workflow-builder

workflow-builder is a skill for Claude Code, Codex from ballerina-platform/ballerina-vscode. It costs 130 tokens per session (6,873 once invoked), scanned A, original, Apache-2.0.

A guide for building durable Ballerina workflows made of an orchestration function and activity steps. Durable means the process can resume after a crash or restart using its recorded history.

In plain words
What is it for?
Use it for long-running, multi-step processes that call services, databases, clocks, random generators, or notification systems.
Why use it?
It avoids fragile hand-written retry loops, polling jobs, and manually saved state that can lose progress or repeat work after failures.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for long-running, multi-step processes that call services, databases, clocks, random generators, or notification systems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ballerina-platform/ballerina-vscode/workflow-builder
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 ballerina-platform/ballerina-vscode --skill workflow-builder
Clone the repo
git clone --depth 1 https://github.com/ballerina-platform/ballerina-vscode

Made for: Claude Code, Codex.

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 workflow-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/ballerina-platform/ballerina-vscode/workflow-builder/github.svg)](https://agentmods.dev/skills/ballerina-platform/ballerina-vscode/workflow-builder)
Your own site
<a href="https://agentmods.dev/skills/ballerina-platform/ballerina-vscode/workflow-builder"><img src="https://agentmods.dev/badge/skills/ballerina-platform/ballerina-vscode/workflow-builder/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.

agentmods 80×15 button for workflow-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/ballerina-platform/ballerina-vscode/workflow-builder"><img src="https://agentmods.dev/badge/skills/ballerina-platform/ballerina-vscode/workflow-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,873 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 $0.00130 $0.06873
Opus 5.5 $0.00052 $0.02749
Sonnet 5.5 $0.00026 $0.01375
Haiku 4.5 $0.00013 $0.00687

Measured 5d ago against content hash 7e4fb3a413a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

workflow-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 5d 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.

packages/ballerina-extension/src/features/ai/agent/skills/workflow-builder/SKILL.md · 585 lines

How it starts

The opening of the file, as written. The whole thing — 585 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow Builder

Always reach for ballerina/workflow when the user describes a durable or long-running process — never a plain function with hand-rolled retry loops, a cron/poll job, or manual state persisted to a database to survive restarts. That is exactly what this module replaces.

The workflow diagram, like the agent diagram, is parsed directly out of the source you write, not generated from a model. Code that compiles but does not match the shapes below still renders as a broken or incomplete node. Follow every rule.

<...> marks a placeholder to substitute from the user's request. Never emit it literally.

import ballerina/workflow;

Workflow vs. activity

A workflow is two kinds of function:

  • The workflow function (@workflow:Workflow) — orchestration only: which activity runs next, and on what condition. It is replayed from recorded history after any crash or restart, so it must be deterministic.
  • Activities (@workflow:Activity) — every piece of real work: calling a service, hitting a database, sending a notification, reading the clock, generating a random value. The engine records each activity's result once and reuses it on replay, so a completed activity never runs twice.

Put all real work in activities. If you find yourself writing an HTTP call, a time:utcNow(), or a random: value directly inside a @workflow:Workflow function, move it into an activity instead.

@workflow:Workflow functions always go in workflows.bal (mirrors the agents.bal convention for AI agents) — create the file if it does not exist. Never put a workflow function in functions.bal, and never leave one in main.bal past a first draft.

Activity functions go in activities.bal by the same convention. The one exception: the low-code diagram itself always appends a newly-generated activity to functions.bal so it never shifts the workflow's own line positions — that placement comes from the diagram tooling, not from you, so don't imitate it when writing activities from a prompt. When you add an activity, put it in activities.bal.

Read the full file on GitHub · 585 lines

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. 5d ago First seen · 585 lines · 130 tokens per session scan A 7e4fb3a413a8

Subscribe to this mod's changes

workflow-builder is a skill published in the GitHub repository ballerina-platform/ballerina-vscode (49 stars, last pushed today), licensed Apache-2.0. It adds 130 tokens to every session and 6,873 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-26.

Related

Other skills, from other repositories

mem0-oss-to-platform

Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…

mem0ai/mem0 · 217 tokens

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…

ag-ui-protocol/ag-ui · 162 tokens

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".

microsoft/skills · 78 tokens

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.

microsoft/skills · 46 tokens

dev-runtime

How the Node side of a dev stack runs without haven, and the backend host: pnpm dev (UI built once, backend reloading), pnpm dev:hmr (adds the Vite ui lane), tools/dev-runtime (api + worker in one Node process), backend reload on a file change, the debounce (quiet window + max wait), ports derived from PORT. Use when…

langwatch/langwatch · 172 tokens

api-design

Use when settling the contract of an API you expose, before implementation: resources/URLs, REST vs GraphQL, versioning, one RFC 9457 error envelope, pagination, idempotency — emitted as OpenAPI 3.1. NOT implementing the endpoints (that is fastapi/nestjs/go/nodejs), NOT auth hardening (that is secure-coding), NOT…

ericrisco/rsc-harness · 105 tokens