validate-recipe

validate-recipe is a skill for Claude Code from rkawaishi/workato-dev-kit. It costs 25 tokens per session (579 once invoked), scanned A, original, MIT.

A checker for Workato recipe and Genie JSON, which describe automated business workflows and their settings.

In plain words
What is it for?
Use it to validate one file, a named project, or every project against the required recipe and Genie structure.
Why use it?
It finds missing fields, invalid identifiers, broken references, and structural errors that could cause a workflow package to be rejected or fail.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the workato-dev-kit plugin — 13 skills, 1 agent shipped together

Good fit Use it to validate one file, a named project, or every project against the required recipe and Genie structure.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rkawaishi/workato-dev-kit/validate-recipe
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.

Any agent
npx skills add rkawaishi/workato-dev-kit --skill validate-recipe
Clone the repo
git clone --depth 1 https://github.com/rkawaishi/workato-dev-kit

Made for: Claude Code.

Or install workato-dev-kit, the plugin that ships this one along with the rest of its 13 skills, 1 agent.

Wrote 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.

agentmods badge for validate-recipe

README.md
[![agentmods](https://agentmods.dev/badge/skills/rkawaishi/workato-dev-kit/validate-recipe.svg)](https://agentmods.dev/skills/rkawaishi/workato-dev-kit/validate-recipe)
Your own site
<a href="https://agentmods.dev/skills/rkawaishi/workato-dev-kit/validate-recipe"><img src="https://agentmods.dev/badge/skills/rkawaishi/workato-dev-kit/validate-recipe.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 579 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00025 $0.00579
Opus 5 $0.00013 $0.00290
Sonnet 5 $0.00005 $0.00116
Haiku 4.5 $0.00003 $0.00058

Measured 8d ago against content hash 7e19cff07ab8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

validate-recipe 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 8d 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/claude/skills/validate-recipe/SKILL.md · 60 lines

What it actually says

/validate-recipe

Validates the structure of Workato JSON files.

Usage

  • /validate-recipe <file-path> — validate a specific file
  • /validate-recipe <project-name> — validate every file in a project
  • /validate-recipe — no argument: validate every project

Checks

recipe.json

  • Required top-level fields: name, version, code, config
  • code.keyword is "trigger" (number: 0)
  • Every step has number, provider, name, keyword, uuid
  • number values are sequential
  • uuid is a valid UUID v4
  • uuid is 36 characters or fewer (push rejects longer values; applies to step uuid, filter.conditions[].uuid, and input.conditions[].uuid)
  • Steps inside block recursively follow the same structure
  • Every provider in config is actually used by the recipe
  • Datapill references (_dp) point at a real step (provider + line)
  • If filter is present, both conditions (array) and operand exist

agentic_genie.json

  • Required fields: name, description, instructions, ai_provider, references
  • Each references entry is type: "agentic_skill" and its zip_name points to a real file
  • instructions is not empty

agentic_skill.json

  • Required fields: name, trigger_description, references
  • references.recipe_id points to a real .recipe.json
  • The referenced recipe uses the workato_genie / start_workflow trigger

connection.json

  • Required fields: name, provider

Output format

✅ file.recipe.json — OK
⚠️  file2.recipe.json — 2 warnings
  - W001: Step 3 is missing its uuid
  - W002: config contains unused provider "slack"
❌ file3.recipe.json — 2 errors
  - E001: code.keyword is not "trigger"
  - E002: Step 5 uuid exceeds 36 characters (push will fail)

Severity: ❌ Error (likely to fail on push) > ⚠️ Warning (works but discouraged) > ℹ️ Info (informational).

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. 8d ago First seen · 60 lines · 25 tokens per session scan A 7e19cff07ab8

Subscribe to this mod's changes

validate-recipe is a skill published in the GitHub repository rkawaishi/workato-dev-kit (5 stars, last pushed 8d ago), licensed MIT. It adds 25 tokens to every session and 579 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.

Related

Other skills, from other repositories

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens