review-flow

review-flow is a skill for Claude Code from APIPASS-Integrations/apipass-headless. It costs 112 tokens per session (7,231 once invoked), scanned A, original, Apache-2.0.

A review skill for APIPASS integration workflows. It checks a workflow’s structure, errors, access controls, credentials, JavaScript, SQL, naming, environment variables, timing, and data storage.

In plain words
What is it for?
It helps review an existing APIPASS workflow, inspect its steps and code, and produce findings grouped by severity.
Why use it?
It provides a structured audit of workflow problems instead of relying on a manual, inconsistent inspection.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the apipass-integrations plugin — 13 skills, 2 agents, 1 hook, 1 MCP server shipped together

Good fit It helps review an existing APIPASS workflow, inspect its steps and code, and produce findings grouped by severity.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/apipass-integrations/apipass-headless/review-flow
Install

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.

Any agent
npx skills add APIPASS-Integrations/apipass-headless --skill review-flow
Clone the repo
git clone --depth 1 https://github.com/APIPASS-Integrations/apipass-headless

Made for: Claude Code.

Or install apipass-integrations, the plugin that ships this one along with the rest of its 13 skills, 2 agents, 1 hook, 1 MCP server.

Wrote 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.

agentmods badge for review-flow

README.md
[![agentmods](https://agentmods.dev/badge/skills/apipass-integrations/apipass-headless/review-flow/github.svg)](https://agentmods.dev/skills/apipass-integrations/apipass-headless/review-flow)
Your own site
<a href="https://agentmods.dev/skills/apipass-integrations/apipass-headless/review-flow"><img src="https://agentmods.dev/badge/skills/apipass-integrations/apipass-headless/review-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.

agentmods 80×15 button for review-flow

Your own site · 80×15
<a href="https://agentmods.dev/skills/apipass-integrations/apipass-headless/review-flow"><img src="https://agentmods.dev/badge/skills/apipass-integrations/apipass-headless/review-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,231 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00112 $0.07231
Opus 5 $0.00056 $0.03615
Sonnet 5 $0.00022 $0.01446
Haiku 4.5 $0.00011 $0.00723

Measured 9d ago against content hash 54a7c1027c01, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-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.

plugins/apipass-integrations/skills/review-flow/SKILL.md · 321 lines

How it starts

The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review de Fluxo APIPASS

Audita um fluxo existente contra as convenções e boas práticas da plataforma APIPASS e produz um relatório com findings classificados por severidade.


1. Autenticação

Verificar apipass_auth_status. Se não autenticado, chamar apipass_login antes de continuar.


2. Resolução do Fluxo

  • Se o usuário passou um nome: chamar list_flows e localizar pelo nome (case-insensitive).
  • Se passou um ID: usar diretamente.
  • Se ambíguo: perguntar ao usuário qual fluxo deseja revisar (listar as opções encontradas).

3. Coleta de Dados

Executar em paralelo:

get_flow_development(flowId)          → estrutura completa (steps, counters, logEnabled)
get_flow_info(flowId)                 → metadados (nome, trigger, projeto)
get_published_environments_for_flow(flowId) → environments publicados (para regra S1)

Para fluxos com steps NodeJS ou custom actions, chamar também:

get_custom_action_file(actionId)  → inspecionar código JS (regras JS1–JS6)

Para steps SQL, extrair as queries dos campos rawData/inputData para análise estática (regras SQL1–SQL5) — não requer chamada adicional, os dados já vêm em get_flow_development.

3a. Subfluxos Aninhados

Após coletar o fluxo principal, identificar todos os subfluxos referenciados:

  • RunChildFlow (type: ".utility.runchildflow.RunChildFlow" ou similar): extrair o flowId do subfluxo referenciado no inputData/mappingAttributes.
  • Steps AMS (coreRouteType: "AMS_SEND_MESSAGE"): localizar o fluxo consumidor da fila — geralmente documentado no campo documentation do step ou identificável pelo nome da fila. Localizar via list_flows filtrando pelo nome da fila.

Para cada subfluxo identificado, executar o mesmo ciclo de coleta (get_flow_development, get_flow_info, get_published_environments_for_flow) e aplicar todas as mesmas regras de revisão (seção 4). Reportar os findings de cada subfluxo em seção própria no relatório, identificada pelo nome do subfluxo.

Read the full file on GitHub · 321 lines

Changes

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.

  1. 9d ago First seen · 321 lines · 112 tokens per session scan A 54a7c1027c01

Subscribe to this mod's changes

review-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 112 tokens to every session and 7,231 once invoked, about $0.0006 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.