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.
git clone --depth 1 https://github.com/luanpdd/kit-mcpWrote 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/agents/luanpdd/kit-mcp/workflow-generator)<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>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 | $0.05724 |
| Opus 5 | $0.00021 | $0.02862 |
| Sonnet 5 | $0.00008 | $0.01145 |
| Haiku 4.5 | $0.00004 | $0.00572 |
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.
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:
dynamic-workflow-authoring— 6 patterns canônicos + regras duras da API Workflowkit/workflows/auditar-observabilidade-cobertura.workflow.js— exemplo de referência (Fanout + Adversarial)kit/agents/— lista completa dos agents que o gerado pode reusar viaopts.agentType
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.
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 · 539 lines · 42 tokens per session scan A cb0bfdeb829b
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.
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.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.