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-recipegit 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-recipe)<a href="https://agentmods.dev/skills/rkawaishi/workato-dev-kit/create-recipe"><img src="https://agentmods.dev/badge/skills/rkawaishi/workato-dev-kit/create-recipe.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 | $0.00034 | $0.02996 |
| Opus 5 | $0.00017 | $0.01498 |
| Sonnet 5 | $0.00007 | $0.00599 |
| Haiku 4.5 | $0.00003 | $0.00300 |
Grade B, and why
create-recipe scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Prohibited**: do not grep `projects/<other-project>/Recipes/` to copy fields from sample JSON. That leaks project-specific logic and naming, and it hides documentation gaps (see "Recipe implementation lifecycle" in ` How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/create-recipe
Generates Workato recipe JSON files from a short interview.
Usage
/create-recipe <project>— generate into that project/create-recipe— infer the project from context and confirm it
Procedure
1. Interview the recipe design
Confirm with the user:
- Recipe purpose: what you want to automate.
- Trigger: which app's which event starts the recipe (e.g. "new email in Gmail").
- Actions: what happens after the trigger (e.g. "upload file to Google Drive").
- Conditions: any filter conditions.
- Target project: which project directory the file goes into.
2. Check the shared asset catalog
If projects/CATALOG.md exists, read it. Look for existing assets matching the requirements:
- Connections: if a shared connection for the same provider exists → propose reusing it.
- Recipe Functions: if the logic you need (manager lookup, notification sender, etc.) already exists → propose calling it via
call_recipe. - If you find matching assets, propose them to the user and bake them in only after they approve.
If the catalog is missing, skip this and tell the user it can be generated with /catalog scan.
3. Check the connector knowledge
- Use
@docs/connectors/_index.mdto identify the connector you'll use. - Read
@docs/connectors/<connector>.mdfor available triggers/actions and field info.
4. Verify field details
- If the connector doc has an Input/Output fields section for the target action, use it.
- If the field info is missing: fetch the official docs with WebFetch.
- URL pattern:
https://docs.workato.com/en/connectors/<name>/<action-name>.html - Or:
https://docs.workato.com/en/connectors/<name>/actions.html
- URL pattern:
- Append what you fetched to
docs/connectors/<connector>.mdso the knowledge accumulates. - Prohibited: do not grep
projects/<other-project>/Recipes/to copy fields from sample JSON. That leaks project-specific logic and naming, and it hides documentation gaps (see "Recipe implementation lifecycle" in@.claude/CLAUDE.md). - If you have to implement best-effort because there's no documentation anywhere, record
provider/actionunder## Unlearnedinorg/docs/connectors/<provider>.mdand tell the user, so/learn-recipecan close the gap after the first push.
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 · 239 lines · 34 tokens per session scan B 198491e85b60
create-recipe is a skill published in the GitHub repository rkawaishi/workato-dev-kit (5 stars, last pushed 7d ago), licensed MIT. It adds 34 tokens to every session and 2,996 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.