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 rules/rkawaishi/workato-dev-kit/workato-recipe-formatgit clone --depth 1 https://github.com/rkawaishi/workato-dev-kitWrote 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/rules/rkawaishi/workato-dev-kit/workato-recipe-format)<a href="https://agentmods.dev/rules/rkawaishi/workato-dev-kit/workato-recipe-format"><img src="https://agentmods.dev/badge/rules/rkawaishi/workato-dev-kit/workato-recipe-format.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 | $0.00000 | $0.02620 |
| Opus 5 | $0.00000 | $0.01310 |
| Sonnet 5 | $0.00000 | $0.00524 |
| Haiku 4.5 | $0.00000 | $0.00262 |
Grade A, and why
workato-recipe-format 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 5d 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workato Recipe JSON Format
Top-level structure
{
"name": "Recipe name",
"description": "Description (Markdown supported)",
"version": 1,
"private": true,
"concurrency": 1,
"code": { /* trigger + action tree */ },
"config": [ /* connection configuration */ ]
}
format_version on the trigger inside code
Workato may stamp "format_version": 2 on the trigger step so it can distinguish a newer recipe structure (it appears after pulling a UI-saved recipe). You can omit it when generating from scratch, but preserve it on push.
UI-only fields (don't write them by hand, but they appear after pushing)
| Field | Where | Meaning |
|---|---|---|
dynamicPickListSelection |
step | Display label for a pick-list selection. Example: {"event_name": "Slash Command (slash_command)"} |
toggleCfg |
step | Toggle state of input fields. true = custom-input mode, false = pick-list mode. |
title |
action step | Override for the action's display name (null = default). |
description |
action step | The action description returned by the connector (may include HTML spans). Added automatically on pull. |
custom: true |
config's account_id |
Marks a custom-connector connection (added automatically on pull). |
You can omit these when writing JSON by hand — Workato fills them in on push. Once present (e.g. after pull), keep them; do not delete them.
code: step tree (recursive)
Each step has:
| Field | Type | Description |
|---|---|---|
number |
int | Step number (0-based; trigger is 0). |
provider |
string | Connector name (e.g. gmail, slack, salesforce). |
name |
string | Action name (e.g. new_email, post_message). |
as |
string | Step reference name (used in datapills). |
keyword |
string | "trigger" / "action" / "foreach". |
input |
object | Input parameters (may include datapill references). |
block |
array | Array of child steps (nestable). |
filter |
object | Conditional filter (optional). |
comment |
string | Step comment (optional). |
uuid |
string | UUID v4. 36 characters or fewer (do not prefix or extend it — push rejects longer values). The same limit applies to uuid fields inside filter.conditions[] and input.conditions[]. |
extended_output_schema |
array/null | Custom output schema. Recommended on both triggers and actions — omitting it forces a UI refresh. |
extended_input_schema |
array/null | Custom input schema. Required on return_result and similar. |
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.
- 5d ago First seen · 310 lines · 0 tokens per session scan A c47ea3f02ad2
workato-recipe-format is a cursor rule published in the GitHub repository rkawaishi/workato-dev-kit (5 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,620 tokens. 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 2026-08-31.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.