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 workato-devs/recipe-skills --skill workato-recipesgit clone --depth 1 https://github.com/workato-devs/recipe-skillsWrote 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/workato-devs/recipe-skills/workato-recipes)<a href="https://agentmods.dev/skills/workato-devs/recipe-skills/workato-recipes"><img src="https://agentmods.dev/badge/skills/workato-devs/recipe-skills/workato-recipes/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/workato-devs/recipe-skills/workato-recipes"><img src="https://agentmods.dev/badge/skills/workato-devs/recipe-skills/workato-recipes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 328 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00042 | $0.09890 |
| Opus 5 | $0.00021 | $0.04945 |
| Sonnet 5 | $0.00008 | $0.01978 |
| Haiku 4.5 | $0.00004 | $0.00989 |
Grade A, and why
workato-recipes scanned grade A 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Use when:** Recipe should be callable via external HTTP request (curl, webhooks, third-party systems). How it starts
The opening of the file, as written. The whole thing — 1,260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workato Recipes Base Skill - Agent Instructions
This document provides foundational knowledge for AI agents to generate valid Workato recipe JSON. This is the base skill that connector-specific skills (stripe-recipes, salesforce-recipes, etc.) extend.
CRITICAL: Pre-Generation Checklist
For EXISTING projects (recipes already exist):
- Read 1-2 existing
.recipe.jsonfiles to understand project structure and patterns - Verify connection names - ask user for exact connection names in their workspace
- Follow established folder structure - match where recipes and connections are organized
For GREENFIELD projects (no existing recipes):
- Use skill templates as reference - see
templates/directory in each skill - Use standard file naming -
{recipe_name}.recipe.json(lowercase, underscores for spaces) - Start recipe names with action verbs - "Create...", "Search...", "Update...", "Process..."
- Ask user for connection names - exact names from their Workato workspace
ALWAYS (both scenarios):
- Use descriptive UUIDs -
{action}-{number}format (e.g.,search-contact-001,return-success-005) - Use API endpoint triggers for testability (unless callable recipe is specifically needed)
- Define all response codes upfront in the trigger (200, 400, 500 at minimum)
UUID Format (MANDATORY)
ALWAYS use descriptive UUIDs, regardless of what existing recipes in a project use:
search-contact-001
create-customer-002
if-found-003
return-success-004
return-error-005
NEVER use random hex UUIDs:
a1b2c3d4-e5f6-7890-abcd-ef1234567890 ← ANTI-PATTERN
11111111-1111-1111-1111-111111111111 ← ANTI-PATTERN
NOTE: Recipes created in Workato's declarative UI have random hash UUIDs. This is a platform limitation, NOT a pattern to follow. When you see random UUIDs in existing recipes, do NOT copy them. Always use descriptive UUIDs for new recipes and actions.
Recipe JSON Structure (CRITICAL)
What ships with it
28 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- control-flow/foreach.md 10 KB
- control-flow/if-else.md 12 KB
- control-flow/repeat-while.md 8.5 KB
- control-flow/stop.md 5.1 KB
- control-flow/try-catch.md 9.3 KB
- fundamentals/config-section.md 8.3 KB
- fundamentals/datapill-syntax.md 8.3 KB
- fundamentals/recipe-structure.md 6.5 KB
- lint-rules.json 985 B
- patterns/adhoc-http-actions.md 30 KB
- patterns/api-platform-artifacts.md 7.3 KB
- patterns/custom-connector-actions.md 6.5 KB
- patterns/jwt-auth.md 7.6 KB
- patterns/python-snippets.md 10 KB
- patterns/variables-and-lists.md 24 KB
- skill.yaml 2.0 KB
- templates/api-endpoint-complete.template.json 34 KB
- templates/api-endpoint-trigger.template.json 4.9 KB
- templates/callable-recipe-complete.template.json 17 KB
- templates/control-flow-examples.template.json 33 KB
- triggers/api-endpoint.md 10.0 KB
- triggers/callable-recipe.md 6.1 KB
- triggers/data-table.md 2.8 KB
- triggers/genie-skill.md 12 KB
- triggers/messaging-topic.md 7.0 KB
- triggers/scheduler.md 5.1 KB
- validation-checklist.md 5.2 KB
- variable/lint-rules.json 955 B
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.
- 10d ago First seen · 1,260 lines · 42 tokens per session scan A b9dcfec79de0
workato-recipes is a skill published in the GitHub repository workato-devs/recipe-skills (18 stars, last pushed 12d ago), licensed MIT. It adds 42 tokens to every session and 9,890 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
migrate-segw-to-rap
Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…
telnyx-messaging-hosted-curl
Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.