@orderful/droid 0.44.1 → 0.45.1

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

@@ -46,10 +46,21 @@ Create a release PR, auto-lock the release branch, and notify Slack.
    # Get commits in release_branch that aren't in production_branch
    gh api repos/{owner}/{repo}/compare/{production_branch}...{release_branch} --jq '.commits[].commit.message'
    ```
-   Extract PR numbers from commit messages (e.g. `(#1234)`) and format as a bulleted list for the PR body.
+   Extract PR numbers from commit messages (e.g. `(#1234)`). For each extracted PR number, fetch metadata including labels:
+   ```bash
+   gh pr view {pr_number} --json number,title,author,labels --repo {owner}/{repo}
+   ```
+   Build the PR list for the body from the results. Collect `HIGH_RISK_PRS` — an array of `{number, title, author}` for any PR whose `labels` array includes an entry with `name: "high-risk"`.
 
    **Do NOT use** `gh pr list --base {release_branch} --state merged` — that returns ALL historically merged PRs, not just the ones since the last release.
 
+3.5. **Warn if high-risk PRs found** — if `HIGH_RISK_PRS` is non-empty, print a terminal warning:
+   ```
+   ⚠️  {n} high-risk PR(s) detected in this release:
+     - #{number} {title} (@{author})
+     ...
+   ```
+
 4. **Ask risk level** — use AskUserQuestion:
    - Low Risk (routine release, no breaking changes)
    - High Risk (breaking changes, data migrations, or high-traffic feature)
@@ -64,6 +75,11 @@ Create a release PR, auto-lock the release branch, and notify Slack.
      --body "{release_pr_body}" \
      --repo {owner}/{repo}
    ```
+   If `HIGH_RISK_PRS` is non-empty, also add `--label "high-risk"` to the command above. If the `high-risk` label does not exist on the repo, `gh pr create` will fail — in that case, retry without `--label "high-risk"` and warn the user:
+   ```
+   ⚠️  Could not apply 'high-risk' label — label does not exist on {repo_name}. Create it in GitHub Labels settings, then add it manually to PR #{number}.
+   ```
+
    See `templates.md` for the PR body template.
 
 6. **Auto-lock branch** (unless `--no-lock`):
@@ -105,7 +121,7 @@ Merge the release PR if all checks are green, then notify Slack.
 
 2. **Find the open release PR:**
    ```bash
-   gh pr list --search "[RELEASE]" --state open --base {production_branch} --head {release_branch} --json number,title,url,statusCheckRollup --repo {owner}/{repo}
+   gh pr list --search "[RELEASE]" --state open --base {production_branch} --head {release_branch} --json number,title,url,statusCheckRollup,labels --repo {owner}/{repo}
    ```
    If no open release PR found, error: "No open release PR found. Run `/release start` first."
 
@@ -115,7 +131,10 @@ Merge the release PR if all checks are green, then notify Slack.
    If any checks are pending: "CI checks are still running on PR #{number}. Wait for them to finish."
    If any checks are failing: "CI checks are failing on PR #{number}. Fix them before merging." Show the failing checks.
 
-4. **Confirm with user** — use AskUserQuestion:
+4. **Confirm with user** — if the release PR's `labels` includes `"high-risk"`, first show an extra AskUserQuestion confirmation:
+   "⚠️ This release includes high-risk PRs. Confirm you have coordinated with the contributors and are ready to proceed."
+
+   Then (regardless of high-risk) show the standard AskUserQuestion:
    "All checks are green on PR #{number}. Merge `{release_branch}` → `{production_branch}`?"
 
 5. **Merge the PR:**
@@ -216,7 +235,7 @@ Check release status across all configured release repos.
 
    **Open release PRs:**
    ```bash
-   gh pr list --search "[RELEASE]" --state open --json number,title,url,statusCheckRollup --repo {owner}/{repo}
+   gh pr list --search "[RELEASE]" --state open --json number,title,url,statusCheckRollup,labels --repo {owner}/{repo}
    ```
 
    **Lock state:**
@@ -232,6 +251,11 @@ Check release status across all configured release repos.
      Branch lock: {release_branch} — locked/unlocked
    ```
 
+   If the release PR's `labels` includes `"high-risk"`, append to the repo's status block:
+   ```
+     ⚠️  High-risk PRs included
+   ```
+
    If no open release PR: "No active release"
    If no release repos configured: "No release repos configured"
 

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

@@ -1,6 +1,6 @@
 {
   "name": "droid-share",
-  "version": "0.1.0",
+  "version": "0.1.1",
   "description": "Share content to external platforms. Publish docs to Confluence or post summaries to Slack.",
   "author": {
     "name": "Orderful",

package/dist/tools/share/TOOL.yaml

@@ -1,6 +1,6 @@
 name: share
 description: "Share content to external platforms. Publish docs to Confluence or post summaries to Slack."
-version: 0.1.0
+version: 0.1.1
 status: beta
 
 includes:

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

@@ -26,6 +26,12 @@ Share content to external platforms. Two modes:
 | Confluence | Atlassian MCP (`mcp__claude_ai_Atlassian__*`) | Publish document as page |
 | Slack | `droid integrations slack post` | Process + post message |
 
+## Custom Instructions
+
+Any command accepts a ` -- {instruction}` suffix. Split on the **first** ` -- ` (space-dash-dash-space): left is the command and its args, right is additional context or instruction to carry through the entire execution. For the Slack flow specifically, the `--` instruction becomes the formatting directive (step S3).
+
+Example: `/share slack #eng -- summarise the action items and tag owners`
+
 ## Procedure
 
 ### 1. Resolve Platform

package/dist/tools/status-update/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "droid-status-update",
-  "version": "0.2.1",
+  "version": "0.2.2",
   "description": "Generate and post project status updates. Aggregates context from codex projects, Jira epics, and manual input. Posts to Slack or prints to terminal.",
   "author": {
     "name": "Orderful",

package/dist/tools/status-update/TOOL.yaml

@@ -1,6 +1,6 @@
 name: status-update
 description: "Generate and post project status updates. Aggregates context from codex projects, Jira epics, and manual input. Posts to Slack or prints to terminal."
-version: 0.2.1
+version: 0.2.2
 status: beta
 
 includes:

package/dist/tools/status-update/skills/status-update/SKILL.md

@@ -30,6 +30,12 @@ Generate formatted project status updates from multiple sources and post to Slac
 |-------------|----------------|----------|
 | **Slack** | If slack.channel configured + SLACK_USER_TOKEN set | Print to terminal |
 
+## Custom Instructions
+
+Any command accepts a ` -- {instruction}` suffix. Split on the **first** ` -- ` (space-dash-dash-space): left is the command and its args, right is additional context or instruction to carry through the entire execution.
+
+Example: `/status-update droid -- emphasise the auth refactor milestone we shipped`
+
 ## Procedure
 
 ### 1. Resolve Project Context

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

@@ -1,6 +1,6 @@
 {
   "name": "droid-tech-design",
-  "version": "0.3.0",
+  "version": "0.3.1",
   "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: 0.3.0
+version: 0.3.1
 status: beta
 
 includes:

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

@@ -47,6 +47,12 @@ Tech-design has no configuration of its own. It delegates to:
 
 **Overrides:** This skill supports user-defined overrides. See `/droid` skill § Skill Overrides.
 
+## Custom Instructions
+
+Any command accepts a ` -- {instruction}` suffix. Split on the **first** ` -- ` (space-dash-dash-space): left is the command and its args, right is additional context or instruction to carry through the entire execution. Note: flag-style `--from` and similar flags use `--flag` syntax (no surrounding spaces) and are distinct from this separator.
+
+Example: `/tech-design draft rollout -- keep it concise, we have limited Ops bandwidth`
+
 ## Four-Document Approach
 
 | Document        | Created When | Purpose                                                  | Location                                         | Audience       | Length  |

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

@@ -1,6 +1,6 @@
 {
   "name": "droid-wrapup",
-  "version": "0.1.3",
+  "version": "0.1.5",
   "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: 0.1.3
+version: 0.1.5
 status: alpha
 
 includes:
@@ -13,4 +13,8 @@ includes:
 
 dependencies: []
 
-config_schema: {}
+config_schema:
+  persist_recaps:
+    type: string
+    default: 'false'
+    description: 'Persist session recap files to brain vault wrapups folder'

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

@@ -10,16 +10,25 @@ Session wrap-up that captures decisions, learnings, and open items before closin
 
 ## Configuration
 
-Wrapup has no configuration of its own. It reads config from other installed tools:
+Wrapup reads config from other installed tools, plus its own settings:
 
 - **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
+- **Brain skill** (optional): `droid config --get tools.brain` → `brain_dir` and `inbox_folder` to update brain docs
 - **Codex skill** (optional): `droid config --get tools.codex` → `codex_repo` to suggest codex entries
+- **Wrapup own config** (optional): `droid config --get tools.wrapup` → `persist_recaps` (`'true'` / `'false'`, default `'false'`)
 
 If these tools aren't configured, wrapup skips those artifacts and focuses on git state and conversation summary.
 
+When `persist_recaps` is `'true'` and brain is configured, session briefs are saved to the brain vault in Phase 4 (see below).
+
 **Overrides:** This skill supports user-defined overrides. See `/droid` skill § Skill Overrides.
 
+## Custom Instructions
+
+Any command accepts a ` -- {instruction}` suffix. Split on the **first** ` -- ` (space-dash-dash-space): left is the command and its args, right is additional context or instruction to carry through the entire execution.
+
+Example: `/wrapup -- also capture the tech debt items we discussed`
+
 ## Context Lifeboat Pattern
 
 This skill runs at the END of sessions when context pressure is highest.
@@ -98,3 +107,17 @@ Present options using AskUserQuestion:
 - **"Skip"** → Close without updating
 
 On approval, write updates using appropriate format for each destination.
+
+**Session recap persistence (if `persist_recaps` is `'true'`):**
+
+After writing all other updates, check whether session briefs should be persisted:
+
+1. Run `droid config --get tools.wrapup` and check if `persist_recaps` equals `'true'`. If not, skip.
+2. Run `droid config --get tools.brain` and parse `brain_dir` and `inbox_folder`.
+   - If `brain_dir` is not set, skip.
+3. Construct the destination path:
+   - If `inbox_folder` is non-empty: `{brain_dir}/{inbox_folder}/wrapups/{session-id}.md`
+   - If `inbox_folder` is empty or absent: `{brain_dir}/wrapups/{session-id}.md`
+   - Avoid double slashes — do not append `inbox_folder` when it is an empty string.
+4. Create the `wrapups/` directory if it does not exist, then copy the Phase 1 brief from `/tmp/wrapup-{session-id}.md` to the constructed path.
+5. Inform the user the recap was saved and where.

package/dist/tools/wrapup/skills/wrapup/references/output-schema.md

@@ -28,7 +28,7 @@ Structured format for subagent findings. Main agent uses this to synthesise the
   ],
   "suggested_actions": [
     {
-      "type": "commit | codex_topic | file_bug | update_docs",
+      "type": "commit | codex_topic | codex_update | file_bug | update_docs",
       "content": "description of suggested action",
       "priority": "high | medium | low"
     }
@@ -63,7 +63,8 @@ Item categories:
 
 Actions that need user judgment:
 - `commit`: Git changes ready to commit
-- `codex_topic`: Knowledge worth codifying
+- `codex_topic`: Net-new knowledge worth codifying as a new codex entry
+- `codex_update`: Update to an existing codex entry (distinct from `codex_topic` which suggests net-new content)
 - `file_bug`: Bug discovered but not filed
 - `update_docs`: Documentation that needs updating
 
@@ -87,7 +88,8 @@ Actions that need user judgment:
   ],
   "suggested_actions": [
     {"type": "commit", "content": "4 files ready: TOOL.yaml, SKILL.md, wrapup.md, changeset", "priority": "high"},
-    {"type": "codex_topic", "content": "Context lifeboat pattern for end-of-session tooling", "priority": "medium"}
+    {"type": "codex_topic", "content": "Context lifeboat pattern for end-of-session tooling", "priority": "medium"},
+    {"type": "codex_update", "content": "Update 'droid' codex entry: add context-lifeboat pattern and subagent parallelisation decision from today's session", "priority": "low"}
   ]
 }
 ```

package/dist/tools/wrapup/skills/wrapup/references/subagent-prompts.md

@@ -76,20 +76,61 @@ Output:
 **Subagent type:** Explore
 
 ```
-Read {session_brief_path} for session context.
-
-Run `droid config --get tools.codex` and check if `codex_repo` is set.
-If not configured, skip codex analysis.
-
-If the session involved:
-- Deep research on a topic
-- Discovering patterns or best practices
-- Solving a non-trivial problem with reusable insights
-
-Then suggest potential codex topics:
-- Topic name
+Read {session_brief_path} for session context. Pay particular attention to the
+"Decisions Made" and "Key Learnings" sections — these are the primary signals
+for both new codex topics and updates to existing entries.
+
+Run `droid config --get tools.codex` and parse the JSON output for `codex_repo`.
+If `codex_repo` is not set, output "No codex suggestions (codex not configured)" and stop.
+
+--- Discover existing codex content ---
+
+1. Attempt to read `{codex_repo}/.codex/manifest.yaml` to get an inventory of
+   existing entries and projects.
+   - If the manifest does not exist, fall back: list the top-level directories
+     inside `{codex_repo}` to infer project names.
+2. Skim entry names, titles, and tags — you do NOT need to read full entry bodies
+   at this stage. Goal is a compact list of what already exists.
+
+--- Compare session against existing codex content ---
+
+3. For each decision or learning in the session brief, check whether it relates
+   to an existing codex entry or project:
+   - A decision "relates to" an entry if the topic, technology, or system name
+     overlaps (e.g., a decision about the droid project file format relates to
+     a codex entry named "droid" or "tool-configuration").
+   - Threshold: if 2 or more session decisions/learnings relate to the same
+     existing codex entry, emit a `codex_update` suggestion for that entry.
+   - For a single related decision/learning, use your judgment — only suggest
+     an update if the insight is clearly additive and not already captured.
+
+4. Read the full content of any existing entries flagged in step 3 to confirm
+   the insight is genuinely new (avoid duplicate suggestions).
+
+--- Identify net-new codex topics ---
+
+5. For decisions/learnings that do NOT relate to any existing entry, consider
+   whether they merit a brand-new codex topic:
+   - Deep research findings
+   - Discovered patterns or best practices
+   - Non-trivial problems solved with reusable insights
+
+--- Output ---
+
+Produce two buckets:
+
+**Suggested updates to existing codex entries (codex_update):**
+For each:
+- Entry name (as it appears in the codex)
+- What to add or amend (specific content, not vague)
+- Which session decisions/learnings drove this suggestion
+- Why the existing entry is incomplete without this update
+
+**Suggested new codex topics (codex_topic):**
+For each:
+- Proposed topic name
 - Brief description of what to capture
 - Why it's worth codifying (reusable, non-obvious, hard-won knowledge)
 
-Output: List of suggested codex topics, or "No codex suggestions" if session was routine.
+If neither bucket has entries, output "No codex suggestions".
 ```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@orderful/droid",
-  "version": "0.44.1",
+  "version": "0.45.1",
   "description": "AI workflow toolkit for sharing skills, commands, and agents across the team",
   "type": "module",
   "bin": {

package/src/commands/tui.tsx

@@ -39,6 +39,7 @@ import { ReposViewerScreen } from './tui/views/ReposViewerScreen';
 import { useAppUpdate } from './tui/hooks/useAppUpdate';
 import { useToolUpdates } from './tui/hooks/useToolUpdates';
 import { checkGhAuth } from '../integrations/github';
+import { checkGranolaAuth } from '../integrations/granola';
 
 // Module-level variable to store exit message (printed after leaving alternate screen)
 let exitMessage: string | null = null;
@@ -203,6 +204,16 @@ function App() {
     }
   }, []);
 
+  // Detect Granola MCP server on first mount by reading Claude Code settings
+  useEffect(() => {
+    if (!getConfigValue('integrations.granola.configured')) {
+      const isConfigured = checkGranolaAuth();
+      if (isConfigured) {
+        setConfigValue('integrations.granola.configured', true);
+      }
+    }
+  }, []);
+
   useInput(
     (input, key) => {
       if (message) setMessage(null);

package/src/integrations/granola/index.ts

@@ -0,0 +1,28 @@
+import { join } from 'path';
+import { homedir } from 'os';
+import { existsSync, readFileSync } from 'fs';
+
+/**
+ * Check if a Granola MCP server is registered in Claude Code's settings.
+ * Returns true if any mcpServers entry key contains "granola" (case-insensitive).
+ */
+export function checkGranolaAuth(): boolean {
+  try {
+    const settingsPath = join(homedir(), '.claude', 'settings.json');
+    if (!existsSync(settingsPath)) {
+      return false;
+    }
+
+    const raw = readFileSync(settingsPath, 'utf-8');
+    const settings = JSON.parse(raw) as Record<string, unknown>;
+
+    const mcpServers = settings['mcpServers'];
+    if (!mcpServers || typeof mcpServers !== 'object') {
+      return false;
+    }
+
+    return Object.keys(mcpServers).some((key) => key.toLowerCase().includes('granola'));
+  } catch {
+    return false;
+  }
+}

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

@@ -1,6 +1,6 @@
 {
   "name": "droid-brain",
-  "version": "0.4.0",
+  "version": "0.4.1",
   "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: 0.4.0
+version: 0.4.1
 status: beta
 
 includes:

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

@@ -47,6 +47,12 @@ droid config --set tools.brain.brain_dir="{user's choice}"
 
 **Overrides:** This skill supports user-defined overrides. See `/droid` skill § Skill Overrides for how to create, register, and use overrides.
 
+## Custom Instructions
+
+Any command accepts a ` -- {instruction}` suffix. Split on the **first** ` -- ` (space-dash-dash-space): left is the command and its args, right is additional context or instruction to carry through the entire execution.
+
+Example: `/brain research caching -- focus on Redis patterns`
+
 ## Commands
 
 **Reserved keywords:** `search`, `add`, `check`, `cleanup`, `done`

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

@@ -1,6 +1,6 @@
 {
   "name": "droid-coach",
-  "version": "0.2.4",
+  "version": "0.3.0",
   "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: 0.2.4
+version: 0.3.0
 status: beta
 
 includes:
@@ -20,3 +20,7 @@ config_schema:
     type: string
     description: "How detailed scaffold hints should be: minimal (signatures only), medium (hints), detailed (pseudocode)"
     default: "medium"
+  coaching_intensity:
+    type: string
+    description: "How Socratic coaching interactions are: light (1-2 targeted questions, concise), moderate (2-3 questions, brief context), deep (thorough exploration, current behaviour)"
+    default: "moderate"

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

@@ -49,10 +49,11 @@ plan → AI scaffolds → human implements → AI coaches → iterate → ship
 
 ## Configuration
 
-| Setting              | Default  | Description                                             |
-| -------------------- | -------- | ------------------------------------------------------- |
-| `scaffold_verbosity` | `medium` | How detailed hints are: `minimal`, `medium`, `detailed` |
-| `override`           | (none)   | User-defined behaviour overrides                        |
+| Setting               | Default    | Description                                                                                       |
+| --------------------- | ---------- | ------------------------------------------------------------------------------------------------- |
+| `scaffold_verbosity`  | `medium`   | How detailed hints are: `minimal`, `medium`, `detailed`                                           |
+| `coaching_intensity`  | `moderate` | How Socratic interactions are: `light` (1-2 questions, concise), `moderate` (2-3 questions), `deep` (thorough Socratic exploration) |
+| `override`            | (none)     | User-defined behaviour overrides                                                                  |
 
 **Overrides:** This skill supports user-defined overrides. See `/droid` skill § Skill Overrides.
 
@@ -62,6 +63,26 @@ plan → AI scaffolds → human implements → AI coaches → iterate → ship
 
 Run `droid config --get tools.coach` to get the merged configuration.
 
+## Custom Instructions
+
+Any command accepts a ` -- {instruction}` suffix. Split on the **first** ` -- ` (space-dash-dash-space): left is the command and its args, right is additional context or instruction to carry through the entire execution.
+
+Example: `/coach plan add auth endpoint -- treat me as a junior learning OAuth for the first time`
+
+---
+
+## Output Discipline
+
+Before each coaching interaction, read `coaching_intensity` from config (`droid config --get tools.coach`):
+
+| Intensity  | Questions per turn | Response length                         |
+| ---------- | ------------------ | --------------------------------------- |
+| `light`    | 1–2 targeted       | Concise — one short paragraph per point |
+| `moderate` | 2–3 focused        | Brief — 3–5 points, context per question (default) |
+| `deep`     | 3+                 | Thorough — current behaviour            |
+
+**Regardless of intensity:** Prefer one sharp, well-framed question over three surface-level ones. Limit each response to 3–5 focused points rather than exhaustive lists. Quality of challenge over quantity of questions.
+
 ---
 
 ## /coach plan
@@ -70,7 +91,10 @@ Run `droid config --get tools.coach` to get the merged configuration.
 
 **Behaviour:**
 
-- Ratio: ~40% proposing, ~60% questioning
+- Proposing/questioning ratio by intensity:
+  - `light` — ~60% proposing, ~40% questioning (lead with concrete guidance)
+  - `moderate` — ~50% proposing, ~50% questioning (default)
+  - `deep` — ~40% proposing, ~60% questioning (current Socratic-heavy behaviour)
 - Ask questions that probe requirements, edge cases, and design tradeoffs
 - Propose structure but let human refine
 - Offer to create a brain doc: "Would you like me to create a brain doc to capture this plan?"
@@ -135,6 +159,7 @@ Run `droid config --get tools.coach` to get the merged configuration.
 - Add inline `// @{user} {question}` comments using the comments skill pattern
 - Questions should probe reasoning, not just confirm choices
 - Focus on: design decisions, edge cases, potential issues, alternatives
+- Question density follows `coaching_intensity`: `light` → 1–2 comments per changed block; `moderate` → 2–3; `deep` → as many as warranted
 
 **Example inline comments:**
 
@@ -179,6 +204,7 @@ Run `droid config --get tools.coach` to get the merged configuration.
 
 - Identify alternative approaches the human might not have considered
 - Use Socratic prompting to guide discovery
+- Question density follows `coaching_intensity`: `light` → 1–2 sharp challenges; `moderate` → 2–3 challenges; `deep` → thorough exploration
 - Ask questions like:
   - "What if I told you there's a potential issue here? Can you find it?"
   - "I can think of another way to implement this. What might it be?"

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

@@ -1,6 +1,6 @@
 {
   "name": "droid-code-review",
-  "version": "0.2.3",
+  "version": "0.2.4",
   "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: 0.2.3
+version: 0.2.4
 status: alpha
 
 includes:

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

@@ -18,6 +18,12 @@ Code-review has no configuration of its own. Optional integration with other too
 
 **Overrides:** This skill supports user-defined overrides. See `/droid` skill § Skill Overrides.
 
+## Custom Instructions
+
+Any command accepts a ` -- {instruction}` suffix. Split on the **first** ` -- ` (space-dash-dash-space): left is the command and its args, right is additional context or instruction to carry through the entire execution.
+
+Example: `/code-review #123 -- pay close attention to SQL injection risks`
+
 ## 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": "0.3.0",
+  "version": "0.3.1",
   "description": "Shared organizational knowledge - PRDs, tech designs, domains, proposals, patterns, and explored topics. Self-describing: structure and workflows defined in codex repo. 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. Self-describing: structure and workflows defined in codex repo. Use when loading project context, searching codex, capturing decisions, or creating new entries."
-version: 0.3.0
+version: 0.3.1
 status: beta
 
 includes:

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

@@ -86,6 +86,12 @@ If prerequisites fail, guide user to fix:
 
 **Overrides:** This skill supports user-defined overrides. See `/droid` skill § Skill Overrides.
 
+## Custom Instructions
+
+Any command accepts a ` -- {instruction}` suffix. Split on the **first** ` -- ` (space-dash-dash-space): left is the command and its args, right is additional context or instruction to carry through the entire execution.
+
+Example: `/codex search webhook -- focus on the retry logic patterns`
+
 ## Commands
 
 All codex operations follow workflows defined in the codex repo's `.codex/workflows/` folder.

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

@@ -1,6 +1,6 @@
 {
   "name": "droid-comments",
-  "version": "0.3.5",
+  "version": "0.3.6",
   "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: 0.3.5
+version: 0.3.6
 status: beta
 
 includes: