rohitg00 · rohitg00 · Feb 5, 2026 · Feb 5, 2026
diff --git a/README.md b/README.md
@@ -5,16 +5,21 @@
 
 Battle-tested Claude Code workflows from power users. Self-correcting memory, parallel worktrees, wrap-up rituals, and the 80/20 AI coding ratio.
 
-**v1.0.0: Now with persistent SQLite storage and searchable learnings!**
+**v1.1.0: Agent teams, custom subagents, adaptive thinking, smart commit, and session insights!**
 
 **If this helps your workflow, please give it a star!**
 
-## What's New in v1.0.0
+## What's New in v1.1.0
 
+- **`/commit`**: Smart commit with quality gates, code review, and learning capture
+- **`/insights`**: Session analytics, learning patterns, correction trends, and productivity metrics
+- **Agent Teams**: Coordinate multiple Claude Code sessions with shared task lists and inter-agent messaging
+- **Custom Subagents**: Create project or user-level subagents with custom tools, memory, and hooks
+- **Adaptive Thinking**: Opus 4.6 calibrates reasoning depth per task automatically
+- **Context Compaction**: Keep long-running agents alive with auto-compaction and PreCompact hooks
+- **Updated Model Selection**: Haiku 4.5, Sonnet 4.5, Opus 4.6 model recommendations
 - **Persistent Storage**: Learnings survive reboots in `~/.pro-workflow/data.db`
 - **Full-Text Search**: Find past learnings instantly with BM25-powered FTS5
-- **Session Analytics**: Track edits, corrections, and prompts per session
-- **New Commands**: `/learn`, `/search`, `/list` for database operations
 
 ## The Core Idea
 
@@ -109,6 +114,8 @@ After plugin install, commands are namespaced:
 | `/pro-workflow:learn` | **NEW** Claude Code best practices & save learnings |
 | `/pro-workflow:search` | **NEW** Search learnings by keyword |
 | `/pro-workflow:list` | **NEW** List all stored learnings |
+| `/pro-workflow:commit` | **NEW** Smart commit with quality gates and code review |
+| `/pro-workflow:insights` | **NEW** Session analytics and learning patterns |
 
 ## Database Features
 
@@ -179,6 +186,22 @@ cp -r /tmp/pw/commands/* ~/.claude/commands/
 | planner | Break down complex tasks |
 | reviewer | Code review, security audit |
 
+### Agent Teams (Experimental)
+
+Coordinate multiple Claude Code sessions working together:
+
+```bash
+# Enable in settings.json
+{ "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" } }
+```
+
+- Lead session coordinates, teammates work independently
+- Teammates message each other directly
+- Shared task list with dependency management
+- Display modes: in-process (`Shift+Up/Down`) or split panes (tmux/iTerm2)
+- Delegate mode (`Shift+Tab`): lead orchestrates only
+- Docs: https://code.claude.com/docs/agent-teams
+
 ## Structure
 
 ```
@@ -203,12 +226,14 @@ pro-workflow/
 │   ├── planner.md            # Planner agent
 │   └── reviewer.md           # Reviewer agent
 ├── commands/
-│   ├── wrap-up.md # Wrap-up command
-│   ├── learn-rule.md # Learn rule command
-│   ├── parallel.md # Parallel command
+│   ├── wrap-up.md
+│   ├── learn-rule.md
+│   ├── parallel.md
 │   ├── learn.md
-│   ├── search.md # Search command
-│   └── list.md # List command
+│   ├── search.md
+│   ├── list.md
+│   ├── commit.md
+│   └── insights.md
 ├── hooks/
 │   └── hooks.json # Hooks file
 ├── scripts/                  # Hook scripts

diff --git a/commands/commit.md b/commands/commit.md
@@ -0,0 +1,119 @@
+# /commit - Smart Commit with Quality Gates
+
+Create a well-crafted commit after running pro-workflow quality checks.
+
+## Process
+
+### 1. Pre-Commit Checks
+
+```bash
+git status
+git diff --stat
+```
+
+- Any unstaged changes to include?
+- Any files that shouldn't be committed (.env, credentials, large binaries)?
+
+### 2. Quality Gates
+
+```bash
+npm run lint 2>&1 | tail -5
+npm run typecheck 2>&1 | tail -5
+npm test -- --changed --passWithNoTests 2>&1 | tail -10
+```
+
+- All checks passing? If not, fix before committing.
+- Skip only if user explicitly says to.
+
+### 3. Code Review
+
+Scan staged changes for:
+- `console.log` / `debugger` statements
+- TODO/FIXME/HACK comments without tickets
+- Hardcoded secrets or API keys
+- Leftover test-only code
+
+Flag any issues before proceeding.
+
+### 4. Commit Message
+
+Draft a commit message based on the staged diff:
+
+```
+<type>(<scope>): <short summary>
+
+<body - what changed and why>
+```
+
+**Types:** feat, fix, refactor, test, docs, chore, perf, ci, style
+
+**Rules:**
+- Summary under 72 characters
+- Body explains *why*, not *what*
+- Reference issue numbers when applicable
+- No generic messages ("fix bug", "update code")
+
+### 5. Stage and Commit
+
+```bash
+git add <specific files>
+git commit -m "<message>"
+```
+
+- Stage specific files, not `git add -A`
+- Show the commit hash and summary after
+
+### 6. Learning Check
+
+After committing, ask:
+- Any learnings from this change to capture?
+- Any patterns worth adding to LEARNED?
+
+## Usage
+
+```
+/commit
+/commit --no-verify
+/commit --amend
+```
+
+## Options
+
+- **--no-verify**: Skip quality gates (use sparingly)
+- **--amend**: Amend the previous commit instead of creating new
+- **--push**: Push to remote after commit
+
+## Example Flow
+
+```
+> /commit
+
+Pre-commit checks:
+  Lint: PASS
+  Types: PASS
+  Tests: 12/12 PASS
+
+Staged changes:
+  src/auth/login.ts (+45 -12)
+  src/auth/session.ts (+8 -3)
+
+Suggested commit:
+  feat(auth): add rate limiting to login endpoint
+
+  Limit login attempts to 5 per IP per 15 minutes using
+  Redis-backed sliding window. Returns 429 with Retry-After
+  header when exceeded.
+
+  Closes #142
+
+Commit? (y/n)
+```
+
+## Related Commands
+
+- `/wrap-up` - Full end-of-session checklist
+- `/learn-rule` - Capture a learning after committing
+
+---
+
+**Trigger:** Use when user says "commit", "save changes", "commit this", or is ready to commit after making changes.
diff --git a/commands/insights.md b/commands/insights.md
@@ -0,0 +1,115 @@
+# /insights - Session & Learning Analytics
+
+Surface patterns from your pro-workflow learnings and session history.
+
+## Usage
+
+```
+/insights
+/insights session
+/insights learnings
+/insights corrections
+```
+
+## What It Shows
+
+### Session Summary
+
+Current session stats:
+```
+Session Insights
+  Duration: 47 min
+  Edits: 23 files modified
+  Corrections: 2 self-corrections applied
+  Learnings: 3 new patterns captured
+  Context: 62% used (safe)
+```
+
+### Learning Analytics
+
+Query the learnings database for patterns:
+```
+Learning Insights (42 total)
+
+Top categories:
+  Testing     12 learnings (29%)
+  Navigation   8 learnings (19%)
+  Git          7 learnings (17%)
+  Quality      6 learnings (14%)
+  Editing      5 learnings (12%)
+  Other        4 learnings (10%)
+
+Most applied:
+  #12 [Testing] Run tests before commit — 15 times
+  #8  [Navigation] Confirm path for common names — 11 times
+  #23 [Git] Use feature branches always — 9 times
+
+Recent learnings (last 7 days):
+  #42 [Claude-Code] Compact at task boundaries
+  #41 [Prompting] Include acceptance criteria
+  #40 [Architecture] Plan before multi-file edits
+
+Stale learnings (never applied):
+  #15 [Editing] Prefer named exports — 0 times (45 days old)
+  #19 [Context] Ask before large refactors — 0 times (30 days old)
+```
+
+### Correction Patterns
+
+Show what types of mistakes are recurring:
+```
+Correction Patterns
+
+Most corrected areas:
+  File navigation    5 corrections
+  Test coverage      3 corrections
+  Commit messages    2 corrections
+
+Trend: Navigation errors decreasing (5 → 2 per week)
+Trend: Testing corrections stable (1 per week)
+
+Suggestions:
+  - Add path confirmation rule to CLAUDE.md (3+ corrections)
+  - Consider /learn-rule for test patterns
+```
+
+### Productivity Metrics
+
+```
+Productivity (last 10 sessions)
+
+  Avg session: 35 min
+  Avg edits/session: 18
+  Correction rate: 12% (improving)
+  Learning capture: 2.1 per session
+
+  Best session: 2026-02-01 (28 edits, 0 corrections)
+  Most productive hour: 10-11am
+```
+
+## Options
+
+- **session**: Current session stats only
+- **learnings**: Learning database analytics
+- **corrections**: Correction pattern analysis
+- **all**: Full report (default)
+- **--export**: Output as markdown file
+
+## How It Works
+
+1. Reads learnings from `~/.pro-workflow/data.db`
+2. Reads session history from the sessions table
+3. Aggregates categories, application counts, and trends
+4. Identifies stale learnings that may need cleanup
+5. Surfaces correction patterns to suggest new rules
+
+## Related Commands
+
+- `/list` - Browse all learnings
+- `/search <query>` - Find specific learnings
+- `/learn-rule` - Capture a new learning
+- `/wrap-up` - End-of-session with learning capture
+
+---
+
+**Trigger:** Use when user asks "show stats", "how am I doing", "what patterns", "analytics", "insights", or wants to understand their learning trajectory.
diff --git a/commands/learn.md b/commands/learn.md
@@ -38,14 +38,19 @@ Learn Claude Code best practices and capture lessons into persistent memory.
 ### CLI Shortcuts
 | Shortcut | Action |
 |----------|--------|
-| `Shift+Tab` | Cycle modes |
+| `Shift+Tab` | Cycle modes (Normal/Auto-Accept/Plan/Delegate) |
 | `Ctrl+L` | Clear screen |
 | `Ctrl+C` | Cancel generation |
 | `Ctrl+B` | Run task in background |
+| `Ctrl+T` | Toggle task list (agent teams) |
+| `Shift+Up/Down` | Navigate teammates (agent teams) |
 | `Up/Down` | Prompt history |
 | `/compact` | Compact context |
 | `/context` | Check context usage |
 | `/clear` | Clear conversation |
+| `/agents` | Manage subagents |
+| `/commit` | Smart commit with quality gates |
+| `/insights` | Session analytics and patterns |
 - **Docs:** https://code.claude.com/docs/cli-reference
 
 ### Prompting
@@ -76,13 +81,42 @@ Subagents run in separate context windows for parallel work.
 - Use for: parallel exploration, background tasks, independent research.
 - Avoid for: single-file reads, tasks needing conversation context.
 - Press `Ctrl+B` to send tasks to background.
+- Create custom subagents in `.claude/agents/` (project) or `~/.claude/agents/` (user).
+- Subagents support: custom tools, permission modes, persistent memory, hooks, and skill preloading.
+- Built-in subagents: Explore (fast read-only), Plan (research), general-purpose (multi-step).
+- Use `/agents` to manage subagents interactively.
 - **Docs:** https://code.claude.com/docs/sub-agents
 - **Pattern:** Parallel Worktrees (Pattern 2)
 
+### Agent Teams (Experimental)
+Coordinate multiple Claude Code instances working together as a team.
+- Enable: set `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` in settings.json or environment.
+- One lead session coordinates, teammates work independently with their own context windows.
+- Teammates can message each other directly (unlike subagents which only report back).
+- Shared task list with self-coordination and dependency management.
+- Display modes: in-process (Shift+Up/Down to navigate) or split panes (tmux/iTerm2).
+- Delegate mode (Shift+Tab): restricts lead to coordination only.
+- Best for: parallel code review, competing hypotheses debugging, cross-layer changes, research.
+- Avoid for: sequential tasks, same-file edits, simple operations.
+- **Docs:** https://code.claude.com/docs/agent-teams
+
+### Adaptive Thinking
+Claude calibrates reasoning depth to each task automatically.
+- Lightweight tasks get quick responses, complex tasks get deep analysis.
+- No configuration needed - works out of the box with Opus 4.6.
+
+### Context Compaction
+Keeps long-running agents from hitting context limits.
+- Auto-compacts at ~95% capacity (configurable via `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE`).
+- Compact manually at task boundaries with `/compact`.
+- Custom subagents support auto-compaction independently.
+- Use PreCompact hooks to save state before compaction.
+
 ### Hooks
 Hooks run scripts on events to automate quality enforcement.
-- Types: PreToolUse, PostToolUse, SessionStart, SessionEnd, Stop, UserPromptSubmit
+- Types: PreToolUse, PostToolUse, SessionStart, SessionEnd, Stop, UserPromptSubmit, PreCompact, SubagentStart, SubagentStop
 - Pro-Workflow ships hooks for edit tracking, quality gates, and learning capture.
+- Subagent hooks: define in frontmatter or settings.json for lifecycle events.
 - **Docs:** https://code.claude.com/docs/hooks
 
 ### Security