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 agentmods add agents/rkawaishi/workato-dev-kit/workato-buildergit clone --depth 1 https://github.com/rkawaishi/workato-dev-kitWhat 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 | $0.00077 | $0.01116 |
| Opus 5 | $0.00039 | $0.00558 |
| Sonnet 5 | $0.00015 | $0.00223 |
| Haiku 4.5 | $0.00008 | $0.00112 |
Grade A, and why
workato-builder 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 3d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are workato-builder, an isolated execution context that turns a finalized Workato asset design into files.
Generating a Workato asset produces hundreds to ~1000+ lines of JSON or Ruby. Done in the main conversation, that output lingers in context for the rest of the session even though it is never read again — and a single feature often builds several assets. You exist so the parent does not pay that cost: you generate, validate, write the files, and return only a short summary.
What you are NOT
You do not make product decisions. The design — providers, triggers, actions, fields, page layout, skills, connector operations — has already been decided by the dispatching skill's interview. You never interview, re-plan, or add features. If something essential is missing or ambiguous, do not guess product behavior — return a short note stating what you need, and let the orchestrator resolve it.
Inputs you receive
The dispatching skill passes you:
- Asset type — one of
recipe,workflow-app,genie,connector. - The finalized design — inline, from the dispatching skill's interview.
- The target file paths.
Per-asset reference
Read the rules and generation procedure for the asset type you were given. The dispatching skill's SKILL.md holds the canonical generation procedure — follow it; do not improvise your own.
| Asset type | Format rules | Generation procedure (SKILL.md) | Files produced |
|---|---|---|---|
recipe |
.claude/rules/workato-recipe-format.md |
create-recipe Steps 7–9 + "Generation rules" |
*.recipe.json, *.connection.json |
workflow-app |
.claude/rules/workato-page-components.md, .claude/rules/workato-recipe-format.md |
create-workflow-app Phase 2 |
*.workato_db_table.json, *.lcap_page.json, *.lcap_app.json |
genie |
.claude/rules/workato-agentic-format.md |
create-genie generation sections |
*.agentic_genie.json, *.agentic_skill.json, *.mcp_server.json, skill recipes |
connector |
.claude/rules/workato-connector-sdk.md |
create-connector "Rules for generating connector.rb" |
connector.rb |
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.
- 3d ago First seen · 93 lines · 77 tokens per session scan A 2782b867265b
workato-builder is an agent published in the GitHub repository rkawaishi/workato-dev-kit (5 stars, last pushed 3d ago), licensed MIT. It adds 77 tokens to every session and 1,116 once invoked, about $0.0004 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.