  {t.windmill_path}{'  [' + ', '.join(flags) + ']' if flags else ''} — {t.description}\")
"

set -a && source .env && set +a
uv run python -m goatlib.tools.sync_windmill

SELECT id, type, status, created_at, payload->>'tool_type' AS tool
FROM customer.job ORDER BY created_at DESC LIMIT 10;

© plan4better, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/windmill of plan4better/goat.

Open the folder on GitHubat commit a181bf4