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 skills add APIPASS-Integrations/apipass-headless --skill build-agent-flowgit clone --depth 1 https://github.com/APIPASS-Integrations/apipass-headlessWrote 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/skills/apipass-integrations/apipass-headless/build-agent-flow)<a href="https://agentmods.dev/skills/apipass-integrations/apipass-headless/build-agent-flow"><img src="https://agentmods.dev/badge/skills/apipass-integrations/apipass-headless/build-agent-flow/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.
<a href="https://agentmods.dev/skills/apipass-integrations/apipass-headless/build-agent-flow"><img src="https://agentmods.dev/badge/skills/apipass-integrations/apipass-headless/build-agent-flow.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00168 | $0.02652 |
| Opus 5 | $0.00084 | $0.01326 |
| Sonnet 5 | $0.00034 | $0.00530 |
| Haiku 4.5 | $0.00017 | $0.00265 |
Grade A, and why
build-agent-flow 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 9d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Construir Fluxo de Agente de IA na APIPASS
Fluxos de agente tem uma topologia diferente da cadeia linear de um fluxo comum. Este guia cobre SO o que e
especifico de agente. Para o resto (autenticacao, trigger, stop/responses/OAS, contadores, posicoes,
save → version → publish, autorizacoes por referencia), siga /apipass-integrations:build-flow e
/apipass-integrations:apipass-patterns. A anatomia de cada acao de IA esta em /apipass-integrations:apipass-agent-actions.
0. Quando usar esta skill
- Agente de IA (decide, usa tools/memoria, base de conhecimento) → esta skill (
.service.ai.AiAgent). - Completion simples ("chame o ChatGPT para gerar/classificar X", sem tools) → passo linear
CHATGPT_CREATE_COMPLETIONnabuild-flowcomum. NAO precisa de agente. - Fluxo de integracao comum (sem IA) →
/apipass-integrations:build-flow.
1. O conceito central: hub-and-spoke
O agente e um hub. Modelo, memoria e tools sao satelites que NAO entram na cadeia nextSteps —
eles "penduram" no agente por campos de id (*RouteConfigId) e ficam posicionados ABAIXO dele no canvas.
trigger → [ … pre-processamento … ] → AGENTE (a0) → a999
│ (ligacoes por *RouteConfigId, sem nextSteps)
┌───────────────┼───────────────┐
modelo (a1) memoria (a2) tool(s) (a3…)
│ (se for retriever RAG)
embedding (a4)
Apenas o agente participa do nextSteps (vem do pre-processamento, vai pro stop). Os satelites se ligam assim
(detalhe e shape de inputData em apipass-agent-actions):
| De → Para | Campo no pai | Back-ref no filho |
|---|---|---|
| Agente → Modelo (1) | llmModelRouteConfigId |
aiAgentRouteConfigId |
| Agente → Memoria (1, opcional) | memoryRouteConfigId |
aiAgentRouteConfigId |
| Agente → Tools (N) | toolRouteConfigs: [{ id, state: "LINKED" }] |
aiAgentRouteConfigId (opcional) |
| Retriever → Embedding | embeddingModelRouteConfigId (em inputData) |
vectorStoreRouteConfigId |
| Ingestor → Loader → Splitter | documentLoaderRouteConfigId / documentSplitterRouteConfigId (em inputData) |
vectorStoreRouteConfigId / documentLoaderRouteConfigId |
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.
- 9d ago First seen · 99 lines · 168 tokens per session scan A 88d99e1c8267
build-agent-flow is a skill published in the GitHub repository APIPASS-Integrations/apipass-headless (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 168 tokens to every session and 2,652 once invoked, about $0.0008 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 skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
azure-search-documents-dotnet
Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.