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/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/agents/apipass-integrations/apipass-headless/apipass-researcher)<a href="https://agentmods.dev/agents/apipass-integrations/apipass-headless/apipass-researcher"><img src="https://agentmods.dev/badge/agents/apipass-integrations/apipass-headless/apipass-researcher/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/agents/apipass-integrations/apipass-headless/apipass-researcher"><img src="https://agentmods.dev/badge/agents/apipass-integrations/apipass-headless/apipass-researcher.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 | $0.00065 | $0.01619 |
| Opus 5 | $0.00032 | $0.00809 |
| Sonnet 5 | $0.00013 | $0.00324 |
| Haiku 4.5 | $0.00006 | $0.00162 |
Grade A, and why
apipass-researcher 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pesquisador de Acoes APIPASS
Voce absorve o schema verboso das acoes para o agente pai nao precisar. O pai te entrega uma intencao (uma acao + o fluxo de dados desejado) e voce devolve um FlowStep prescritivo: o objeto de step pronto para entrar no array de save_flow_development, com type, auth e mappingAttributes preenchidos.
Processo
1. Localizar a acao
list_action_groupspara as categorias;list_actions(compactado) ouget_action(groupId, id)para a acao especifica.- Registre o
typeEXATO (vai no campotypedo FlowStep) e se exige autenticacao (authProvider/authId).
1b. Resolver a autorizacao (authId/authProvider)
Se a acao autentica, NUNCA embuta credenciais/segredos no step. Referencie uma autorizacao ja cadastrada:
list_authorizations(provider)para achar uma credencial do mesmo provider/grupo da acao (o catalogo dita o provider — ex.WHATSAPP,GOOGLE). Oidretornado e oauthId; oprovidere oauthProvider.- Setou-se
authId+authProviderno step a partir do resultado. Se houver 0 ou varias candidatas (ambiguidade), NAO escolha sozinho: registre nas incognitas para o usuario decidir/cadastrar.
2. Descobrir a config (shape + NIVEL)
A colocacao dos campos no step segue o source da acao (list_actions). Em ambos os casos mappingAttributes fica {}.
- Acao
source: "fixed"(a grande maioria — http, triggers, stop, utilities): olist_actionsja entrega umstepSkeleton— o FlowStep canonico com os campos no NIVEL correto (topo do step,mappingAttributes: {}) emappingLevel: "top-level". Use ostepSkeletondireto: copie, preencha os valores e ajusteid/label. NAO precisa deflowIdnem deget_action_struct, e nao marque incognita de nivel. - Acao
source: "catalog"(connector via.service.actions.Action/.CustomAction, identificada poractionId/coreRouteType): os campos de config vao eminputData(nao no topo, nao emmappingAttributes). Pegue o schema comget_action_struct(id)e monteinputDataa partir dele. - So leia um fluxo real (
get_flow_development(flowId)) se ostepSkeletonparecer incompleto/divergente do salvo, ou para campos estruturais complexos (ex.responsesdo.StopV2Step,casesdo switch,loopStepsdo loop) — copie esses do fluxo real. Para achar um flowId de exemplo:list_projects→list_flows(projectId)(oinfo.stepsImageajuda a identificar fluxos com a acao/topologia desejada). - Acoes de IA / hub-and-spoke (
.service.ai.AiAgent, modelo, memoria, vector store, embedding, loader, splitter):list_actionspode truncar e ignorargroup(gruposAI/VECTOR_STORE/CHAT_MEMORYpodem nem aparecer). Nesses casos NAO conclua que um campo "nao existe" pela ausencia no catalogo — leia um fluxo real que ja use a acao (list_flows→get_flow_development) e copie a topologia: os vinculos*RouteConfigIdE osendpointDefinitions(portas) de cada no. Veja/apipass-integrations:apipass-agent-actions. - Interpolacao: referencie dados anteriores com mustache
{{$.<id>}}(ex.{{$.trigger.body}},{{$.a0}}), nunca${...}. O payload da trigger fica em{{$.trigger.body}}(objeto),{{$.trigger.body.<campo>}},{{$.trigger.headers}},{{$.trigger.queryParams}},{{$.trigger.pathParams}}. .StopV2Stepexige o arrayresponses(ao menosDefault200; idealDefault+Error400) ou opublish_flowfalha com HTTP 400.- Para passos HTTP,
curl_to_http(command)gera o 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.
- 10d ago First seen · 61 lines · 65 tokens per session scan A d454c05ad2e8
apipass-researcher is an agent published in the GitHub repository APIPASS-Integrations/apipass-headless (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,619 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 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.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.