workato-agentic-format

A set of rules for creating Workato Agentic JSON files, which define AI agents and the skills, models, and services they use.

In plain words
What is it for?
Use it when writing or checking `.agentic_genie.json` files, including agent instructions, AI providers, models, MCP servers, and linked skills.
Why use it?
It gives projects a consistent structure for describing Workato AI agents and their references.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/rkawaishi/workato-dev-kit/workato-agentic-format
Clone the repo
git clone --depth 1 https://github.com/rkawaishi/workato-dev-kit
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,905 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01905
Opus 5 $0.00000 $0.00953
Sonnet 5 $0.00000 $0.00381
Haiku 4.5 $0.00000 $0.00191

Measured 2d ago against content hash 56982057df98, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workato-agentic-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 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.

framework/cursor/rules/workato-agentic-format.mdc · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workato Agentic JSON Format

Genie (AI agent): *.agentic_genie.json

{
  "name": "Genie name",
  "logo_file_name": "logo.png",
  "logo_content_type": "image/png",
  "description": "Short description of the Genie",
  "instructions": "System prompt (Markdown)",
  "ai_provider": "anthropic",
  "ai_model": null,
  "matrix": false,
  "mcp_servers": [],
  "references": {
    "ref_0": {
      "type": "agentic_skill",
      "id": {
        "zip_name": "skill_name.agentic_skill.json",
        "name": "Skill display name",
        "folder": ""
      }
    }
  }
}

Field details

Field Description
instructions The Genie's system prompt. Describe its role, target users, behavior, and prohibitions.
ai_provider "anthropic" / "openai" / etc.
ai_model null for the default, or a specific model name.
matrix Matrix mode (run multiple skills in parallel).
mcp_servers List of MCP servers to connect to.
references Use ref_0, ref_1, ... to reference the skills this Genie uses.

Best practices for instructions

Structure the Genie's prompt under these sections:

  • What's my job? — primary responsibilities
  • Who will need my help? — target users
  • How do I get things done? — behavior patterns
  • What should I avoid? — prohibitions
  • What results do you want me to track? — metrics to follow
  • How should I talk to people? — communication style
  • Any extra tips? — anything else

Agentic Skill: *.agentic_skill.json

{
  "name": "Skill name",
  "trigger_description": "When to use this skill\n\nSpecific trigger conditions",
  "references": {
    "recipe_id": {
      "type": "recipe",
      "id": {
        "zip_name": "skill_recipe.recipe.json",
        "name": "Recipe name",
        "folder": ""
      }
    }
  }
}

Relationship between skills and recipes

agentic_genie.json
  └── references → agentic_skill.json (multiple allowed)
                      └── references.recipe_id → recipe.json

Read the full file on GitHub · 218 lines

Changes

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.

  1. 2d ago First seen · 218 lines · 0 tokens per session scan A 56982057df98

Subscribe to this mod's changes

workato-agentic-format is a cursor rule published in the GitHub repository rkawaishi/workato-dev-kit (5 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,905 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.