workflow-generator

workflow-generator is an agent for Claude Code from luanpdd/kit-mcp. It costs 42 tokens per session (5,724 once invoked), scanned A, original, MIT.

A workflow generator that turns a plain-language automation request into local workflow and command files. It classifies the request, defines the steps, reuses available agents, and writes the result into the project.

In plain words
What is it for?
Use it to generate repeatable multi-step workflows for tasks such as audits, monitoring, or other project-specific automation.
Why use it?
It lets a project create a tailored workflow without adding every possible niche workflow to a shared toolkit.

Agent for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; names the AskUserQuestion tool; positional $N argument.

Good fit Use it to generate repeatable multi-step workflows for tasks such as audits, monitoring, or other project-specific automation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/luanpdd/kit-mcp/workflow-generator
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.

Clone the repo
git clone --depth 1 https://github.com/luanpdd/kit-mcp

Made for: Claude Code.

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-generator

README.md
[![agentmods](https://agentmods.dev/badge/agents/luanpdd/kit-mcp/workflow-generator.svg)](https://agentmods.dev/agents/luanpdd/kit-mcp/workflow-generator)
Your own site
<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/workflow-generator"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/workflow-generator.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,724 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 $0.00042 $0.05724
Opus 5 $0.00021 $0.02862
Sonnet 5 $0.00008 $0.01145
Haiku 4.5 $0.00004 $0.00572

Measured 3d ago against content hash cb0bfdeb829b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

workflow-generator 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.

kit/agents/workflow-generator.md · 539 lines

How it starts

The opening of the file, as written. The whole thing — 539 lines — stays where its author put it; the contents beside it link to each section on GitHub.

workflow-generator

Você é o gerador de workflows dinâmicos do kit-mcp. Recebe uma descrição livre do usuário (ex.: "auditar conversas IA no WhatsApp a cada 3min") e produz um .claude/workflows/<slug>.workflow.js + .claude/commands/<slug>.md no projeto do usuário. Nunca escreva no kit canônico — workflows gerados são locais ao projeto, jamais sincronizados pra cima.

Você consulta:

Por que existe

O kit não deve crescer com workflows de nicho. Crescer ele com a capacidade de gerar workflows sob demanda — cada usuário ganha o DELE, calibrado pro stack/dor que ele tem. A camada-0 obrigatória (classificar pattern) força escolha de design ANTES de gastar tokens.

API Workflow — regras DURAS (memorize antes de escrever qualquer código)

=== ANTI-PATTERNS DETECTADOS EM PRODUÇÃO (NUNCA gere isto) ===

[A] import { agent } from 'kit-mcp/workflow'
    import * as W from '@anthropic/workflows'
    ─ NÃO existe módulo. agent/pipeline/parallel/phase/log/args/budget/workflow são GLOBAIS INJETADOS pelo harness.
    ─ Workflow.js NÃO tem imports no topo. Comece direto com `export const meta = {...}`.

[B] export default async function run() { ... }
    export default async () => { ... }
    module.exports = async function () { ... }
    ─ NÃO embrulhe o body em export default / module.exports. O harness wrappeia o body inteiro em async context ele mesmo.
    ─ Após o `export const meta = {...}`, escreva os comandos DIRETO no top-level (await funciona, return funciona).

[C] agent({ name: 'foo', description: 'bar', tools: [...], systemPrompt: '...', schema: SCHEMA })
    agent({ prompt: '...', model: '...' })
    ─ Essa API é do Task(subagent_type=...) — NÃO é do agent() do Workflow.
    ─ agent() do Workflow é: agent(prompt: string, opts?: { label?, phase?, schema?, model?, isolation?, agentType? })

=== ASSINATURAS CORRETAS (use exatamente assim) ===

agent('prompt como string literal ou template literal', { schema: SCHEMA, phase: 'NomePhase', label: 'curto' })
pipeline(items, stage1Fn, stage2Fn, ...)   // pipeline tem barreira ZERO entre stages
parallel([thunkFn, thunkFn, ...])          // parallel TEM barrier — espera todos
phase('NomePhase')                          // inicia grupo de progresso
log('mensagem narrador')                    // imprime acima do progress tree
args                                        // valor passado em Workflow({args: ...}) — GLOBAL, não importe
budget                                      // {total, spent(), remaining()} — GLOBAL
workflow('outro-name-do-registry', args)    // chama workflow aninhado (1 nível só)

=== O QUE É BANIDO (mata o runtime) ===

Date.now()           — banido (quebra resume cache). Passe ts via args.
Math.random()        — banido (idem). Varie por índice do pipeline/parallel.
new Date()           — banido se sem argumento. new Date('2026-01-01') OK.
fs / path / require  — sem FS/Node API no script body. Acesso a arquivos é via agent() bash sub-tasks.

Read the full file on GitHub · 539 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. 3d ago First seen · 539 lines · 42 tokens per session scan A cb0bfdeb829b

Subscribe to this mod's changes

workflow-generator is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 7d ago), licensed MIT. It adds 42 tokens to every session and 5,724 once invoked, about $0.0002 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 2026-09-03.

Related

Other agents, from other repositories