@orderful/droid 0.35.1 → 0.35.3

package/.claude-plugin/marketplace.json

@@ -22,7 +22,7 @@
     {
       "name": "droid-brain",
       "description": "Your scratchpad (or brain) - a collaborative space for planning and research. Create docs with /brain plan, /brain research, or /brain review. Use @mentions for async discussion. Docs persist across sessions.",
-      "version": "0.3.5",
+      "version": "0.3.7",
       "source": {
         "source": "github",
         "repo": "orderful/droid",
@@ -35,7 +35,7 @@
     {
       "name": "droid-coach",
       "description": "Learning-mode AI assistance - AI as coach, not crutch. Use /coach plan for co-authored planning, /coach scaffold for structure with hints, /coach review for Socratic questions.",
-      "version": "0.2.3",
+      "version": "0.2.4",
       "source": {
         "source": "github",
         "repo": "orderful/droid",
@@ -48,7 +48,7 @@
     {
       "name": "droid-code-review",
       "description": "Comprehensive code review using specialized agents. Reviews PRs, staged changes, branches, or specific files with confidence scoring.",
-      "version": "0.2.2",
+      "version": "0.2.3",
       "source": {
         "source": "github",
         "repo": "orderful/droid",
@@ -61,7 +61,7 @@
     {
       "name": "droid-codex",
       "description": "Shared organizational knowledge - PRDs, tech designs, domains, proposals, patterns, and explored topics. Use when loading project context, searching codex, capturing decisions, or creating new entries.",
-      "version": "0.2.1",
+      "version": "0.2.2",
       "source": {
         "source": "github",
         "repo": "orderful/droid",
@@ -74,7 +74,7 @@
     {
       "name": "droid-comments",
       "description": "Enable inline conversations using @droid/@user markers. Tag @droid to ask the AI, AI responds with @{your-name}. Use /comments check to address markers, /comments cleanup to remove resolved threads. Ideal for code review notes and async collaboration.",
-      "version": "0.3.3",
+      "version": "0.3.4",
       "source": {
         "source": "github",
         "repo": "orderful/droid",
@@ -87,7 +87,7 @@
     {
       "name": "droid-plan",
       "description": "Task-scoped planning with portable, structured plans. Use when planning implementation for a PR, ticket, or small feature. User prompts like 'let's plan this', 'can we start a plan', 'think through the implementation'.",
-      "version": "0.1.0",
+      "version": "0.1.1",
       "source": {
         "source": "github",
         "repo": "orderful/droid",
@@ -100,7 +100,7 @@
     {
       "name": "droid-project",
       "description": "Manage project context files for persistent AI memory across sessions. Load, update, or create project context before working on multi-session features.",
-      "version": "0.3.3",
+      "version": "0.3.4",
       "source": {
         "source": "github",
         "repo": "orderful/droid",
@@ -113,7 +113,7 @@
     {
       "name": "droid-tech-design",
       "description": "Technical design authoring tool for engineers. Create structured tech design docs with /tech-design start, iterate in brain, publish to codex. Three-document approach: research doc (codebase discoveries) + thought doc (design workspace) + roll-up (clean summary for review).",
-      "version": "0.2.3",
+      "version": "0.2.4",
       "source": {
         "source": "github",
         "repo": "orderful/droid",
@@ -126,7 +126,7 @@
     {
       "name": "droid-wrapup",
       "description": "Session wrap-up that captures decisions, learnings, and open items to persistent docs.",
-      "version": "0.1.2",
+      "version": "0.1.3",
       "source": {
         "source": "github",
         "repo": "orderful/droid",

package/CHANGELOG.md

@@ -1,5 +1,41 @@
 # @orderful/droid
 
+## 0.35.3
+
+### Patch Changes
+
+- [#215](https://github.com/Orderful/droid/pull/215) [`5241570`](https://github.com/Orderful/droid/commit/5241570ab1b14bb819c5635834706ad67f0525a2) Thanks [@frytyler](https://github.com/frytyler)! - Fix brain comment responses blockquoting section content
+
+  When responding to `> @droid` comments in brain docs, Claude was wrapping all subsequent section content in blockquotes. Now only the `> @fry` response line is blockquoted, with substantive content (sections, analysis) in regular markdown for better readability.
+
+- [#217](https://github.com/Orderful/droid/pull/217) [`6484016`](https://github.com/Orderful/droid/commit/648401686c3e6c5f59ccb08d55947beb3170d352) Thanks [@frytyler](https://github.com/frytyler)! - fix(skills): add Bash to allowed-tools for skills using droid config commands
+
+  Multiple skills require running `droid config --get` commands but didn't have Bash in their allowed-tools list. This caused them to fail when trying to read configuration.
+
+  Fixed skills:
+  - coach (0.2.4): Added Bash to allowed-tools
+  - codex (0.2.2): Added Bash(droid:\*) to allowed-tools
+  - comments (0.3.4): Added Bash to allowed-tools
+  - tech-design (0.2.4): Added Bash(droid:\*) to allowed-tools
+  - project (0.3.4): Added Bash to allowed-tools
+
+## 0.35.2
+
+### Patch Changes
+
+- [#213](https://github.com/Orderful/droid/pull/213) [`95a67d7`](https://github.com/Orderful/droid/commit/95a67d7f3bc57652113cf89bfb24de84d5d94490) Thanks [@frytyler](https://github.com/frytyler)! - Add explicit Configuration sections to all skills to prevent ambiguous config references. This ensures Claude sees the exact config commands (`droid config --get`) in the main SKILL.md file rather than having to look in references.
+
+  **Updated skills:**
+  - **wrapup** (v0.1.3): Added Configuration section explaining it uses configs from project, brain, and codex tools
+  - **code-review** (v0.2.3): Added Configuration section explaining optional brain integration
+  - **brain** (v0.3.6): Updated brain-obsidian to use explicit `droid config --get` commands instead of referencing override files directly
+
+  This follows the progressive disclosure principle: SKILL.md should have explicit config commands to prevent misinterpretation, with detailed procedures in references.
+
+- [#213](https://github.com/Orderful/droid/pull/213) [`95a67d7`](https://github.com/Orderful/droid/commit/95a67d7f3bc57652113cf89bfb24de84d5d94490) Thanks [@frytyler](https://github.com/frytyler)! - Fix plan skill to use explicit config commands instead of deprecated syntax. The plan skill now clearly specifies `droid config --get tools.brain` and `droid config --get user_mention` instead of the ambiguous "Read config" instruction that was causing Claude to use the deprecated `droid config <tool>` command.
+
+  Also corrected `inbox_dir` to `inbox_folder` throughout plan skill docs to match the actual config schema.
+
 ## 0.35.1
 
 ### Patch Changes

package/dist/tools/brain/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "droid-brain",
-  "version": "0.3.5",
+  "version": "0.3.7",
   "description": "Your scratchpad (or brain) - a collaborative space for planning and research. Create docs with /brain plan, /brain research, or /brain review. Use @mentions for async discussion. Docs persist across sessions.",
   "author": {
     "name": "Orderful",

package/dist/tools/brain/TOOL.yaml

@@ -1,6 +1,6 @@
 name: brain
 description: "Your scratchpad (or brain) - a collaborative space for planning and research. Create docs with /brain plan, /brain research, or /brain review. Use @mentions for async discussion. Docs persist across sessions."
-version: 0.3.5
+version: 0.3.7
 status: beta
 
 includes:

package/dist/tools/brain/skills/brain/references/workflows.md

@@ -177,8 +177,21 @@ Detailed procedures for each brain operation.
    - Add response as blockquote with user's mention (from `droid config --get tools.brain`): `> @{user_mention} Your response here`
    - Example: `> @{user} Yes, the index covers that query pattern.`
    - **CRITICAL:** NEVER use `@droid` in your responses. Use `@{user_mention}` from config (e.g., `@{user}`)
-   - **CRITICAL:** Always include the `>` prefix to maintain blockquote formatting
+   - **CRITICAL:** Always include the `>` prefix for the @mention response line to maintain blockquote formatting
    - **CRITICAL:** If `preserve_comments: true`, keep the original `@droid` comment and add your response below it. Do NOT remove the original comment.
+   - **CRITICAL:** When adding substantive content (sections, analysis, etc.) AFTER your `> @{user_mention}` response, use regular markdown formatting (NOT blockquoted). Only the @mention line should be blockquoted.
+
+   **Format example:**
+   ```markdown
+   > @droid Show me the architecture section
+
+   > @{user_mention} Here's the architecture section.
+
+   ## Architecture
+
+   The system uses a three-tier architecture...
+   (regular markdown, NOT blockquoted)
+   ```
 
 6. **Update the doc** with responses
 

package/dist/tools/brain/skills/brain-obsidian/SKILL.md

@@ -15,13 +15,14 @@ Extends the brain skill with Obsidian-specific features. **This skill overrides
 
 ## Configuration
 
-**Required:** Set vault path in `~/.droid/skills/brain/overrides.yaml`:
+**Required:** Run `droid config --get tools.brain` and ensure `brain_dir` is set to your Obsidian vault path.
 
-```yaml
-brain_dir: ~/path/to/your/vault
+If not configured, set it with:
+```bash
+droid config --set tools.brain.brain_dir=~/path/to/your/vault
 ```
 
-**Optional:** Configure folders in `~/.droid/skills/brain-obsidian/overrides.yaml`:
+**Optional:** Configure Obsidian-specific folders with `droid config --get tools.brain-obsidian`:
 
 | Setting            | Default       | Description                     |
 | ------------------ | ------------- | ------------------------------- |

package/dist/tools/coach/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "droid-coach",
-  "version": "0.2.3",
+  "version": "0.2.4",
   "description": "Learning-mode AI assistance - AI as coach, not crutch. Use /coach plan for co-authored planning, /coach scaffold for structure with hints, /coach review for Socratic questions.",
   "author": {
     "name": "Orderful",

package/dist/tools/coach/TOOL.yaml

@@ -1,6 +1,6 @@
 name: coach
 description: "Learning-mode AI assistance - AI as coach, not crutch. Use /coach plan for co-authored planning, /coach scaffold for structure with hints, /coach review for Socratic questions."
-version: 0.2.3
+version: 0.2.4
 status: beta
 
 includes:

package/dist/tools/coach/skills/coach/SKILL.md

@@ -2,7 +2,7 @@
 name: coach
 description: "Learning-mode AI assistance - scaffolds don't implement, questions don't fix. Use when learning a new codebase, wanting to understand deeply, or building skills to retain. User prompts like 'coach me on', 'help me think through', 'I want to learn how to', 'don't just give me the answer'."
 argument-hint: "[plan {task} | scaffold [{path}] | review [{path}] | check | challenge [{path}]]"
-allowed-tools: [Read, Grep, Glob]
+allowed-tools: [Read, Grep, Glob, Bash]
 ---
 
 # Coach Skill

package/dist/tools/code-review/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "droid-code-review",
-  "version": "0.2.2",
+  "version": "0.2.3",
   "description": "Comprehensive code review using specialized agents. Reviews PRs, staged changes, branches, or specific files with confidence scoring.",
   "author": {
     "name": "Orderful",

package/dist/tools/code-review/TOOL.yaml

@@ -1,6 +1,6 @@
 name: code-review
 description: "Comprehensive code review using specialized agents. Reviews PRs, staged changes, branches, or specific files with confidence scoring."
-version: 0.2.2
+version: 0.2.3
 status: alpha
 
 includes:

package/dist/tools/code-review/skills/code-review/SKILL.md

@@ -9,6 +9,13 @@ allowed-tools: [Read, Grep, Glob, Bash, Task]
 
 Run comprehensive code reviews using specialized agents, each focused on a specific concern.
 
+## Configuration
+
+Code-review has no configuration of its own. Optional integration with other tools:
+
+- **Brain skill** (optional): If installed, offers to save review results to a `/brain review` doc
+  - Check with: `droid config --get tools.brain` to see if `brain_dir` is configured
+
 ## How It Works
 
 The `/code-review` command orchestrates multiple specialized agents in parallel:

package/dist/tools/codex/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "droid-codex",
-  "version": "0.2.1",
+  "version": "0.2.2",
   "description": "Shared organizational knowledge - PRDs, tech designs, domains, proposals, patterns, and explored topics. Use when loading project context, searching codex, capturing decisions, or creating new entries.",
   "author": {
     "name": "Orderful",

package/dist/tools/codex/TOOL.yaml

@@ -1,6 +1,6 @@
 name: codex
 description: "Shared organizational knowledge - PRDs, tech designs, domains, proposals, patterns, and explored topics. Use when loading project context, searching codex, capturing decisions, or creating new entries."
-version: 0.2.1
+version: 0.2.2
 status: beta
 
 includes:

package/dist/tools/codex/skills/codex/SKILL.md

@@ -13,6 +13,7 @@ allowed-tools:
     Bash(git:*),
     Bash(ls:*),
     Bash(mkdir:*),
+    Bash(droid:*),
   ]
 ---
 

package/dist/tools/comments/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "droid-comments",
-  "version": "0.3.3",
+  "version": "0.3.4",
   "description": "Enable inline conversations using @droid/@user markers. Tag @droid to ask the AI, AI responds with @{your-name}. Use /comments check to address markers, /comments cleanup to remove resolved threads. Ideal for code review notes and async collaboration.",
   "author": {
     "name": "Orderful",

package/dist/tools/comments/TOOL.yaml

@@ -1,6 +1,6 @@
 name: comments
 description: "Enable inline conversations using @droid/@user markers. Tag @droid to ask the AI, AI responds with @{your-name}. Use /comments check to address markers, /comments cleanup to remove resolved threads. Ideal for code review notes and async collaboration."
-version: 0.3.3
+version: 0.3.4
 status: beta
 
 includes:

package/dist/tools/comments/skills/comments/SKILL.md

@@ -2,7 +2,7 @@
 name: comments
 description: "Inline conversations using @droid/@user markers in any file. Use when leaving async questions in code or having discussion that should stay near the code. User prompts like 'check for comments', 'address the @droid markers', 'clean up resolved comments'."
 argument-hint: "[check [{path}] | cleanup]"
-allowed-tools: [Read, Grep, Glob, Edit]
+allowed-tools: [Read, Grep, Glob, Edit, Bash]
 ---
 
 # Comments Skill

package/dist/tools/plan/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "droid-plan",
-  "version": "0.1.0",
+  "version": "0.1.1",
   "description": "Task-scoped planning with portable, structured plans. Use when planning implementation for a PR, ticket, or small feature. User prompts like 'let's plan this', 'can we start a plan', 'think through the implementation'.",
   "author": {
     "name": "Orderful",

package/dist/tools/plan/TOOL.yaml

@@ -1,6 +1,6 @@
 name: plan
 description: "Task-scoped planning with portable, structured plans. Use when planning implementation for a PR, ticket, or small feature. User prompts like 'let's plan this', 'can we start a plan', 'think through the implementation'."
-version: 0.1.0
+version: 0.1.1
 status: alpha
 
 includes:

package/dist/tools/plan/skills/plan/SKILL.md

@@ -24,8 +24,8 @@ Task-scoped planning for PRs, tickets, and small features. Lighter than `/tech-d
 ## Configuration
 
 Uses config from dependencies:
-- `droid config --get tools.brain` → `brain_dir`, `inbox_dir`
-- `droid config --get tools.comments` → `user_mention`
+- `droid config --get tools.brain` → `brain_dir`, `inbox_folder`
+- `droid config --get user_mention` → `user_mention` (global config)
 
 ## Commands
 
@@ -39,10 +39,13 @@ Uses config from dependencies:
 
 ## `/plan new {topic}`
 
-1. Read config (`brain_dir`, `inbox_dir`, `user_mention`)
+1. **Read config first:**
+   - Run `droid config --get tools.brain` for `brain_dir` and `inbox_folder`
+   - Run `droid config --get user_mention` for user's mention tag
+   - If `brain_dir` not configured, ask user where to store plans
 2. Determine location:
    - If `/project` active → offer: `{projects_dir}/{project}/plans/`
-   - Otherwise → `{brain_dir}/{inbox_dir}/plans/`
+   - Otherwise → `{brain_dir}/{inbox_folder}/plans/`
 3. Offer context loading (`/project`, `/codex` search)
 4. Ask clarifying questions (goal, scope, constraints)
 5. Generate plan from template (see `references/templates.md`)

package/dist/tools/plan/skills/plan/references/templates.md

@@ -173,4 +173,4 @@ Plans are named `plan-{topic}.md` with kebab-case topic:
 
 ## Location
 
-Plans live in `{brain_dir}/{inbox_dir}/plans/` or `{projects_dir}/{project}/plans/` if project-nested.
+Plans live in `{brain_dir}/{inbox_folder}/plans/` or `{projects_dir}/{project}/plans/` if project-nested.

package/dist/tools/plan/skills/plan/references/workflows.md

@@ -7,8 +7,8 @@ Detailed command flows for the plan skill.
 ### Step 1: Read Configuration
 
 ```bash
-droid config --get tools.brain   # → brain_dir, inbox_dir
-droid config --get tools.comments # → user_mention
+droid config --get tools.brain   # → brain_dir, inbox_folder
+droid config --get user_mention  # → user_mention (global config)
 ```
 
 If brain not configured, ask user for `brain_dir` location.
@@ -21,12 +21,12 @@ Check if `/project` is active (check `{projects_dir}/{project}/PROJECT.md` exist
 ```
 Offer choice via AskUserQuestion:
 - "Project folder" → {projects_dir}/{project}/plans/plan-{topic}.md
-- "Inbox" → {brain_dir}/{inbox_dir}/plans/plan-{topic}.md
+- "Inbox" → {brain_dir}/{inbox_folder}/plans/plan-{topic}.md
 ```
 
 **If no project:**
 ```
-Use: {brain_dir}/{inbox_dir}/plans/plan-{topic}.md
+Use: {brain_dir}/{inbox_folder}/plans/plan-{topic}.md
 ```
 
 ### Step 3: Check for Existing Plan

package/dist/tools/project/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "droid-project",
-  "version": "0.3.3",
+  "version": "0.3.4",
   "description": "Manage project context files for persistent AI memory across sessions. Load, update, or create project context before working on multi-session features.",
   "author": {
     "name": "Orderful",

package/dist/tools/project/TOOL.yaml

@@ -1,6 +1,6 @@
 name: project
 description: "Manage project context files for persistent AI memory across sessions. Load, update, or create project context before working on multi-session features."
-version: 0.3.3
+version: 0.3.4
 status: beta
 
 includes:

package/dist/tools/project/skills/project/SKILL.md

@@ -2,7 +2,7 @@
 name: project
 description: "Persistent project context for AI memory across sessions. Use when working on multi-session features, refactors, or any work that benefits from accumulated context. User prompts like 'load the project', 'update project context', 'what's the current project?'."
 argument-hint: "[{keywords} | update | create {name}]"
-allowed-tools: [Read, Write, Glob, Grep]
+allowed-tools: [Read, Write, Glob, Grep, Bash]
 ---
 
 # Project Skill

package/dist/tools/tech-design/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "droid-tech-design",
-  "version": "0.2.3",
+  "version": "0.2.4",
   "description": "Technical design authoring tool for engineers. Create structured tech design docs with /tech-design start, iterate in brain, publish to codex. Three-document approach: research doc (codebase discoveries) + thought doc (design workspace) + roll-up (clean summary for review).",
   "author": {
     "name": "Orderful",

package/dist/tools/tech-design/TOOL.yaml

@@ -1,6 +1,6 @@
 name: tech-design
 description: "Technical design authoring tool for engineers. Create structured tech design docs with /tech-design start, iterate in brain, publish to codex. Three-document approach: research doc (codebase discoveries) + thought doc (design workspace) + roll-up (clean summary for review)."
-version: 0.2.3
+version: 0.2.4
 status: beta
 
 includes:

package/dist/tools/tech-design/skills/tech-design/SKILL.md

@@ -3,7 +3,7 @@ name: tech-design
 description: "Technical design authoring with three-document approach - research doc (codebase discoveries), thought doc (design iteration), and roll-up (clean summary). Use when writing tech designs, drafting sections, exploring architectural ideas, or publishing to codex. User prompts like 'start tech design for X', 'draft the rollout section', 'let's think through the API design', 'publish this to codex'."
 argument-hint: "[start --from codex:{project} | draft [section] | think [topic] | gaps | publish]"
 allowed-tools:
-  [Read, Write, Edit, Glob, Grep, Bash(gh:*), Bash(git:*), Bash(mkdir:*), Task]
+  [Read, Write, Edit, Glob, Grep, Bash(gh:*), Bash(git:*), Bash(mkdir:*), Bash(droid:*), Task]
 ---
 
 # Tech Design Skill

package/dist/tools/wrapup/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "droid-wrapup",
-  "version": "0.1.2",
+  "version": "0.1.3",
   "description": "Session wrap-up that captures decisions, learnings, and open items to persistent docs.",
   "author": {
     "name": "Orderful",

package/dist/tools/wrapup/TOOL.yaml

@@ -1,6 +1,6 @@
 name: wrapup
 description: "Session wrap-up that captures decisions, learnings, and open items to persistent docs."
-version: 0.1.2
+version: 0.1.3
 status: alpha
 
 includes:

package/dist/tools/wrapup/skills/wrapup/SKILL.md

@@ -8,6 +8,16 @@ allowed-tools: [Read, Edit, Write, Glob, Grep, Bash, Task]
 
 Session wrap-up that captures decisions, learnings, and open items before closing.
 
+## Configuration
+
+Wrapup has no configuration of its own. It reads config from other installed tools:
+
+- **Project skill** (optional): `droid config --get tools.project` → `projects_dir` to update project files
+- **Brain skill** (optional): `droid config --get tools.brain` → `brain_dir` to update brain docs
+- **Codex skill** (optional): `droid config --get tools.codex` → `codex_repo` to suggest codex entries
+
+If these tools aren't configured, wrapup skips those artifacts and focuses on git state and conversation summary.
+
 ## Context Lifeboat Pattern
 
 This skill runs at the END of sessions when context pressure is highest.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@orderful/droid",
-  "version": "0.35.1",
+  "version": "0.35.3",
   "description": "AI workflow toolkit for sharing skills, commands, and agents across the team",
   "type": "module",
   "bin": {

package/src/tools/brain/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "droid-brain",
-  "version": "0.3.5",
+  "version": "0.3.7",
   "description": "Your scratchpad (or brain) - a collaborative space for planning and research. Create docs with /brain plan, /brain research, or /brain review. Use @mentions for async discussion. Docs persist across sessions.",
   "author": {
     "name": "Orderful",

package/src/tools/brain/TOOL.yaml

@@ -1,6 +1,6 @@
 name: brain
 description: "Your scratchpad (or brain) - a collaborative space for planning and research. Create docs with /brain plan, /brain research, or /brain review. Use @mentions for async discussion. Docs persist across sessions."
-version: 0.3.5
+version: 0.3.7
 status: beta
 
 includes:

package/src/tools/brain/skills/brain/references/workflows.md

@@ -177,8 +177,21 @@ Detailed procedures for each brain operation.
    - Add response as blockquote with user's mention (from `droid config --get tools.brain`): `> @{user_mention} Your response here`
    - Example: `> @{user} Yes, the index covers that query pattern.`
    - **CRITICAL:** NEVER use `@droid` in your responses. Use `@{user_mention}` from config (e.g., `@{user}`)
-   - **CRITICAL:** Always include the `>` prefix to maintain blockquote formatting
+   - **CRITICAL:** Always include the `>` prefix for the @mention response line to maintain blockquote formatting
    - **CRITICAL:** If `preserve_comments: true`, keep the original `@droid` comment and add your response below it. Do NOT remove the original comment.
+   - **CRITICAL:** When adding substantive content (sections, analysis, etc.) AFTER your `> @{user_mention}` response, use regular markdown formatting (NOT blockquoted). Only the @mention line should be blockquoted.
+
+   **Format example:**
+   ```markdown
+   > @droid Show me the architecture section
+
+   > @{user_mention} Here's the architecture section.
+
+   ## Architecture
+
+   The system uses a three-tier architecture...
+   (regular markdown, NOT blockquoted)
+   ```
 
 6. **Update the doc** with responses
 

package/src/tools/brain/skills/brain-obsidian/SKILL.md

@@ -15,13 +15,14 @@ Extends the brain skill with Obsidian-specific features. **This skill overrides
 
 ## Configuration
 
-**Required:** Set vault path in `~/.droid/skills/brain/overrides.yaml`:
+**Required:** Run `droid config --get tools.brain` and ensure `brain_dir` is set to your Obsidian vault path.
 
-```yaml
-brain_dir: ~/path/to/your/vault
+If not configured, set it with:
+```bash
+droid config --set tools.brain.brain_dir=~/path/to/your/vault
 ```
 
-**Optional:** Configure folders in `~/.droid/skills/brain-obsidian/overrides.yaml`:
+**Optional:** Configure Obsidian-specific folders with `droid config --get tools.brain-obsidian`:
 
 | Setting            | Default       | Description                     |
 | ------------------ | ------------- | ------------------------------- |

package/src/tools/coach/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "droid-coach",
-  "version": "0.2.3",
+  "version": "0.2.4",
   "description": "Learning-mode AI assistance - AI as coach, not crutch. Use /coach plan for co-authored planning, /coach scaffold for structure with hints, /coach review for Socratic questions.",
   "author": {
     "name": "Orderful",

package/src/tools/coach/TOOL.yaml

@@ -1,6 +1,6 @@
 name: coach
 description: "Learning-mode AI assistance - AI as coach, not crutch. Use /coach plan for co-authored planning, /coach scaffold for structure with hints, /coach review for Socratic questions."
-version: 0.2.3
+version: 0.2.4
 status: beta
 
 includes:

package/src/tools/coach/skills/coach/SKILL.md

@@ -2,7 +2,7 @@
 name: coach
 description: "Learning-mode AI assistance - scaffolds don't implement, questions don't fix. Use when learning a new codebase, wanting to understand deeply, or building skills to retain. User prompts like 'coach me on', 'help me think through', 'I want to learn how to', 'don't just give me the answer'."
 argument-hint: "[plan {task} | scaffold [{path}] | review [{path}] | check | challenge [{path}]]"
-allowed-tools: [Read, Grep, Glob]
+allowed-tools: [Read, Grep, Glob, Bash]
 ---
 
 # Coach Skill

package/src/tools/code-review/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "droid-code-review",
-  "version": "0.2.2",
+  "version": "0.2.3",
   "description": "Comprehensive code review using specialized agents. Reviews PRs, staged changes, branches, or specific files with confidence scoring.",
   "author": {
     "name": "Orderful",

package/src/tools/code-review/TOOL.yaml

@@ -1,6 +1,6 @@
 name: code-review
 description: "Comprehensive code review using specialized agents. Reviews PRs, staged changes, branches, or specific files with confidence scoring."
-version: 0.2.2
+version: 0.2.3
 status: alpha
 
 includes:

package/src/tools/code-review/skills/code-review/SKILL.md

@@ -9,6 +9,13 @@ allowed-tools: [Read, Grep, Glob, Bash, Task]
 
 Run comprehensive code reviews using specialized agents, each focused on a specific concern.
 
+## Configuration
+
+Code-review has no configuration of its own. Optional integration with other tools:
+
+- **Brain skill** (optional): If installed, offers to save review results to a `/brain review` doc
+  - Check with: `droid config --get tools.brain` to see if `brain_dir` is configured
+
 ## How It Works
 
 The `/code-review` command orchestrates multiple specialized agents in parallel:

package/src/tools/codex/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "droid-codex",
-  "version": "0.2.1",
+  "version": "0.2.2",
   "description": "Shared organizational knowledge - PRDs, tech designs, domains, proposals, patterns, and explored topics. Use when loading project context, searching codex, capturing decisions, or creating new entries.",
   "author": {
     "name": "Orderful",

package/src/tools/codex/TOOL.yaml

@@ -1,6 +1,6 @@
 name: codex
 description: "Shared organizational knowledge - PRDs, tech designs, domains, proposals, patterns, and explored topics. Use when loading project context, searching codex, capturing decisions, or creating new entries."
-version: 0.2.1
+version: 0.2.2
 status: beta
 
 includes:

package/src/tools/codex/skills/codex/SKILL.md

@@ -13,6 +13,7 @@ allowed-tools:
     Bash(git:*),
     Bash(ls:*),
     Bash(mkdir:*),
+    Bash(droid:*),
   ]
 ---
 

package/src/tools/comments/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "droid-comments",
-  "version": "0.3.3",
+  "version": "0.3.4",
   "description": "Enable inline conversations using @droid/@user markers. Tag @droid to ask the AI, AI responds with @{your-name}. Use /comments check to address markers, /comments cleanup to remove resolved threads. Ideal for code review notes and async collaboration.",
   "author": {
     "name": "Orderful",

package/src/tools/comments/TOOL.yaml

@@ -1,6 +1,6 @@
 name: comments
 description: "Enable inline conversations using @droid/@user markers. Tag @droid to ask the AI, AI responds with @{your-name}. Use /comments check to address markers, /comments cleanup to remove resolved threads. Ideal for code review notes and async collaboration."
-version: 0.3.3
+version: 0.3.4
 status: beta
 
 includes:

package/src/tools/comments/skills/comments/SKILL.md

@@ -2,7 +2,7 @@
 name: comments
 description: "Inline conversations using @droid/@user markers in any file. Use when leaving async questions in code or having discussion that should stay near the code. User prompts like 'check for comments', 'address the @droid markers', 'clean up resolved comments'."
 argument-hint: "[check [{path}] | cleanup]"
-allowed-tools: [Read, Grep, Glob, Edit]
+allowed-tools: [Read, Grep, Glob, Edit, Bash]
 ---
 
 # Comments Skill

package/src/tools/plan/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "droid-plan",
-  "version": "0.1.0",
+  "version": "0.1.1",
   "description": "Task-scoped planning with portable, structured plans. Use when planning implementation for a PR, ticket, or small feature. User prompts like 'let's plan this', 'can we start a plan', 'think through the implementation'.",
   "author": {
     "name": "Orderful",

package/src/tools/plan/TOOL.yaml

@@ -1,6 +1,6 @@
 name: plan
 description: "Task-scoped planning with portable, structured plans. Use when planning implementation for a PR, ticket, or small feature. User prompts like 'let's plan this', 'can we start a plan', 'think through the implementation'."
-version: 0.1.0
+version: 0.1.1
 status: alpha
 
 includes:

package/src/tools/plan/skills/plan/SKILL.md

@@ -24,8 +24,8 @@ Task-scoped planning for PRs, tickets, and small features. Lighter than `/tech-d
 ## Configuration
 
 Uses config from dependencies:
-- `droid config --get tools.brain` → `brain_dir`, `inbox_dir`
-- `droid config --get tools.comments` → `user_mention`
+- `droid config --get tools.brain` → `brain_dir`, `inbox_folder`
+- `droid config --get user_mention` → `user_mention` (global config)
 
 ## Commands
 
@@ -39,10 +39,13 @@ Uses config from dependencies:
 
 ## `/plan new {topic}`
 
-1. Read config (`brain_dir`, `inbox_dir`, `user_mention`)
+1. **Read config first:**
+   - Run `droid config --get tools.brain` for `brain_dir` and `inbox_folder`
+   - Run `droid config --get user_mention` for user's mention tag
+   - If `brain_dir` not configured, ask user where to store plans
 2. Determine location:
    - If `/project` active → offer: `{projects_dir}/{project}/plans/`
-   - Otherwise → `{brain_dir}/{inbox_dir}/plans/`
+   - Otherwise → `{brain_dir}/{inbox_folder}/plans/`
 3. Offer context loading (`/project`, `/codex` search)
 4. Ask clarifying questions (goal, scope, constraints)
 5. Generate plan from template (see `references/templates.md`)

package/src/tools/plan/skills/plan/references/templates.md

@@ -173,4 +173,4 @@ Plans are named `plan-{topic}.md` with kebab-case topic:
 
 ## Location
 
-Plans live in `{brain_dir}/{inbox_dir}/plans/` or `{projects_dir}/{project}/plans/` if project-nested.
+Plans live in `{brain_dir}/{inbox_folder}/plans/` or `{projects_dir}/{project}/plans/` if project-nested.

package/src/tools/plan/skills/plan/references/workflows.md

@@ -7,8 +7,8 @@ Detailed command flows for the plan skill.
 ### Step 1: Read Configuration
 
 ```bash
-droid config --get tools.brain   # → brain_dir, inbox_dir
-droid config --get tools.comments # → user_mention
+droid config --get tools.brain   # → brain_dir, inbox_folder
+droid config --get user_mention  # → user_mention (global config)
 ```
 
 If brain not configured, ask user for `brain_dir` location.
@@ -21,12 +21,12 @@ Check if `/project` is active (check `{projects_dir}/{project}/PROJECT.md` exist
 ```
 Offer choice via AskUserQuestion:
 - "Project folder" → {projects_dir}/{project}/plans/plan-{topic}.md
-- "Inbox" → {brain_dir}/{inbox_dir}/plans/plan-{topic}.md
+- "Inbox" → {brain_dir}/{inbox_folder}/plans/plan-{topic}.md
 ```
 
 **If no project:**
 ```
-Use: {brain_dir}/{inbox_dir}/plans/plan-{topic}.md
+Use: {brain_dir}/{inbox_folder}/plans/plan-{topic}.md
 ```
 
 ### Step 3: Check for Existing Plan

package/src/tools/project/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "droid-project",
-  "version": "0.3.3",
+  "version": "0.3.4",
   "description": "Manage project context files for persistent AI memory across sessions. Load, update, or create project context before working on multi-session features.",
   "author": {
     "name": "Orderful",

package/src/tools/project/TOOL.yaml

@@ -1,6 +1,6 @@
 name: project
 description: "Manage project context files for persistent AI memory across sessions. Load, update, or create project context before working on multi-session features."
-version: 0.3.3
+version: 0.3.4
 status: beta
 
 includes:

package/src/tools/project/skills/project/SKILL.md

@@ -2,7 +2,7 @@
 name: project
 description: "Persistent project context for AI memory across sessions. Use when working on multi-session features, refactors, or any work that benefits from accumulated context. User prompts like 'load the project', 'update project context', 'what's the current project?'."
 argument-hint: "[{keywords} | update | create {name}]"
-allowed-tools: [Read, Write, Glob, Grep]
+allowed-tools: [Read, Write, Glob, Grep, Bash]
 ---
 
 # Project Skill

package/src/tools/tech-design/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "droid-tech-design",
-  "version": "0.2.3",
+  "version": "0.2.4",
   "description": "Technical design authoring tool for engineers. Create structured tech design docs with /tech-design start, iterate in brain, publish to codex. Three-document approach: research doc (codebase discoveries) + thought doc (design workspace) + roll-up (clean summary for review).",
   "author": {
     "name": "Orderful",

package/src/tools/tech-design/TOOL.yaml

@@ -1,6 +1,6 @@
 name: tech-design
 description: "Technical design authoring tool for engineers. Create structured tech design docs with /tech-design start, iterate in brain, publish to codex. Three-document approach: research doc (codebase discoveries) + thought doc (design workspace) + roll-up (clean summary for review)."
-version: 0.2.3
+version: 0.2.4
 status: beta
 
 includes:

package/src/tools/tech-design/skills/tech-design/SKILL.md

@@ -3,7 +3,7 @@ name: tech-design
 description: "Technical design authoring with three-document approach - research doc (codebase discoveries), thought doc (design iteration), and roll-up (clean summary). Use when writing tech designs, drafting sections, exploring architectural ideas, or publishing to codex. User prompts like 'start tech design for X', 'draft the rollout section', 'let's think through the API design', 'publish this to codex'."
 argument-hint: "[start --from codex:{project} | draft [section] | think [topic] | gaps | publish]"
 allowed-tools:
-  [Read, Write, Edit, Glob, Grep, Bash(gh:*), Bash(git:*), Bash(mkdir:*), Task]
+  [Read, Write, Edit, Glob, Grep, Bash(gh:*), Bash(git:*), Bash(mkdir:*), Bash(droid:*), Task]
 ---
 
 # Tech Design Skill

package/src/tools/wrapup/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "droid-wrapup",
-  "version": "0.1.2",
+  "version": "0.1.3",
   "description": "Session wrap-up that captures decisions, learnings, and open items to persistent docs.",
   "author": {
     "name": "Orderful",

package/src/tools/wrapup/TOOL.yaml

@@ -1,6 +1,6 @@
 name: wrapup
 description: "Session wrap-up that captures decisions, learnings, and open items to persistent docs."
-version: 0.1.2
+version: 0.1.3
 status: alpha
 
 includes:

package/src/tools/wrapup/skills/wrapup/SKILL.md

@@ -8,6 +8,16 @@ allowed-tools: [Read, Edit, Write, Glob, Grep, Bash, Task]
 
 Session wrap-up that captures decisions, learnings, and open items before closing.
 
+## Configuration
+
+Wrapup has no configuration of its own. It reads config from other installed tools:
+
+- **Project skill** (optional): `droid config --get tools.project` → `projects_dir` to update project files
+- **Brain skill** (optional): `droid config --get tools.brain` → `brain_dir` to update brain docs
+- **Codex skill** (optional): `droid config --get tools.codex` → `codex_repo` to suggest codex entries
+
+If these tools aren't configured, wrapup skips those artifacts and focuses on git state and conversation summary.
+
 ## Context Lifeboat Pattern
 
 This skill runs at the END of sessions when context pressure is highest.