convez.ai
AgenteDevOps & InfraestruturaAvançado
windyroad

Windy Road Agent Plugins

windyroad/agent-plugins

Governança automática para agentes de código Claude

Ver no GitHub
InicialPluginScore · de 0 a 100

Conjunto de plugins de governança para agentes de código Claude que enforçam padrões arquiteturais, testes, avaliação de risco e qualidade de entrega automaticamente. Intercepta ações no Claude Code e bloqueia edições até que revisões obrigatórias sejam completadas, trazendo guardrails de governança corporativa para desenvolvimento acelerado por IA.

Instalação

$npx convez-ai windyroad/agent-plugins

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
6
Forks
1
Acompanhando
0
Saúde
62%
Último commit
há 1 dia
Versão
@windyroad/itil@3.7.7
Issues abertas
92
Contribuidores
3

Casos de uso

  • Enforçar revisões arquiteturais antes de mudanças de código
  • Implementar ciclos TDD obrigatórios em agents de IA
  • Avaliar e bloquear commits com risco elevado ou vazamento de secrets
  • Revisar mudanças de UI contra guias de estilo e jobs-to-be-done
  • Gerenciar incidentes e problemas com rastreamento ITIL

Veredito

Solução madura e pragmática para times que já usam Claude Code e precisam de controles de qualidade em escala. Excelente para organizações com standards estritos, mas requer investimento inicial em políticas documentadas e configuração por projeto.

README

A tradução para o português deste README ainda está na fila.

Windy Road Agent Plugins

Governance guardrails for AI coding agents. Architecture reviews, risk scoring, TDD enforcement, and delivery quality gates that run automatically inside Claude Code.

Built by Windy Road Technology.

The Problem

AI coding agents are fast. Sometimes too fast. They skip architecture reviews, introduce risk without assessment, ignore your design system, and write implementation before tests. The same governance that keeps human teams shipping safely gets bypassed when an agent writes code.

These plugins bring that governance back -- automatically. They hook into Claude Code's plugin system and enforce your team's standards on every edit, commit, and push. No manual checks. No hoping the agent remembers.

Quick Start

Install all plugins with one command:

npx @windyroad/agent-plugins

Restart Claude Code. That's it. The plugins activate automatically based on what they find in your project.

Install only what you need:

npx @windyroad/agent-plugins --plugin architect tdd risk-scorer

Or install a single plugin directly:

npx @windyroad/architect

Plugins install to your project by default (not globally), so they won't affect your other projects. Pass --scope user to install globally.

After installing, type /wr- in Claude Code to see all available skills.

How It Works

Each plugin uses Claude Code's hook system to intercept actions at the right moment:

  1. Detect -- A UserPromptSubmit hook scans for relevant project files (e.g., docs/decisions/ for architect, RISK-POLICY.md for risk-scorer)
  2. Gate -- A PreToolUse hook blocks edits to relevant files until the review agent has been consulted
  3. Review -- The agent reviews the proposed change against your project's policy documents
  4. Unlock -- A PostToolUse hook marks the review as complete, allowing edits to proceed

Policy files are generated for you. When a plugin detects that its policy file is missing, it blocks edits and directs you to the setup skill (e.g., /wr-voice-tone:update-guide).

Plugins

Governance and Quality Gates

These plugins enforce review workflows. They block edits to relevant files until the appropriate review agent has been consulted.

PackageWhat it enforces
@windyroad/architectArchitecture decisions reviewed before code changes
@windyroad/risk-scorerPipeline risk scoring, commit/push gates, secret leak detection
@windyroad/tddRed-Green-Refactor TDD cycle for implementation code
@windyroad/voice-toneUser-facing copy reviewed against voice and tone guide
@windyroad/style-guideCSS and UI components reviewed against style guide
@windyroad/jtbdUI changes reviewed against jobs-to-be-done document

Process Tools

PackageWhat it does
@windyroad/itilITIL-aligned IT service management — problem management (WSJF-prioritised) and evidence-first incident management with automatic handoff
@windyroad/retrospectiveSession retrospectives that update briefings and create problem tickets
@windyroad/connectCross-repo agent collaboration via Discord channels (experimental — see plugin README)

Diagram Generation

PackageWhat it does
@windyroad/c4C4 architecture diagram generation and validation
@windyroad/wardleyWardley Map generation from source code analysis

Meta-Installer

PackageWhat it does
@windyroad/agent-pluginsOne-command installer for all plugins

Dependencies Between Plugins

Most plugins are standalone. Two have dependencies:

@windyroad/retrospective
  └── @windyroad/itil
        └── @windyroad/risk-scorer

The installer warns if dependencies are missing.

Jobs to be Done

Each plugin's value framing is anchored to documented Jobs to be Done — persona-grouped jobs that describe what user pain the plugin removes, not just what features it ships. Per ADR-051, every @windyroad/* plugin README cites at least one current JTBD job ID so the README is a navigable index into the JTBD research, not just a feature list.

PersonaPrimary jobsPlugins serving this persona
Developer — uses AI agents solo, in a small team, or on a larger software development teamJTBD-001 Enforce Governance Without Slowing Down, JTBD-002 Ship with Confidence, JTBD-003 Compose Only the Guardrails I Need, JTBD-006 Progress the Backlog While I'm Away, JTBD-007 Keep Plugins Current Across Projectsarchitect, risk-scorer, tdd, jtbd, voice-tone, style-guide, retrospective, agent-plugins
Tech lead / consultant — accountable for code quality across teams or client engagementsJTBD-201 Restore Service Fast with an Audit Trail, JTBD-202 Pre-Flight Governance Checks Before Releaseitil, architect, risk-scorer, c4, wardley
Plugin developer — extends the suite with new pluginsJTBD-101 Extend the Suite with New Pluginsarchitect, agent-plugins, c4, wardley
Plugin user — installed a plugin and hit a problem; reporting is incidental to their primary workJTBD-301 Report a Problem Without Pre-Classifying It, JTBD-302 Trust That the README Describes the Plugin I Just Installeditil (intake surface), every plugin (README currency)

See docs/jtbd/README.md for the full index.

Risk Management

This suite follows ISO 31000 / ISO 27001 risk management practice. Risk criteria, impact and likelihood scales, appetite, and the matrix are defined in RISK-POLICY.md. Standing risks the suite tolerates and treats are tracked in the risk register. Per-change pipeline risk is scored on every commit, push, and release by @windyroad/risk-scorer and snapshotted to .risk-reports/ for audit purposes.

Updating and Uninstalling

# Update everything
npx @windyroad/agent-plugins --update

# Update a single plugin
npx @windyroad/architect --update

# Remove everything
npx @windyroad/agent-plugins --uninstall

# Remove a single plugin
npx @windyroad/architect --uninstall

Development

For plugin development, load directly from source with --plugin-dir:

claude --plugin-dir ~/Projects/windyroad-agent-plugins/packages/architect

Or load all plugins at once:

./claude-wr.sh

Changes take effect on session restart -- no install or update step needed.

Running Tests

Hook tests use BATS (Bash Automated Testing System):

npm test

Releasing

This monorepo uses Changesets for versioning:

npx changeset        # Create a changeset
npm run release      # Publish to npm
npm run push:watch   # Push and watch CI

Monorepo Structure

packages/
  agent-plugins/    Meta-installer for all plugins
  architect/        Architecture decision enforcement
  risk-scorer/      Pipeline risk scoring and gates
  tdd/              TDD state machine enforcement
  voice-tone/       Voice and tone review
  style-guide/      Style guide review
  jtbd/             Jobs-to-be-done review
  itil/             ITIL problem and incident management
  retrospective/    Session retrospectives
  connect/          Cross-repo agent collaboration via Discord
  c4/               C4 diagram generation
  wardley/          Wardley Map generation
  shared/           Shared install utilities (internal)

Licence

MIT

Ver o original no GitHub

Bom para

Relacionados