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 apipass-agent-actionsgit 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/apipass-agent-actions)<a href="https://agentmods.dev/skills/apipass-integrations/apipass-headless/apipass-agent-actions"><img src="https://agentmods.dev/badge/skills/apipass-integrations/apipass-headless/apipass-agent-actions/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/apipass-agent-actions"><img src="https://agentmods.dev/badge/skills/apipass-integrations/apipass-headless/apipass-agent-actions.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 | $0.00066 | $0.04339 |
| Opus 5 | $0.00033 | $0.02169 |
| Sonnet 5 | $0.00013 | $0.00868 |
| Haiku 4.5 | $0.00007 | $0.00434 |
Grade A, and why
apipass-agent-actions 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 10d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Catalogo de Acoes de IA e Anatomia do Agente
A familia de IA da APIPASS (Agent Builder) tem uma topologia hub-and-spoke: o step .service.ai.AiAgent
e o hub; modelo, memoria e tools sao satelites que NAO entram na cadeia nextSteps — eles se ligam ao
agente por campos *RouteConfigId. O processo de montagem fica em /apipass-integrations:build-agent-flow;
este arquivo e a referencia de cada acao (type/actionId, papel, campo de ligacao, auth, inputData).
Descubra/confirme os types e schemas pelo catalogo, nunca invente:
list_actions(group)lista a familia,get_action_struct(id)traz o schema deinputData, eget_flow_development(flowId)mostra um fluxo real. Grupos de IA:LANGUAGE_MODELS,CHAT_MEMORY,VECTOR_STORE,EMBEDDING,DOCUMENT_LOADER,DOCUMENT_SPLITTER,CHATGPT(+ o tipo core.service.ai.AiAgent).Caveat:
list_actionspode truncar (~40 de N) e nao aplicargroup— os grupos de IA podem nao aparecer na listagem. Para descobrir/confirmar shapes de IA, leia um fluxo real (list_flows(projectId)→get_flow_development(flowId)) ou useget_action(groupId, id)com o id conhecido.
Renderizacao no canvas: endpointDefinitions (gotcha critico)
Os campos *RouteConfigId fazem o fluxo EXECUTAR, mas o designer so DESENHA as arestas de configuracao se
cada no tiver endpointDefinitions. Sem isso o canvas fica quebrado / agente "sem modelo" (mesmo executando ok).
- Hub (agente) e ingestor:
endpointDefinitions: { hasSource: true, targetPosition: "Left", bottomEndpoints: [...] }— as portas de saida (modelo/memoria/tools, ou embedding/loader). - Satelites (modelo, memoria, embedding, splitter, retriever):
endpointDefinitions: { targetPosition: "Top" }(maisbottomEndpointsproprio se tiverem sub-no, ex. retriever→embedding, loader→splitter). labelde porta: use chave i18n REAL (AI_AGENT.MODEL/.MEMORY/.TOOLS,DOCUMENT_LOADER.TEXT_SPLITTER) ou texto literal. Uma chave inventada (ex.VECTOR_STORE.EMBEDDING) aparece crua no canvas — nesse caso prefira literal ("Embedding").- Os shapes canonicos de cada
endpointDefinitionsvem do proprio catalogo (list_actionstrazendpointDefinitionspor acao para os grupos de IA) — copie de la quando disponivel.
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.
- 10d ago First seen · 171 lines · 66 tokens per session scan A 394c4b9d1c05
apipass-agent-actions is a skill published in the GitHub repository APIPASS-Integrations/apipass-headless (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 4,339 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…