@mthanhlm/autodev 0.3.4 → 0.3.5

package/.claude-plugin/plugin.json

@@ -0,0 +1,9 @@
+{
+  "name": "autodev",
+  "description": "A lean Claude Code workflow system with a single entrypoint, task-based phase execution, and read-only git.",
+  "version": "0.3.5",
+  "author": {
+    "name": "mthanhlm"
+  },
+  "license": "MIT"
+}

package/PUBLISH.md

@@ -20,6 +20,7 @@ npm whoami
 ```bash
 cd autodev
 npm test
+claude plugin validate .
 npm pack
 ```
 
@@ -73,3 +74,9 @@ Open Claude Code in that directory and run:
 ```text
 /autodev-help
 ```
+
+Optional source-tree check during development:
+
+```bash
+claude --plugin-dir . agents
+```

package/README.md

@@ -4,7 +4,7 @@
 
 ## What It Does
 
-- Installs a small Claude Code workflow under `~/.claude/` or `./.claude/`
+- Installs a standalone Claude Code workflow under `~/.claude/` or `./.claude/`
 - Keeps project state in `.autodev/`
 - Uses `/autodev` as the main command
 - Organizes work as `project -> track -> phase -> tasks`
@@ -24,6 +24,9 @@
 
 ## Install
 
+Primary supported usage is the standalone `npx` installer.
+The repo also carries Claude Code plugin metadata for validation and local development, but the supported end-user runtime remains the installed `.claude/` workflow.
+
 ```bash
 npx @mthanhlm/autodev@latest --global
 ```

package/agents/autodev-codebase-domain.md

@@ -1,3 +1,10 @@
+---
+name: autodev-codebase-domain
+description: Product and domain mapper for brownfield exploration. Use proactively when mapping an existing codebase and writing `.autodev/codebase/domain.md`.
+tools: Read, Grep, Glob, Bash, Write
+model: inherit
+---
+
 # autodev-codebase-domain
 
 You are responsible for `.autodev/codebase/domain.md`.

package/agents/autodev-codebase-quality.md

@@ -1,3 +1,10 @@
+---
+name: autodev-codebase-quality
+description: Testing and technical-debt mapper for brownfield exploration. Use proactively when mapping an existing codebase and writing `.autodev/codebase/quality.md`.
+tools: Read, Grep, Glob, Bash, Write
+model: inherit
+---
+
 # autodev-codebase-quality
 
 You are responsible for `.autodev/codebase/quality.md`.

package/agents/autodev-codebase-runtime.md

@@ -1,3 +1,10 @@
+---
+name: autodev-codebase-runtime
+description: Runtime and dependency mapper for brownfield exploration. Use proactively when mapping an existing codebase and writing `.autodev/codebase/runtime.md`.
+tools: Read, Grep, Glob, Bash, Write
+model: inherit
+---
+
 # autodev-codebase-runtime
 
 You are responsible for `.autodev/codebase/runtime.md`.

package/agents/autodev-codebase-structure.md

@@ -1,3 +1,10 @@
+---
+name: autodev-codebase-structure
+description: Repository structure mapper for brownfield exploration. Use proactively when mapping an existing codebase and writing `.autodev/codebase/structure.md`.
+tools: Read, Grep, Glob, Bash, Write
+model: inherit
+---
+
 # autodev-codebase-structure
 
 You are responsible for `.autodev/codebase/structure.md`.

package/agents/autodev-review-integration.md

@@ -1,3 +1,10 @@
+---
+name: autodev-review-integration
+description: Integration review specialist for executed phases. Use proactively after code changes to find cross-module regressions and wiring mistakes.
+tools: Read, Grep, Glob, Bash
+model: inherit
+---
+
 # autodev-review-integration
 
 Review the executed phase for integration and regression risk.

package/agents/autodev-review-polish.md

@@ -1,3 +1,10 @@
+---
+name: autodev-review-polish
+description: Product polish review specialist for executed phases. Use proactively after code changes to find rough UX, copy, and finish issues.
+tools: Read, Grep, Glob, Bash
+model: inherit
+---
+
 # autodev-review-polish
 
 Review the executed phase for product polish and obvious AI-generated roughness.

package/agents/autodev-review-quality.md

@@ -1,3 +1,10 @@
+---
+name: autodev-review-quality
+description: Quality review specialist for executed phases. Use proactively after code changes to find correctness, maintainability, and test issues.
+tools: Read, Grep, Glob, Bash
+model: inherit
+---
+
 # autodev-review-quality
 
 Review the executed phase for code quality.

package/agents/autodev-review-security.md

@@ -1,3 +1,10 @@
+---
+name: autodev-review-security
+description: Security review specialist for executed phases. Use proactively after code changes to find auth, input-handling, and trust-boundary issues.
+tools: Read, Grep, Glob, Bash
+model: inherit
+---
+
 # autodev-review-security
 
 Review the executed phase for security and misuse risks.

package/agents/autodev-task-worker.md

@@ -1,3 +1,10 @@
+---
+name: autodev-task-worker
+description: Single-task implementation worker for autodev phases. Use proactively when one `.autodev` task should run in a fresh agent context and produce its matching `TASK-NN-SUMMARY.md`.
+tools: Read, Grep, Glob, Bash, Edit, Write
+model: inherit
+---
+
 # autodev-task-worker
 
 Execute one assigned task inside the current phase and report back to the main phase session.

package/autodev/workflows/autodev.md

@@ -15,19 +15,20 @@ Use `/autodev` as the single entrypoint for the normal workflow. Route automatic
 1. Run:
 
 ```bash
-node "$HOME/.claude/autodev/bin/autodev-tools.cjs" status
+AUTODEV_ROOT="${CLAUDE_PLUGIN_ROOT:-$HOME/.claude}"
+node "$AUTODEV_ROOT/autodev/bin/autodev-tools.cjs" status
 ```
 
 2. Inspect the returned `route.kind`, `project_type`, `tracks`, and active track data.
 
 3. Route as follows:
-   - `init_project`: read `@~/.claude/autodev/workflows/new-project.md`, then perform that workflow.
-   - `explore_codebase`: read `@~/.claude/autodev/workflows/explore-codebase.md`, then perform that workflow.
-   - `plan_phase`: read `@~/.claude/autodev/workflows/plan-phase.md`, then perform that workflow.
-   - `plan_review`: read `@~/.claude/autodev/workflows/review-plan.md`, then perform that workflow so the user can review the phase plan before any execution starts.
-   - `execute_phase`: read `@~/.claude/autodev/workflows/execute-phase.md`, then perform that workflow, which should advance one task-sized unit in the current phase session by trying a fresh worker agent first and falling back cleanly when agent delegation is unavailable.
-   - `review_phase`: read `@~/.claude/autodev/workflows/review-phase.md`, then perform that workflow.
-   - `verify_phase`: read `@~/.claude/autodev/workflows/verify-work.md`, then perform that workflow.
+   - `init_project`: load and perform the new-project workflow.
+   - `explore_codebase`: load and perform the explore-codebase workflow.
+   - `plan_phase`: load and perform the plan-phase workflow.
+   - `plan_review`: load and perform the review-plan workflow so the user can review the phase plan before any execution starts.
+   - `execute_phase`: load and perform the execute-phase workflow, which should advance one task-sized unit in the current phase session by trying a fresh worker agent first and falling back cleanly when agent delegation is unavailable.
+   - `review_phase`: load and perform the review-phase workflow.
+   - `verify_phase`: load and perform the verify-work workflow.
 
 4. Read only the workflow file needed for the selected route. Do not load the others "just in case".
 

package/autodev/workflows/cleanup.md

@@ -13,7 +13,8 @@ Clean or archive autodev state without flags. Prefer preserving useful project c
 1. Run:
 
 ```bash
-node "$HOME/.claude/autodev/bin/autodev-tools.cjs" cleanup
+AUTODEV_ROOT="${CLAUDE_PLUGIN_ROOT:-$HOME/.claude}"
+node "$AUTODEV_ROOT/autodev/bin/autodev-tools.cjs" cleanup
 ```
 
 2. If no `.autodev/` project exists, stop and say there is nothing to clean.

package/autodev/workflows/execute-phase.md

@@ -19,7 +19,8 @@ Execute an active-track phase through task-sized worker runs, keep the main sess
 1. Run:
 
 ```bash
-node "$HOME/.claude/autodev/bin/autodev-tools.cjs" init execute-phase "$ARGUMENTS"
+AUTODEV_ROOT="${CLAUDE_PLUGIN_ROOT:-$HOME/.claude}"
+node "$AUTODEV_ROOT/autodev/bin/autodev-tools.cjs" init execute-phase "$ARGUMENTS"
 ```
 
 2. If no phase is found or the plan file is missing, stop and direct the user to `/autodev-plan-phase`.
@@ -48,8 +49,12 @@ node "$HOME/.claude/autodev/bin/autodev-tools.cjs" init execute-phase "$ARGUMENT
    - verification plan
    - any dependency note
 
-7. If agent delegation is available, first try to spawn one fresh background worker using `autodev-task-worker` for the selected task.
-   Tell it:
+7. If agent delegation is available, explicitly call the `Agent` tool and select the installed task-worker subagent for the selected task.
+   Use:
+   - `autodev-task-worker` when autodev is installed into `.claude/`
+   - `autodev:autodev-task-worker` only when this workflow is being run directly from a plugin directory
+
+   Tell the subagent:
    - phase path
    - task path
    - summary path to write

package/autodev/workflows/explore-codebase.md

@@ -13,7 +13,8 @@ Map a brownfield repository quickly and produce a usable codebase brief without
 1. Run:
 
 ```bash
-node "$HOME/.claude/autodev/bin/autodev-tools.cjs" init explore-codebase
+AUTODEV_ROOT="${CLAUDE_PLUGIN_ROOT:-$HOME/.claude}"
+node "$AUTODEV_ROOT/autodev/bin/autodev-tools.cjs" init explore-codebase
 ```
 
 2. If no project exists, stop and tell the user to use `/autodev` or `/autodev-new-project`.
@@ -25,11 +26,11 @@ node "$HOME/.claude/autodev/bin/autodev-tools.cjs" init explore-codebase
    - the active track docs if they exist
    - representative repo files needed to orient the exploration
 
-4. If specialized agents are available, spawn four parallel agents with these owned outputs:
-   - `autodev-codebase-structure` owns `.autodev/codebase/structure.md`
-   - `autodev-codebase-domain` owns `.autodev/codebase/domain.md`
-   - `autodev-codebase-runtime` owns `.autodev/codebase/runtime.md`
-   - `autodev-codebase-quality` owns `.autodev/codebase/quality.md`
+4. If specialized agents are available, explicitly call the `Agent` tool four times with these installed subagents and owned outputs:
+   - `autodev-codebase-structure` for standalone installs, or `autodev:autodev-codebase-structure` in direct plugin runs, owns `.autodev/codebase/structure.md`
+   - `autodev-codebase-domain` for standalone installs, or `autodev:autodev-codebase-domain` in direct plugin runs, owns `.autodev/codebase/domain.md`
+   - `autodev-codebase-runtime` for standalone installs, or `autodev:autodev-codebase-runtime` in direct plugin runs, owns `.autodev/codebase/runtime.md`
+   - `autodev-codebase-quality` for standalone installs, or `autodev:autodev-codebase-quality` in direct plugin runs, owns `.autodev/codebase/quality.md`
 
 5. Tell each agent:
    - it is not alone in the codebase

package/autodev/workflows/new-project.md

@@ -13,7 +13,8 @@ Initialize `.autodev/` with useful project-level context, then create the first
 1. Run:
 
 ```bash
-node "$HOME/.claude/autodev/bin/autodev-tools.cjs" init new-project
+AUTODEV_ROOT="${CLAUDE_PLUGIN_ROOT:-$HOME/.claude}"
+node "$AUTODEV_ROOT/autodev/bin/autodev-tools.cjs" init new-project
 ```
 
 2. If `.autodev/PROJECT.md` already exists, stop and tell the user to use `/autodev`.

package/autodev/workflows/plan-phase.md

@@ -15,7 +15,8 @@ Create one practical phase plan for the active track, then break it into reviewa
 1. Run:
 
 ```bash
-node "$HOME/.claude/autodev/bin/autodev-tools.cjs" init plan-phase "$ARGUMENTS"
+AUTODEV_ROOT="${CLAUDE_PLUGIN_ROOT:-$HOME/.claude}"
+node "$AUTODEV_ROOT/autodev/bin/autodev-tools.cjs" init plan-phase "$ARGUMENTS"
 ```
 
 2. If there is no active track or no roadmap for it, stop and tell the user to run `/autodev`.

package/autodev/workflows/progress.md

@@ -6,7 +6,8 @@ Render the current autodev status with no extra ceremony.
 1. Run:
 
 ```bash
-node "$HOME/.claude/autodev/bin/autodev-tools.cjs" progress table
+AUTODEV_ROOT="${CLAUDE_PLUGIN_ROOT:-$HOME/.claude}"
+node "$AUTODEV_ROOT/autodev/bin/autodev-tools.cjs" progress table
 ```
 
 2. Output the table directly.

package/autodev/workflows/review-phase.md

@@ -13,7 +13,8 @@ Run the automatic review bundle after execution so the user sees code quality, s
 1. Run:
 
 ```bash
-node "$HOME/.claude/autodev/bin/autodev-tools.cjs" init review-phase "$ARGUMENTS"
+AUTODEV_ROOT="${CLAUDE_PLUGIN_ROOT:-$HOME/.claude}"
+node "$AUTODEV_ROOT/autodev/bin/autodev-tools.cjs" init review-phase "$ARGUMENTS"
 ```
 
 2. If no executed phase is found, stop and direct the user to `/autodev-execute-phase`.
@@ -27,11 +28,11 @@ node "$HOME/.claude/autodev/bin/autodev-tools.cjs" init review-phase "$ARGUMENTS
    - `NN-SUMMARY.md`
    - relevant source files and tests
 
-4. If specialized agents are available, spawn four parallel review agents:
-   - `autodev-review-quality`
-   - `autodev-review-security`
-   - `autodev-review-integration`
-   - `autodev-review-polish`
+4. If specialized agents are available, explicitly call the `Agent` tool four times with these installed review subagents:
+   - `autodev-review-quality` for standalone installs, or `autodev:autodev-review-quality` in direct plugin runs
+   - `autodev-review-security` for standalone installs, or `autodev:autodev-review-security` in direct plugin runs
+   - `autodev-review-integration` for standalone installs, or `autodev:autodev-review-integration` in direct plugin runs
+   - `autodev-review-polish` for standalone installs, or `autodev:autodev-review-polish` in direct plugin runs
 
 5. Tell each review agent:
    - it is not alone in the codebase

package/autodev/workflows/review-plan.md

@@ -13,7 +13,8 @@ Pause after phase planning so the user can review the generated plan and task br
 1. Run:
 
 ```bash
-node "$HOME/.claude/autodev/bin/autodev-tools.cjs" init review-plan "$ARGUMENTS"
+AUTODEV_ROOT="${CLAUDE_PLUGIN_ROOT:-$HOME/.claude}"
+node "$AUTODEV_ROOT/autodev/bin/autodev-tools.cjs" init review-plan "$ARGUMENTS"
 ```
 
 2. If no planned phase is found, stop and direct the user to `/autodev`.
@@ -36,11 +37,11 @@ node "$HOME/.claude/autodev/bin/autodev-tools.cjs" init review-plan "$ARGUMENTS"
    - stop here
 
 6. If the user chooses to execute now:
-   - read `@~/.claude/autodev/workflows/execute-phase.md`
-   - perform that workflow in the same turn
+   - load the execute-phase workflow
+   - perform it in the same turn
 
 7. If the user chooses to revise the plan:
-   - read `@~/.claude/autodev/workflows/plan-phase.md`
+   - load the plan-phase workflow
    - revise the same phase in the same turn
 
 8. If the user chooses to stop here:

package/autodev/workflows/verify-work.md

@@ -12,7 +12,8 @@ Run lightweight user acceptance testing after review and keep the next action ob
 1. Run:
 
 ```bash
-node "$HOME/.claude/autodev/bin/autodev-tools.cjs" init verify-work "$ARGUMENTS"
+AUTODEV_ROOT="${CLAUDE_PLUGIN_ROOT:-$HOME/.claude}"
+node "$AUTODEV_ROOT/autodev/bin/autodev-tools.cjs" init verify-work "$ARGUMENTS"
 ```
 
 2. If no reviewed phase is found, stop and direct the user to `/autodev-review-phase`.

package/bin/install.js

@@ -13,6 +13,7 @@ const reset = '\x1b[0m';
 const MANAGED_PREFIX = 'autodev-';
 const ROOT_COMMAND = 'autodev';
 const HOOK_FILES = [
+  'hooks.json',
   'autodev-context-monitor.js',
   'autodev-git-guard.js',
   'autodev-phase-boundary.sh',

package/hooks/hooks.json

@@ -0,0 +1,79 @@
+{
+  "hooks": {
+    "SessionStart": [
+      {
+        "hooks": [
+          {
+            "type": "command",
+            "command": "bash \"${CLAUDE_PLUGIN_ROOT}/hooks/autodev-session-state.sh\"",
+            "timeout": 5
+          }
+        ]
+      }
+    ],
+    "PreToolUse": [
+      {
+        "matcher": "Write|Edit",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/autodev-prompt-guard.js\"",
+            "timeout": 5
+          }
+        ]
+      },
+      {
+        "matcher": "Write|Edit",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/autodev-read-guard.js\"",
+            "timeout": 5
+          }
+        ]
+      },
+      {
+        "matcher": "Write|Edit",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/autodev-workflow-guard.js\"",
+            "timeout": 5
+          }
+        ]
+      },
+      {
+        "matcher": "Bash",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/autodev-git-guard.js\"",
+            "timeout": 5
+          }
+        ]
+      }
+    ],
+    "PostToolUse": [
+      {
+        "matcher": "Bash|Edit|Write|MultiEdit|Agent|Task",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/autodev-context-monitor.js\"",
+            "timeout": 10
+          }
+        ]
+      },
+      {
+        "matcher": "Write|Edit",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "bash \"${CLAUDE_PLUGIN_ROOT}/hooks/autodev-phase-boundary.sh\"",
+            "timeout": 5
+          }
+        ]
+      }
+    ]
+  }
+}

package/package.json

@@ -1,11 +1,12 @@
 {
   "name": "@mthanhlm/autodev",
-  "version": "0.3.4",
+  "version": "0.3.5",
   "description": "A lean Claude Code workflow system with a single entrypoint, task-based phase execution, and read-only git.",
   "bin": {
     "autodev": "bin/install.js"
   },
   "files": [
+    ".claude-plugin",
     "bin",
     "commands",
     "agents",