@orderful/droid 0.26.0 → 0.27.0

package/src/tools/coach/commands/coach.md

@@ -1,71 +1,31 @@
 ---
+name: coach
 description: "Learning-mode AI assistance - scaffolds don't implement, questions don't fix"
 argument-hint: "[plan {task} | scaffold [{path}] | review [{path}] | check | challenge [{path}]]"
-allowed-tools: [Read, Write, Edit, Glob, Grep, Bash(ls:*)]
 ---
 
 # /coach
 
-Entry point for learning-mode AI assistance. See the **coach skill** for full behaviour.
+**User invoked:** `/coach $ARGUMENTS`
 
-## Arguments
+**Your task:** Invoke the **coach skill** with these arguments.
 
-$ARGUMENTS
+**Philosophy:** "AI as coach, not crutch" - preserves learning-through-doing while leveraging AI for guardrails and feedback.
 
-## Philosophy
+## Examples
 
-**"AI as coach, not crutch"** - preserves learning-through-doing while leveraging AI for guardrails and feedback.
+- `/coach plan refactor auth` → Co-authored planning with Socratic questions
+- `/coach scaffold src/lib/auth.ts` → Generate types/signatures for that file
+- `/coach review` → Review recent changes with inline questions
+- `/coach challenge --staged` → Challenge on staged changes
 
-## Usage
+## Quick Reference
 
 ```
 /coach plan {task}          # Co-authored planning with Socratic questions
-/coach scaffold             # Generate types/signatures for current context
-/coach scaffold {path}      # Generate scaffold for specific file/feature
-/coach review               # Review recent changes with inline questions
-/coach review {path}        # Review specific file with inline questions
-/coach check                # Process comment responses (defers to /comments check)
-/coach challenge            # Productive struggle on current file
-/coach challenge {path}     # Challenge on specific file
-/coach challenge --staged   # Challenge on staged changes
+/coach scaffold [{path}]    # Generate types/signatures
+/coach review [{path}]      # Review with inline questions
+/coach challenge [{path}]   # Productive struggle mode
 ```
 
-## Mode Behaviour
-
-### plan
-
-- Co-author, don't dictate
-- ~30% proposing, ~70% questioning
-- Offer to create brain doc for persistence
-
-### scaffold
-
-- Types, signatures, stubs with hint comments
-- Points at what to think about, not the answer
-- Human fills in the actual logic
-
-### review
-
-- Uses comments skill for inline `// @{user}` questions
-- Socratic - probe reasoning, don't fix code
-- Vary questions based on context
-
-### check
-
-- Defers to `/comments check`
-
-### challenge
-
-- Productive struggle - find what you missed
-- Guide discovery, don't give answers
-- Opt-in for those seeking growth
-
-## Configuration
-
-Read `~/.droid/skills/coach/overrides.yaml` for:
-
-- `scaffold_verbosity` - `minimal` | `medium` | `detailed`
-
-## The Golden Rule
-
-**Never write code unless explicitly asked.** Only ask questions, explain tradeoffs, provide hints, or generate structure.
+See the **coach skill** for complete documentation and procedures.

package/{dist/tools/coach/skills/droid-coach → src/tools/coach/skills/coach}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: droid-coach
+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'."
 alwaysApply: false
 allowed-tools: [Read, Grep, Glob]
@@ -40,7 +40,7 @@ plan → AI scaffolds → human implements → AI coaches → iterate → ship
 ## Commands
 
 | Command            | Purpose                                                 |
-|--------------------|---------------------------------------------------------|
+| ------------------ | ------------------------------------------------------- |
 | `/coach plan`      | Co-authored planning with Socratic questions            |
 | `/coach scaffold`  | Generate types/signatures/stubs with hints              |
 | `/coach review`    | Inline questions via comments skill                     |
@@ -50,7 +50,7 @@ plan → AI scaffolds → human implements → AI coaches → iterate → ship
 ## Configuration
 
 | Setting              | Default  | Description                                             |
-|----------------------|----------|---------------------------------------------------------|
+| -------------------- | -------- | ------------------------------------------------------- |
 | `scaffold_verbosity` | `medium` | How detailed hints are: `minimal`, `medium`, `detailed` |
 
 > @fry Not yet - droid currently shows config as free text input. But we could add an `enum` type to the config schema that presents as a select dropdown in the TUI. Good feature request - want me to create an issue for it?
@@ -139,6 +139,7 @@ Read from `~/.droid/skills/coach/overrides.yaml` if present.
 // @fry What happens if this promise rejects?
 // @fry I notice you're mutating state directly - was that intentional?
 ```
+
 > @droid is it worth mentioning using the correct comment syntax for the file language? We typically use TS but could be others
 
 **Key principle:** Vary questions based on specific code and context. Avoid formulaic patterns. Questions show the _spirit_, not a script.

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

@@ -1,6 +1,6 @@
 {
   "name": "droid-code-review",
-  "version": "0.1.2",
+  "version": "0.2.0",
   "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

@@ -1,14 +1,15 @@
 name: code-review
 description: "Comprehensive code review using specialized agents. Reviews PRs, staged changes, branches, or specific files with confidence scoring."
-version: 0.1.2
+version: 0.2.0
 status: alpha
 
 includes:
   skills:
-    - name: droid-code-review
+    - name: code-review
       required: true
   commands:
-    - code-review
+    - name: code-review
+      is_alias: false
   agents:
     - edi-standards-reviewer
     - error-handling-reviewer

package/src/tools/code-review/commands/code-review.md

@@ -1,113 +1,29 @@
 ---
-description: Run comprehensive code review using specialized agents. Accepts PR number, 'staged', 'branch', or file path.
+name: code-review
+description: "Run comprehensive code review using specialized agents. Accepts PR number, 'staged', 'branch', or file path."
 argument-hint: "[#123 | staged | branch | path/to/file.ts]"
-allowed-tools: [Task, Bash(git:*), Bash(gh:*), Read, Glob]
 ---
 
-# /code-review - Run comprehensive code review using specialized agents
+# /code-review
 
-Review target: $ARGUMENTS
+**User invoked:** `/code-review $ARGUMENTS`
 
-## Usage
+**Your task:** Invoke the **code-review skill** with these arguments.
 
-```
-/code-review #123           # Review PR #123
-/code-review staged         # Review staged changes
-/code-review branch         # Review current branch vs main
-/code-review path/to/file   # Review specific file
-```
-
-### Step 0: Check for Brain Integration
-
-**If the `brain` skill is installed** (check for `~/.claude/skills/brain/SKILL.md` or `~/.config/opencode/skills/brain/SKILL.md`):
-
-Ask the user: **"Would you like the review results saved to a `/brain review` doc?"**
-
-- If yes: Create a brain review doc at the start using `/brain review {PR title or branch name}`
-- The final report will be written to the brain doc instead of just displayed
-- This allows for async discussion via `@droid`/`@{user}` comments
-
-If brain skill is not installed or user declines, proceed with normal terminal output.
-
-### Step 1: Determine Review Scope
-
-Parse the argument to determine what to review:
-
-**If argument starts with `#` or is a number (e.g., `#123` or `123`):**
-
-- This is a PR number
-- Fetch PR details: `gh pr view $PR_NUMBER --json title,body,baseRefName,headRefName,files`
-- Get the diff: `gh pr diff $PR_NUMBER`
-- Note the PR author and description for context
-
-**If argument is `staged` or empty:**
-
-- Review staged changes: `git diff --cached`
-
-**If argument is `branch`:**
-
-- Review current branch vs main: `git diff origin/main...HEAD`
-
-**If argument is a file path:**
-
-- Review specific file: `git diff HEAD -- $FILE_PATH`
-- If no changes, review the entire file for issues
-
-### Step 2: Gather Context
-
-For PR reviews, also fetch:
-
-- PR description (may contain context about the change)
-- Linked issues: `gh pr view $PR_NUMBER --json body` and parse for #issue refs
-- Changed files list for targeted agent assignment
+## Examples
 
-### Step 3: Parallel Agent Reviews
+- `/code-review #123` → Review PR #123 using specialized agents
+- `/code-review staged` → Review currently staged changes
+- `/code-review branch` → Review current branch vs main
+- `/code-review src/lib/auth.ts` → Review specific file
 
-Launch these agents in parallel using the Task tool with `run_in_background: true`:
+## Quick Reference
 
-1. **edi-standards-reviewer**: EDI patterns, partnership handling, billing concerns
-2. **test-coverage-analyzer**: Test completeness and edge cases
-3. **error-handling-reviewer**: Silent failures, missing error handling
-4. **type-reviewer**: Type design, interface contracts
-
-Pass each agent:
-
-1. The diff content
-2. The full file content for changed files (for context)
-3. PR description if available
-
-Use TaskOutput to collect results from all agents.
-
-### Step 4: Confidence Filtering
-
-Each agent returns issues with confidence scores (0-100).
-Filter out issues with confidence < 80.
-
-### Step 5: Synthesize Report
-
-Compile findings into a prioritized report:
-
-**PR #123: "Add partnership billing events"** (if reviewing a PR)
-_Author: @username_
-
-**Critical** (security, data loss, billing errors)
-
-- `file.ts:42` - Issue description
-
-**Important** (bugs, missing tests, type issues)
-
-- `file.ts:67` - Issue description
-
-**Suggestions** (style, readability)
-
-- `file.ts:89` - Issue description
-
-**Summary**: X critical, Y important, Z suggestions across N files.
-
-### Step 6: Offer Actions (for PRs)
-
-After presenting the report, offer:
+```
+/code-review #123           # Review PR
+/code-review staged         # Review staged changes
+/code-review branch         # Review current branch
+/code-review {path}         # Review specific file
+```
 
-- "Would you like me to post this as a PR comment?"
-- "Should I suggest fixes for any of these issues?"
-- "Want me to check out this branch and fix the critical issues?"
+See the **code-review skill** for complete documentation and procedures.

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

@@ -0,0 +1,154 @@
+---
+name: code-review
+description: "Comprehensive code review using specialized agents. Use when reviewing PRs, checking staged changes, or analysing code quality. User prompts like 'review this PR', 'check my changes', 'review before I commit'."
+globs:
+  - "**/*"
+alwaysApply: false
+allowed-tools: [Read, Grep, Glob, Bash, Task]
+---
+
+# Code Review Skill
+
+Run comprehensive code reviews using specialized agents, each focused on a specific concern.
+
+## How It Works
+
+The `/code-review` command orchestrates multiple specialized agents in parallel:
+
+1. **edi-standards-reviewer** - EDI patterns, partnership handling, billing concerns
+2. **test-coverage-analyzer** - Test completeness and edge cases
+3. **error-handling-reviewer** - Silent failures, missing error handling
+4. **type-reviewer** - TypeScript type design, interface contracts
+
+Each agent returns issues with confidence scores (0-100). Issues below 80% confidence are filtered out to reduce noise.
+
+## Usage
+
+```bash
+/code-review #123           # Review PR #123
+/code-review staged         # Review staged changes
+/code-review branch         # Review current branch vs main
+/code-review path/to/file   # Review specific file
+```
+
+## Output Format
+
+Reviews are presented in prioritized categories:
+
+🔴 **Critical** - Security, data loss, billing errors
+🟠 **Important** - Bugs, missing tests, type issues
+🟡 **Suggestions** - Style, readability improvements
+
+## Post-Review Actions
+
+After presenting findings, you can:
+
+- Post the review as a PR comment
+- Get suggested fixes for specific issues
+- Check out the branch and fix critical issues
+
+## Domain-Aware Reviews
+
+The EDI Standards Reviewer discovers project conventions by reading:
+
+- `.claude/CLAUDE.md` or `CLAUDE.md` for team conventions
+- `AGENTS.md` or `docs/` for architecture guidance
+
+This lets it apply your project's specific patterns rather than generic rules.
+
+## Review Procedure
+
+### Step 0: Check for Brain Integration
+
+**If the `brain` skill is installed** (check for `~/.claude/skills/brain/SKILL.md` or `~/.config/opencode/skills/brain/SKILL.md`):
+
+Ask the user: **"Would you like the review results saved to a `/brain review` doc?"**
+
+- If yes: Create a brain review doc at the start using `/brain review {PR title or branch name}`
+- The final report will be written to the brain doc instead of just displayed
+- This allows for async discussion via `@droid`/`@{user}` comments
+
+If brain skill is not installed or user declines, proceed with normal terminal output.
+
+### Step 1: Determine Review Scope
+
+Parse the argument to determine what to review:
+
+**If argument starts with `#` or is a number (e.g., `#123` or `123`):**
+
+- This is a PR number
+- Fetch PR details: `gh pr view $PR_NUMBER --json title,body,baseRefName,headRefName,files`
+- Get the diff: `gh pr diff $PR_NUMBER`
+- Note the PR author and description for context
+
+**If argument is `staged` or empty:**
+
+- Review staged changes: `git diff --cached`
+
+**If argument is `branch`:**
+
+- Review current branch vs main: `git diff origin/main...HEAD`
+
+**If argument is a file path:**
+
+- Review specific file: `git diff HEAD -- $FILE_PATH`
+- If no changes, review the entire file for issues
+
+### Step 2: Gather Context
+
+For PR reviews, also fetch:
+
+- PR description (may contain context about the change)
+- Linked issues: `gh pr view $PR_NUMBER --json body` and parse for #issue refs
+- Changed files list for targeted agent assignment
+
+### Step 3: Parallel Agent Reviews
+
+Launch these agents in parallel using the Task tool with `run_in_background: true`:
+
+1. **edi-standards-reviewer**: EDI patterns, partnership handling, billing concerns
+2. **test-coverage-analyzer**: Test completeness and edge cases
+3. **error-handling-reviewer**: Silent failures, missing error handling
+4. **type-reviewer**: Type design, interface contracts
+
+Pass each agent:
+
+1. The diff content
+2. The full file content for changed files (for context)
+3. PR description if available
+
+Use TaskOutput to collect results from all agents.
+
+### Step 4: Confidence Filtering
+
+Each agent returns issues with confidence scores (0-100).
+Filter out issues with confidence < 80.
+
+### Step 5: Synthesize Report
+
+Compile findings into a prioritized report:
+
+**PR #123: "Add partnership billing events"** (if reviewing a PR)
+_Author: @username_
+
+**Critical** (security, data loss, billing errors)
+
+- `file.ts:42` - Issue description
+
+**Important** (bugs, missing tests, type issues)
+
+- `file.ts:67` - Issue description
+
+**Suggestions** (style, readability)
+
+- `file.ts:89` - Issue description
+
+**Summary**: X critical, Y important, Z suggestions across N files.
+
+### Step 6: Offer Actions (for PRs)
+
+After presenting the report, offer:
+
+- "Would you like me to post this as a PR comment?"
+- "Should I suggest fixes for any of these issues?"
+- "Want me to check out this branch and fix the critical issues?"

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

@@ -1,6 +1,6 @@
 {
   "name": "droid-codex",
-  "version": "0.1.5",
+  "version": "0.1.6",
   "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

@@ -1,14 +1,15 @@
 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: 0.1.5
+version: 0.1.6
 status: beta
 
 includes:
   skills:
-    - name: droid-codex
+    - name: codex
       required: true
   commands:
-    - codex
+    - name: codex
+      is_alias: false
   agents:
     - codex-document-processor
 

package/src/tools/codex/commands/codex.md

@@ -1,78 +1,31 @@
 ---
-description: Shared organizational knowledge - PRDs, tech designs, patterns, domains, proposals, and explored topics
+name: codex
+description: "Shared organizational knowledge - PRDs, tech designs, patterns, domains, proposals, and explored topics"
 argument-hint: "[projects | domains | proposals | patterns | topics | {name} | search {query} | new {type} {name} | decision {text}]"
-allowed-tools: [Read, Write, Edit, Glob, Grep, Bash(gh:*), Bash(git:*), Bash(ls:*), Bash(mkdir:*)]
 ---
 
 # /codex
 
-Entry point for shared organizational knowledge. See the **codex skill** for full behaviour.
+**User invoked:** `/codex $ARGUMENTS`
 
-> Context is AI's multiplier. This is Orderful's.
-
-## Arguments
-
-$ARGUMENTS
-
-## Prerequisites
-
-Before first use, verify:
-
-1. **Repo cloned** at configured `codex_repo` path
-2. **gh CLI** installed and authenticated
-
-## Usage
-
-```bash
-/codex                           # Show categories (5 total)
-/codex projects                  # List projects
-/codex domains                   # List domains
-/codex proposals                 # List proposals
-/codex patterns                  # List patterns
-/codex topics                    # List topics
-/codex {name}                    # Load entry (searches all categories)
-/codex search {query}            # Search across everything
-/codex new {name}                # Scaffold new project (shorthand)
-/codex new project {name}        # Scaffold new project from templates
-/codex new domain {name}         # Scaffold new domain entry
-/codex new proposal {name}       # Scaffold new proposal entry
-/codex new pattern {name}        # Scaffold new pattern entry
-/codex new topic {name}          # Scaffold new topic entry
-/codex decision {text}           # Append to active project's DECISIONS.md
-/codex snapshot {type} {file} {name}  # Import PDF/markdown to codex
-/codex artifact {file} {project}      # Add supporting artifact to project
-```
-
-## Configuration
-
-**ALWAYS read `~/.droid/skills/codex/overrides.yaml` first.**
-
-- `codex_repo` - Path to local orderful-codex repository (required)
-- `freshness_days` - Days before showing staleness warning (default: 30)
-
-## Behaviour
-
-Refer to the codex skill for:
-- **Loading**: How to search, handle matches, check freshness, auto-generate CONTEXT.md
-- **Decisions**: How to append to active project's DECISIONS.md
-- **Creating**: How to scaffold new entries (projects, domains, proposals, patterns, topics)
-
-The skill's `references/` folder contains detailed procedures for each workflow.
+**Your task:** Invoke the **codex skill** with these arguments.
 
 ## Examples
 
-```bash
-# Load project context
-/codex transaction-templates
-
-# Search for webhook-related content
-/codex search webhook
+- `/codex projects` → List all projects in the codex
+- `/codex transaction-templates` → Load the transaction-templates entry
+- `/codex search webhook` → Search for "webhook" across all codex content
+- `/codex new project billing-v2` → Create new project scaffolding
+- `/codex decision "Use PostgreSQL for audit log"` → Append decision to active project
 
-# Capture a decision during implementation
-/codex decision "Using UUIDv7 for IDs because it's sortable and includes timestamp"
+## Quick Reference
 
-# Create new entries
-/codex new domain partnerships
-/codex new proposal caching-layer
-/codex new topic organization-hierarchy
 ```
+/codex                      # Show categories overview
+/codex {name}               # Load entry (searches all categories)
+/codex search {query}       # Search across everything
+/codex new project {name}   # Scaffold new project
+/codex decision {text}      # Append to active project's DECISIONS.md
+```
+
+See the **codex skill** for complete documentation and procedures.