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 research-actiongit 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/research-action)<a href="https://agentmods.dev/skills/apipass-integrations/apipass-headless/research-action"><img src="https://agentmods.dev/badge/skills/apipass-integrations/apipass-headless/research-action/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/research-action"><img src="https://agentmods.dev/badge/skills/apipass-integrations/apipass-headless/research-action.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 | $0.00041 | $0.00750 |
| Opus 5 | $0.00020 | $0.00375 |
| Sonnet 5 | $0.00008 | $0.00150 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
research-action 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pesquisar Acao: $ARGUMENTS
Para builds reais, prefira delegar ao subagent apipass-researcher (ele absorve o schema verboso e devolve um passo pronto). Use este processo direto para buscas triviais.
Pare e pergunte se
- O
get_action_structnao revelar os campos/valores. - Houver campos ambiguos (status, tipo, prioridade) sem valores claros.
- A autenticacao da acao for incerta.
Passo 1: Localizar a acao
list_action_groupspara ver as categorias.list_actions(catalogo completo — vem compactado) ouget_action(groupId, id)para uma acao especifica.- Registre o
typeEXATO da acao (e o que vai no campotypedo FlowStep) e se ela exige autenticacao (authProvider/authId).
Passo 1b: Resolver a autorizacao (se a acao autentica)
- Nunca embuta credenciais no step — referencie uma autorizacao por
authId+authProvider. list_authorizations(provider)acha credenciais do provider/grupo da acao;id=>authId,provider=>authProvider. Filtre porprojectIdquando aplicavel.get_authorization(id)detalha;get_authorization_interpolation_fields(id)lista campos interpolaveis (use via{{...}}em headers/params, sem expor o segredo).- 0 ou varias candidatas = ambiguidade: registre nas incognitas para o usuario decidir/cadastrar.
Passo 2: Descobrir o shape da config
- Prefira ler um fluxo real que ja usa essa acao:
get_flow_development(flowId)e copie o shape exato — isso revela tambem o NIVEL onde cada campo mora (topo do step vs dentro demappingAttributes), que o struct nao garante. Sempre que possivel, peca/use umflowIdde exemplo. get_action_struct(id)lista QUAIS campos a acao tem (util como referencia), mas: pode 404 em acoesfixed/embutidas (ex..trigger.rest.RestTrigger) e nao diz em que nivel os campos aparecem no step salvo.- Atencao: em muitas acoes (ex.
.service.http.HttpRequest) a config fica no nivel superior do step (url,method,rawData, ...) commappingAttributes: {}. O corpo HTTP vai emrawData. - Interpolacao entre passos: mustache
{{$.<id>}}(ex.{{$.trigger.body}}), nunca${...}. - Para passos HTTP,
curl_to_http(command)converte um cURL em request pronto.
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 · 40 lines · 41 tokens per session scan A 07cf96eb61dd
research-action is a skill published in the GitHub repository APIPASS-Integrations/apipass-headless (2 stars, last pushed 29d ago), licensed Apache-2.0. It adds 41 tokens to every session and 750 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 2026-08-31.
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…