feat: add agent-ready plugin

.claude-plugin/marketplace.json

@@ -52,6 +52,12 @@
       "source": "./plugins/codebase-readiness",
       "description": "Score your codebase's readiness for autonomous AI agent work across 8 dimensions, framed around the Stripe benchmark of 1k+ AI-generated PRs per week",
       "version": "1.5.0"
+    },
+    {
+      "name": "agent-ready",
+      "source": "./plugins/agent-ready",
+      "description": "Make a codebase agent-ready by scaffolding CLAUDE.md, ARCHITECTURE.md, and docs/ structure following progressive disclosure patterns",
+      "version": "1.0.0"
     }
   ]
 }

README.md

@@ -36,6 +36,8 @@ The [Codebase Readiness](plugins/codebase-readiness/README.md) plugin scores you
 
 You get a band rating (Agent-Ready → Not Agent-Ready), a concrete improvement roadmap, and an optional saved report to share with your team. Not opinions — evidence gathered from your actual codebase.
 
+Once you have your score, the [agent-ready](plugins/agent-ready/README.md) plugin fixes the documentation gaps automatically: CLAUDE.md, ARCHITECTURE.md, and docs/ structure following progressive disclosure patterns.
+
 [Learn more →](plugins/codebase-readiness/README.md) | [See the full assessment details](https://www.damiangalarza.com/codebase-readiness/?utm_source=github&utm_medium=readme&utm_campaign=codebase-readiness) | [Want help improving your score?](https://www.damiangalarza.com/services/ai-enablement/?utm_source=github&utm_medium=readme&utm_campaign=claude-code-workflows)
 
 ---
@@ -45,6 +47,7 @@ You get a band rating (Agent-Ready → Not Agent-Ready), a concrete improvement
 | Skill | Description |
 |-------|-------------|
 | [Codebase Readiness](plugins/codebase-readiness/README.md) | Score your repo's readiness for autonomous AI agent work |
+| [Agent Ready](plugins/agent-ready/README.md) | Fix documentation gaps: scaffold CLAUDE.md, ARCHITECTURE.md, and docs/ |
 | [TDD Workflow](plugins/tdd-workflow/README.md) | Test-driven development, one test at a time |
 | [Conventional Commits](plugins/conventional-commits/README.md) | Structured commit messages |
 | [Parallel Code Review](plugins/parallel-code-review/README.md) | Multi-agent code reviews |

plugins/agent-ready/.claude-plugin/plugin.json

@@ -0,0 +1,20 @@
+{
+  "name": "agent-ready",
+  "version": "1.0.0",
+  "description": "Make a codebase agent-ready by scaffolding CLAUDE.md, ARCHITECTURE.md, and docs/ structure following progressive disclosure patterns",
+  "author": {
+    "name": "Damian Galarza",
+    "url": "https://www.damiangalarza.com"
+  },
+  "repository": "https://github.com/dgalarza/claude-code-workflows",
+  "license": "MIT",
+  "keywords": [
+    "ai",
+    "agents",
+    "documentation",
+    "architecture",
+    "claude-md",
+    "progressive-disclosure",
+    "scaffolding"
+  ]
+}

plugins/agent-ready/README.md

@@ -0,0 +1,44 @@
+# agent-ready
+
+Make a codebase agent-ready by scaffolding CLAUDE.md, ARCHITECTURE.md, and docs/ structure following progressive disclosure patterns.
+
+This is the **remediation companion** to [codebase-readiness](../codebase-readiness/). While codebase-readiness *scores* how agent-ready your codebase is, agent-ready *fixes* the gaps by generating the documentation and structural artifacts that make a codebase legible to AI agents.
+
+## Install
+
+```
+/plugin marketplace add dgalarza/claude-code-workflows
+/plugin install agent-ready@dgalarza-workflows
+```
+
+## Modes
+
+| Mode | What It Does | Example Prompt |
+|------|-------------|----------------|
+| **scaffold** | Full documentation setup: docs/ structure, ARCHITECTURE.md, CLAUDE.md, starter ADR | "Make this codebase agent-ready" |
+| **architecture** | Generate ARCHITECTURE.md from actual codebase analysis | "Create an ARCHITECTURE.md" |
+| **claude-md** | Create or refactor CLAUDE.md for progressive disclosure | "Set up CLAUDE.md" |
+| **audit** | Check existing agent-readiness artifacts for staleness and coherence | "Are my agent docs up to date?" |
+
+## Principles
+
+Built on two key sources:
+
+- **Harness Engineering (OpenAI)** -- repository as system of record, progressive disclosure, CLAUDE.md as table of contents not encyclopedia, enforce invariants not implementations
+- **matklad's ARCHITECTURE.md** -- bird's-eye codemap, name important modules, call out invariants (especially absences), point out boundaries
+
+## Integration with codebase-readiness
+
+If an `AGENT_READY_ASSESSMENT.md` exists from a prior codebase-readiness assessment, agent-ready will read it and auto-suggest which mode to run first based on the weakest dimensions.
+
+**Recommended workflow:**
+
+1. Run [codebase-readiness](../codebase-readiness/) to score your repo and identify gaps
+2. Run agent-ready to fix the documentation and structure gaps automatically
+3. Re-run the assessment to measure improvement
+
+[What each dimension means and why it matters →](https://www.damiangalarza.com/codebase-readiness/?utm_source=github&utm_medium=readme&utm_campaign=agent-ready)
+
+## Want Help Beyond Documentation?
+
+Built by [Damian Galarza](https://www.damiangalarza.com?utm_source=github&utm_medium=readme&utm_campaign=agent-ready). Documentation is one dimension. If your assessment surfaced gaps across test infrastructure, architecture, or team adoption, the [AI Workflow Enablement Program](https://www.damiangalarza.com/services/ai-enablement/?utm_source=github&utm_medium=readme&utm_campaign=agent-ready) works through all of it on your actual codebase.