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 rkawaishi/workato-dev-kit --skill create-geniegit 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/skills/rkawaishi/workato-dev-kit/create-genie)<a href="https://agentmods.dev/skills/rkawaishi/workato-dev-kit/create-genie"><img src="https://agentmods.dev/badge/skills/rkawaishi/workato-dev-kit/create-genie.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 5.1 | $0.00025 | $0.02168 |
| Opus 5 | $0.00013 | $0.01084 |
| Sonnet 5 | $0.00005 | $0.00434 |
| Haiku 4.5 | $0.00003 | $0.00217 |
Grade A, and why
create-genie 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 7d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/create-genie
Generate the full file set for a Workato Genie (AI agent). Supports Genie alone, MCP server alone, or both.
Genie vs MCP Server — when to use which
| Genie | MCP Server | |
|---|---|---|
| Purpose | Conversational AI agent | Expose tools to external AIs |
| Channels | Slack, Teams, Workato GO | Claude Desktop, Cursor, ChatGPT |
| Files | .agentic_genie.json |
.mcp_server.json |
| Skill references | Direct via references |
Ordered + described via the tools[] array |
| AI instructions | instructions (system prompt) |
tools[].description (tool-selection guidance) |
- Genie only: a conversational agent for internal chat.
- MCP Server only: tools callable from external AI editors / chat.
- Both: usable inside Genie and callable externally (skills/recipes can be shared).
Procedure
-
Interview the user:
- Genie purpose: what AI agent are we building?
- Target users: who uses it?
- Skill list: which skills should the Genie have (purposes of each)?
- AI provider:
anthropic/openai(default:anthropic). - Target project: which project directory to create in.
- MCP exposure: also expose as an MCP server? (default: No.)
- VUA: is Verified User Access needed (API calls using the end user's credentials)?
-
Read the references:
@.claude/rules/workato-agentic-format.md@.claude/rules/workato-recipe-format.md@.claude/rules/workato-project-structure.md@docs/connectors/_index.md+ relevant connector knowledge@docs/platform/agent-studio.md@docs/platform/mcp.md
-
If an existing Genie is available, reference its structure.
-
Generate the Genie configuration files (following
@.claude/rules/workato-project-structure.md):<project>/Agents/<name>.agentic_genie.json— the Genie itself.- For each skill:
<project>/Agents/<skill_name>.agentic_skill.json— skill definition.
- For MCP exposure:
<project>/Agents/<name>.mcp_server.json— MCP server definition. - Make sure
zip_name/folderinside the JSON include the subfolder path.
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.
- 7d ago First seen · 221 lines · 25 tokens per session scan A 1a56f299abdb
create-genie is a skill published in the GitHub repository rkawaishi/workato-dev-kit (5 stars, last pushed 7d ago), licensed MIT. It adds 25 tokens to every session and 2,168 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…