AI agent plugins for architecture governance, risk management, TDD enforcement, and delivery quality by Windy Road Technology.
Install everything with one command:
npx @windyroad/agent-plugins
Or install only what you need:
npx @windyroad/agent-plugins --plugin architect tdd risk-scorer
Or install individual packages directly:
npx @windyroad/architect
npx @windyroad/c4
Restart Claude Code after installing. Type /wr: to see all available skills.
These plugins enforce review workflows via hooks. They block edits to relevant files until the appropriate review agent has been consulted.
| Package | Plugin | Agent | Skills | What it enforces |
|---|---|---|---|---|
@windyroad/architect | wr-architect | wr-architect:agent | /wr:adr | Architecture decisions reviewed before code changes |
@windyroad/risk-scorer | wr-risk-scorer | wr-risk-scorer:agent + 4 variants | /wr:risk-policy | Pipeline risk scoring, commit/push gates, secret leak detection |
@windyroad/voice-tone | wr-voice-tone | wr-voice-tone:agent | /wr:voice-tone | User-facing copy reviewed against voice and tone guide |
@windyroad/style-guide | wr-style-guide | wr-style-guide:agent | /wr:style-guide | CSS and UI components reviewed against style guide |
@windyroad/jtbd | wr-jtbd | wr-jtbd:agent | /wr:jtbd | UI changes reviewed against jobs-to-be-done document |
@windyroad/tdd | wr-tdd | /wr:tdd | Red-Green-Refactor TDD cycle enforced for implementation code |
When a policy file is missing (e.g., no docs/VOICE-AND-TONE.md), the hooks block edits and direct you to the create skill to generate one.
| Package | Plugin | Skills | What it does |
|---|---|---|---|
@windyroad/problem | wr-problem | /wr:problem | ITIL-aligned problem management with WSJF prioritisation |
@windyroad/retrospective | wr-retrospective | /wr:retrospective | Session retrospectives that update briefings and create problem tickets |
| Package | Plugin | Skills | What it does |
|---|---|---|---|
@windyroad/c4 | wr-c4 | /wr:c4, /wr:c4-check | C4 architecture diagram generation and validation |
@windyroad/wardley | wr-wardley | /wr:wardley | Wardley Map generation |
Some plugins depend on others:
The installer warns if dependencies are missing.
# Update everything
npx @windyroad/agent-plugins --update
# Update a single package
npx @windyroad/architect --update
# Remove everything
npx @windyroad/agent-plugins --uninstall
# Remove a single plugin
npx @windyroad/architect --uninstall
For plugin development, use --plugin-dir to load directly from source:
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/update needed).
packages/
agent-plugins/ @windyroad/agent-plugins (meta-installer)
architect/ @windyroad/architect
risk-scorer/ @windyroad/risk-scorer
tdd/ @windyroad/tdd
voice-tone/ @windyroad/voice-tone
style-guide/ @windyroad/style-guide
jtbd/ @windyroad/jtbd
problem/ @windyroad/problem
retrospective/ @windyroad/retrospective
c4/ @windyroad/c4
wardley/ @windyroad/wardley
shared/ Shared install utilities
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub windyroad/agent-plugins --plugin wr-tddWardley Map generation for Claude Code
Style guide enforcement for Claude Code
Voice and tone enforcement for Claude Code
Session retrospective reminders and plan review for Claude Code
C4 architecture diagram generation and validation for Claude Code
Automated Test-Driven Development enforcement
Strict red-green-refactor TDD loop. Failing test, then minimum code, then refactor. Commits after each cycle.
Test-driven development skill that enforces red-green-refactor, one test at a time
Test-driven development methodology with red-green-refactor cycles and code review
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Memory compression system for Claude Code - persist context across sessions