CodexPluginStats
← Claude plugins
CLAUDE PLUGIN

wicked-garden

Mike Parcewski v3.9.0

Wicked Garden — AI-Native SDLC A full software development lifecycle as a single Claude Code plugin. 14 domains, 80 specialist agents, 152 commands — covering everything from requirements through ...

Create a free account to save this plugin.

From the developer

License

MIT

Works with

Claude Code

Description

From the marketplace listing

Wicked Garden — AI-Native SDLC A full software development lifecycle as a single Claude Code plugin. 14 domains, 80 specialist agents, 152 commands — covering everything from requirements through production operations. What makes it different from a good CLAUDE.md: it's executable infrastructure, not passive guidance. Hooks enforce workflow gates before Claude sees your prompt. Context from memory, search, and project state is assembled automatically on every turn. Decisions persist across sessions. Quality gates actually block progression when evidence is missing. Works standalone with zero external dependencies. Local SQLite storage. No API keys, no cloud services, no setup beyond install. Core systems: - Crew — Signal-driven project workflows with 8 phases (clarify → design → build → test → review → operate), 7-dimension complexity scoring, hard-enforced quality gates, and multi-perspective consensus review for high-stakes decisions - Smaht — Automatic context assembly on every prompt via 3-tier routing (hot/fast/slow). Surfaces relevant memories, code search results, kanban state, and crew context without you asking - Mem — 3-tier persistent memory (working → episodic → semantic) with auto-consolidation, tag-based search, and access-frequency ranking. Decisions from month-old sessions surface when relevant - Search — Code intelligence with symbol search, blast radius analysis, data lineage tracing, and service map discovery - Jam — AI brainstorming with dynamic persona focus groups and multi-model council sessions using installed LLM CLIs (Codex, Gemini, Copilot) Plus specialist agents for engineering, product, platform/DevSecOps, QE, data, delivery, agentic architecture, and on-demand personas.

Source repository ↗ Website ↗

What changed

No changes recorded yet. Follow this plugin to keep track of future changes.

Keywords

Files & skills

wicked-garden · catalog manifest

Saved declaration

{}
wicked-garden · catalog manifest

Saved declaration

{
  "name": "wicked-garden",
  "source": {
    "sha": "ba0a6ca91029ffe032977b0ebdce2461bf6de49e",
    "url": "https://github.com/mikeparcewski/wicked-garden.git",
    "source": "url"
  },
  "homepage": "https://github.com/mikeparcewski/wicked-garden",
  "description": "Wicked Garden — AI-Native SDLC\n\nA full software development lifecycle as a single Claude Code plugin. 14 domains, 80 specialist agents, 152 commands — covering everything from requirements through production operations.\n\nWhat makes it different from a good CLAUDE.md: it's executable infrastructure, not passive guidance. Hooks enforce workflow gates before Claude sees your prompt. Context from memory, search, and project state is assembled automatically on\nevery turn. Decisions persist across sessions. Quality gates actually block progression when evidence is missing.\n\nWorks standalone with zero external dependencies. Local SQLite storage. No API keys, no cloud services, no setup beyond install.\n\nCore systems:\n\n- Crew — Signal-driven project workflows with 8 phases (clarify → design → build → test → review → operate), 7-dimension complexity scoring, hard-enforced quality gates, and multi-perspective consensus review for high-stakes decisions\n- Smaht — Automatic context assembly on every prompt via 3-tier routing (hot/fast/slow). Surfaces relevant memories, code search results, kanban state, and crew context without you asking\n- Mem — 3-tier persistent memory (working → episodic → semantic) with auto-consolidation, tag-based search, and access-frequency ranking. Decisions from month-old sessions surface when relevant\n- Search — Code intelligence with symbol search, blast radius analysis, data lineage tracing, and service map discovery\n- Jam — AI brainstorming with dynamic persona focus groups and multi-model council sessions using installed LLM CLIs (Codex, Gemini, Copilot)\n\nPlus specialist agents for engineering, product, platform/DevSecOps, QE, data, delivery, agentic architecture, and on-demand personas."
}
wicked-garden · catalog manifest

Saved declaration

{
  "name": "wicked-garden",
  "author": {
    "name": "Mike Parcewski"
  },
  "license": "MIT",
  "version": "3.9.0",
  "keywords": [
    "sdlc",
    "workflow",
    "engineering",
    "testing",
    "delivery",
    "memory",
    "search",
    "brainstorming",
    "personas",
    "code-intelligence",
    "kanban",
    "agentic"
  ],
  "repository": "https://github.com/mikeparcewski/wicked-garden",
  "description": "AI-Native SDLC — executable infrastructure, not passive guidance. Hooks enforce workflow gates, assemble context from memory and code search on every prompt, and persist decisions across sessions. 14 domains with 80 specialist agents cover the full lifecycle: signal-driven crew workflows with hard quality gates, 3-tier persistent memory with auto-consolidation, structural code intelligence, multi-model brainstorming, and domain experts for security, architecture, QE, product, data, and delivery. Zero external dependencies — runs standalone with local SQLite storage.",
  "_future_channels": {
    "jira": {
      "auth": "oauth2",
      "type": "rest-api",
      "description": "Jira issue tracker for bi-directional sync with kanban domain",
      "capabilities": [
        "read-issues",
        "write-issues",
        "webhooks"
      ]
    },
    "slack": {
      "auth": "webhook-url",
      "type": "webhook",
      "description": "Slack notifications for crew phase completions and gate failures",
      "capabilities": [
        "send-messages"
      ]
    },
    "github": {
      "auth": "token",
      "type": "rest-api",
      "description": "GitHub for issue triage, PR creation, and CI status",
      "capabilities": [
        "read-issues",
        "write-issues",
        "read-prs",
        "write-prs",
        "read-checks"
      ]
    },
    "linear": {
      "auth": "api-key",
      "type": "rest-api",
      "description": "Linear issue tracker for bi-directional sync with kanban domain",
      "capabilities": [
        "read-issues",
        "write-issues",
        "webhooks"
      ]
    },
    "_comment": "Issue #348: channels field is not yet supported in plugin.json schema. When Claude Code adds channel support, move these declarations to a top-level channels block. Channels formalize external service connections with discovery and auth."
  },
  "_future_lspServers": {
    "_comment": "Issue #347: lspServers field enables Language Server Protocol integration for richer code intelligence (go-to-definition, find-references, hover, diagnostics). When Claude Code adds lspServers support to plugins, investigate integrating with the search/CIQ domain for enhanced symbol resolution. Candidate servers: TypeScript (typescript-language-server), Python (pyright), Rust (rust-analyzer)."
  },
  "_future_userConfig": {
    "_comment": "Issue #335, #346: userConfig is not yet supported in plugin.json schema. When Claude Code adds userConfig support, move these fields out of _future_userConfig and into a top-level userConfig block. This would replace the manual /wicked-garden:setup flow.",
    "log_level": {
      "enum": [
        "debug",
        "info",
        "warn",
        "error"
      ],
      "type": "string",
      "default": "info",
      "description": "Verbosity level for operational logs"
    },
    "storage_mode": {
      "enum": [
        "local",
        "sqlite"
      ],
      "type": "string",
      "default": "local",
      "description": "Where to persist plugin state: local JSON files or SQLite with FTS5"
    },
    "jira_api_token": {
      "type": "string",
      "_comment": "Issue #346: When userConfig supports sensitive:true, this field should use it to store the token in the OS keychain rather than plaintext.",
      "sensitive": true,
      "description": "Jira API token for issue sync (stored in OS keychain when sensitive flag is supported)"
    },
    "linear_api_token": {
      "type": "string",
      "sensitive": true,
      "description": "Linear API token for issue sync (stored in OS keychain when sensitive flag is supported)"
    },
    "slack_webhook_url": {
      "type": "string",
      "sensitive": true,
      "description": "Slack webhook URL for notifications (stored in OS keychain when sensitive flag is supported)"
    },
    "onboarding_preference": {
      "enum": [
        "auto",
        "manual",
        "skip"
      ],
      "type": "string",
      "default": "auto",
      "description": "How to handle first-run onboarding: auto-detect and configure, prompt user, or skip"
    }
  },
  "_future_outputStyles": {
    "_comment": "Issue #338: outputStyles field is not yet supported as a configuration block in plugin.json. When Claude Code adds outputStyles support, move these declarations to a top-level outputStyles block or the ./styles/ directory. These define domain-specific formatting for different work modes.",
    "crew-phase": {
      "format": "markdown",
      "sections": [
        "phase-header",
        "deliverables",
        "gate-result",
        "evidence-summary"
      ],
      "description": "Structured output for crew workflow phases with phase headers, gate results, and evidence summaries"
    },
    "qe-results": {
      "format": "markdown",
      "sections": [
        "summary",
        "results-table",
        "failure-analysis",
        "coverage"
      ],
      "description": "Test execution results with pass/fail counts, coverage, and failure analysis"
    },
    "delivery-report": {
      "format": "markdown",
      "sections": [
        "velocity",
        "risks",
        "forecast",
        "recommendations"
      ],
      "description": "Delivery metrics report with velocity charts, risk indicators, and forecast"
    },
    "engineering-review": {
      "format": "markdown",
      "sections": [
        "summary",
        "findings-by-severity",
        "file-annotations",
        "action-items"
      ],
      "description": "Code review output with severity-tagged findings, file annotations, and action items"
    },
    "brainstorm-synthesis": {
      "format": "markdown",
      "sections": [
        "perspectives",
        "convergence",
        "divergence",
        "next-steps"
      ],
      "description": "Jam session output with perspectives, convergence points, and actionable next steps"
    }
  }
}

plugin.json observed Nov 6, 2026 · 10:51 UTC. Manifest source ↗

Catalog declarations and available plugin.json metadata are saved. Referenced skills and executable source files are not downloaded or tested. Missing components in a manifest do not prove that the plugin has none.

Installation instructions

Community

/plugin marketplace add anthropics/claude-plugins-community
/plugin install wicked-garden@claude-community

Claude Code installation documentation

Technical details
Sources
Community
First seen
Oct 3, 2026 · 22:13 UTC
Last seen
Nov 9, 2026 · 06:00 UTC
Latest observed change
Oct 3, 2026 · 22:13 UTC
Collection status
Listed
Reported installs
Not provided

Installation counts are source-reported, not independently verified active users. Observation dates are not release dates.

Download plugin data (JSON)

Plugin history: freshly prepared. Prepared . Refreshed when catalog data changes or after 6 hours. Your account and Follow status are live.