shipwright-cli 2.0.0 → 2.1.0

package/README.md

@@ -6,14 +6,14 @@
 
 <p align="center">
   <strong>The Autonomous Delivery Platform</strong><br>
-  From labeled GitHub issue to merged PR — zero human intervention.
+  From labeled GitHub issue to merged PR — with 18 new autonomous agents orchestrating every step.
 </p>
 
 <p align="center">
   <a href="https://github.com/sethdford/shipwright/actions/workflows/test.yml"><img src="https://github.com/sethdford/shipwright/actions/workflows/test.yml/badge.svg" alt="Tests"></a>
   <a href="https://github.com/sethdford/shipwright/actions/workflows/shipwright-pipeline.yml"><img src="https://github.com/sethdford/shipwright/actions/workflows/shipwright-pipeline.yml/badge.svg" alt="Pipeline"></a>
-  <img src="https://img.shields.io/badge/tests-450%2B_passing-4ade80?style=flat-square" alt="450+ tests">
-  <img src="https://img.shields.io/badge/version-1.12.0-00d4ff?style=flat-square" alt="v1.12.0">
+  <img src="https://img.shields.io/badge/tests-500%2B_passing-4ade80?style=flat-square" alt="500+ tests">
+  <img src="https://img.shields.io/badge/version-2.1.0-00d4ff?style=flat-square" alt="v2.1.0">
   <img src="https://img.shields.io/badge/license-MIT-green?style=flat-square" alt="MIT License">
   <img src="https://img.shields.io/badge/bash-3.2%2B-7c3aed?style=flat-square" alt="Bash 3.2+">
 </p>
@@ -28,17 +28,19 @@ This repo uses Shipwright to process its own issues. Label a GitHub issue with `
 
 ---
 
-## What's New
+## What's New in v2.1.0
 
-**v1.13.0** brings faster feedback loops and lower operational overhead:
+**tmux visual overhaul** — role-colored borders, pipeline status widgets, and active pane depth:
 
-- **Webhook receiver** — Zero-latency issue processing (no more polling)
-- **PR lifecycle automation** — Auto-review, merge, cleanup reduces manual toil
-- **Fleet auto-discovery** — Populate fleet config from GitHub org in one command
-- **SQLite persistence** — ACID-safe state, crash recovery, transactional safety
-- **Issue decomposition** — AI-split complex features into manageable subtasks
-- **systemd support** — Cross-platform process supervision (Linux + macOS)
-- **Context engine** — Rich context injection for smarter pipeline decisions
+- **Role-Colored Pane Borders** — Border color reflects agent role (builder=blue, reviewer=orange, tester=yellow)
+- **Pipeline Stage Badge** — Live `⚙ BUILD` / `⚡ TEST` / `↑ PR` widget in status bar with stage-colored badges
+- **Active Pane Lift** — Subtle background depth effect between active and inactive panes
+- **Agent Count Widget** — `λN` heartbeat-based agent counter in status bar
+- **`shipwright init --repair`** — Force clean reinstall after OS upgrades
+- **Color Palette Overhaul** — Warm grays replace harsh near-white text across all tmux chrome
+- **7 tmux Bug Fixes** — Pane indexing, capture bindings, reload, clipboard, and more
+
+**v2.0.0 highlights**: 18 autonomous agents, 100+ CLI commands, intelligence layer, multi-repo fleet, local mode
 
 ---
 
@@ -115,23 +117,65 @@ shipwright doctor
 # One-command setup
 shipwright init
 
+# See what's running
+shipwright status
+
 # Process a GitHub issue end-to-end
 shipwright pipeline start --issue 42
 
-# Watch GitHub and build autonomously 24/7
+# Run daemon 24/7 with agent orchestration
 shipwright daemon start --detach
 
-# Spin up a 3-agent team for manual work
+# See live agent activity
+shipwright activity
+
+# Spin up agent team for manual work
 shipwright session my-feature -t feature-dev
 
+# View DORA metrics and pipeline vitals
+shipwright dora
+
 # Continuous build loop with test validation
 shipwright loop "Build auth module" --test-cmd "npm test"
+
+# Multi-repo operations
+shipwright fleet start
+shipwright fix "upgrade deps" --repos ~/a,~/b,~/c
+
+# Release automation
+shipwright release --version 2.1.0
+shipwright changelog generate
 ```
 
 ---
 
 ## Features
 
+### 18 Autonomous Agents
+
+Wave 1 (Organizational):
+
+- **Swarm Manager** — Orchestrates dynamic agent teams with specialization roles
+- **Autonomous PM** — Team leadership, task scheduling, roadmap execution
+- **Knowledge Guild** — Cross-team learning, pattern capture, mentorship
+- **Recruitment System** — Talent acquisition and team composition
+- **Standup Automaton** — Daily standups, progress tracking, blocker detection
+
+Wave 2 (Operational Backbone):
+
+- **Quality Oversight** — Intelligent audits, zero-defect gates, completeness verification
+- **Strategic Agent** — Long-term planning, goal decomposition, roadmap intelligence
+- **Code Reviewer** — Architecture analysis, clean code standards, best practices
+- **Security Auditor** — Vulnerability detection, threat modeling, compliance
+- **Test Generator** — Coverage analysis, scenario discovery, regression prevention
+- **Incident Commander** — Autonomous triage, root cause analysis, resolution
+- **Dependency Manager** — Semantic versioning, update orchestration, compatibility checking
+- **Release Manager** — Release planning, changelog generation, deployment orchestration
+- **Adaptive Tuner** — DORA metrics analysis, self-optimization, performance tuning
+- **Strategic Intelligence** — Predictive analysis, trend detection, proactive recommendations
+
+Plus 10+ specialized agents for observability, UX, documentation, and more.
+
 ### 12-Stage Delivery Pipeline
 
 ```
@@ -286,47 +330,52 @@ Rich context injection for pipeline stages. Pulls together: contributor history,
 
 ## Commands
 
-| Command                                   | Purpose                            |
-| ----------------------------------------- | ---------------------------------- |
-| `shipwright init`                         | One-command tmux setup             |
-| `shipwright setup`                        | Guided setup wizard                |
-| `shipwright pipeline start --issue N`     | Full delivery pipeline for issue   |
-| `shipwright pipeline start --goal "..."`  | Pipeline from goal description     |
-| `shipwright pipeline resume`              | Resume from last checkpoint        |
-| `shipwright daemon start`                 | Watch GitHub for labeled issues    |
-| `shipwright daemon start --detach`        | Background daemon in tmux          |
-| `shipwright daemon metrics`               | DORA/DX metrics dashboard          |
-| `shipwright fleet start`                  | Multi-repo daemon orchestration    |
-| `shipwright fix "goal" --repos ~/a,~/b`   | Apply same fix across repos        |
-| `shipwright loop "goal" --test-cmd "..."` | Continuous autonomous loop         |
-| `shipwright session name -t template`     | Create team session with agents    |
-| `shipwright memory show`                  | View persistent memory             |
-| `shipwright cost show`                    | Token usage and spending           |
-| `shipwright cost budget set 50`           | Set daily budget limit             |
-| `shipwright prep`                         | Analyze repo, generate configs     |
-| `shipwright doctor`                       | Validate setup, diagnose issues    |
-| `shipwright status`                       | Team dashboard                     |
-| `shipwright ps`                           | Running agent processes            |
-| `shipwright logs team --follow`           | Tail agent logs                    |
-| `shipwright github context`               | Show repo GitHub context           |
-| `shipwright github security`              | CodeQL + Dependabot alerts         |
-| `shipwright checks list`                  | GitHub Check runs                  |
-| `shipwright deploys list`                 | Deployment history                 |
-| `shipwright intelligence`                 | Run intelligence analysis          |
-| `shipwright predict`                      | Risk assessment                    |
-| `shipwright optimize`                     | Self-optimization pass             |
-| `shipwright dashboard`                    | Start web dashboard                |
-| `shipwright webhook listen`               | Receive GitHub webhook events      |
-| `shipwright webhook register`             | Register webhook in GitHub repo    |
-| `shipwright pr auto-review`               | Auto-review PRs by risk + coverage |
-| `shipwright pr merge`                     | Intelligent PR auto-merge          |
-| `shipwright pr cleanup`                   | Clean up stale branches            |
-| `shipwright fleet discover --org <org>`   | Auto-discover repos in GitHub org  |
-| `shipwright decompose --issue N`          | Split complex issue into subtasks  |
-| `shipwright context gather`               | Assemble rich context for stages   |
-| `shipwright db <cmd>`                     | SQLite persistence management      |
-| `shipwright cleanup --force`              | Kill orphaned sessions             |
-| `shipwright upgrade --apply`              | Pull latest updates                |
+Over 100 commands. Key workflows:
+
+```bash
+# Autonomous delivery
+shipwright pipeline start --issue 42
+shipwright daemon start --detach
+
+# Agent teams
+shipwright swarm list
+shipwright recruit --roles builder,tester
+shipwright standup
+shipwright guild members
+
+# Quality gates
+shipwright code-review
+shipwright security-audit
+shipwright testgen
+shipwright quality check
+
+# Observability
+shipwright vitals
+shipwright dora
+shipwright stream
+shipwright activity
+
+# Multi-repo operations
+shipwright fleet start
+shipwright fix "feat: add auth" --repos ~/a,~/b,~/c
+shipwright fleet-viz
+
+# Release automation
+shipwright release --version 2.1.0
+shipwright changelog generate
+shipwright deploys list
+
+# Setup & maintenance
+shipwright init
+shipwright prep
+shipwright doctor
+shipwright upgrade --apply
+
+# See all commands
+shipwright --help
+```
+
+See `.claude/CLAUDE.md` for the complete 100+ command reference organized by workflow.
 
 ## Pipeline Templates for Teams
 
@@ -362,29 +411,68 @@ shipwright templates list
 
 ## Architecture
 
-48 bash scripts (~51K lines), 24 test suites (450+ tests), plus a Bun TypeScript dashboard server. Bash 3.2 compatible — runs on macOS out of the box.
+95+ bash scripts (~100K lines), 27 test suites (500+ tests), plus a TypeScript dashboard server. Bash 3.2 compatible — runs on macOS and Linux out of the box.
+
+**Core Layers:**
 
 ```
-scripts/
-  sw                          # CLI router
-  sw-pipeline.sh              # 12-stage delivery pipeline
-  sw-daemon.sh                # Autonomous issue watcher
-  sw-loop.sh                  # Continuous build loop
+Pipeline Layer
+  sw-pipeline.sh              # 12-stage delivery orchestration
+  sw-daemon.sh                # Autonomous GitHub issue watcher
+  sw-loop.sh                  # Continuous multi-iteration build loop
+
+Agent Layer (18 agents)
+  sw-swarm.sh                 # Dynamic agent team orchestration
+  sw-pm.sh                    # Autonomous PM coordination
+  sw-recruit.sh               # Agent recruitment system
+  sw-standup.sh               # Daily team standups
+  sw-guild.sh                 # Knowledge guilds
+  sw-oversight.sh             # Quality oversight board
+  sw-strategic.sh             # Strategic intelligence
+  sw-scale.sh                 # Dynamic team scaling
+  ... 10 more agent scripts
+
+Intelligence Layer
   sw-intelligence.sh          # AI analysis engine
   sw-predictive.sh            # Risk scoring + anomaly detection
-  sw-adversarial.sh           # Red-team code review
-  sw-self-optimize.sh         # DORA-driven self-tuning
-  sw-pipeline-composer.sh     # Dynamic pipeline generation
-  sw-github-graphql.sh        # GitHub GraphQL client
-  sw-github-checks.sh         # Native CI check runs
-  sw-github-deploy.sh         # Deployment tracking
+  sw-adaptive.sh              # Data-driven pipeline tuning
+  sw-security-audit.sh        # Security analysis
+  sw-code-review.sh           # Code quality analysis
+  sw-testgen.sh               # Test generation
+  sw-architecture.sh          # Architecture enforcement
+
+Operational Layer
   sw-fleet.sh                 # Multi-repo orchestration
-  sw-memory.sh                # Persistent learning
+  sw-ci.sh                    # CI/CD orchestration
+  sw-webhook.sh               # GitHub webhooks
+  sw-incident.sh              # Incident response
+  sw-release-manager.sh       # Release automation
+  ... 20+ operational scripts
+
+Observability Layer
+  sw-vitals.sh                # Pipeline health scoring
+  sw-dora.sh                  # DORA metrics dashboard
+  sw-activity.sh              # Live activity streams
+  sw-replay.sh                # Pipeline playback
+  sw-trace.sh                 # E2E traceability
+  sw-otel.sh                  # OpenTelemetry integration
+  ... observability services
+
+Infrastructure
+  sw-github-graphql.sh        # GitHub GraphQL API client
+  sw-github-checks.sh         # Native GitHub check runs
+  sw-github-deploy.sh         # Deployment tracking
+  sw-memory.sh                # Persistent learning system
   sw-cost.sh                  # Cost intelligence
-  ...                         # 33 more scripts
-dashboard/
-  server.ts                   # Bun WebSocket dashboard (4300+ lines)
-  public/                     # Dashboard frontend
+  sw-db.sh                    # SQLite persistence
+  sw-eventbus.sh              # Async event bus
+
+Tools & UX
+  dashboard/server.ts         # Real-time dashboard
+  sw-session.sh               # tmux agent sessions
+  sw-status.sh                # Team dashboard
+  sw-docs.sh                  # Documentation sync
+  sw-tmux.sh                  # tmux health management
 ```
 
 ## Contributing

package/completions/_shipwright

@@ -7,6 +7,11 @@
 _shipwright() {
     local -a commands
     commands=(
+        'agent:Agent management (recruit, swarm, standup, guild, oversight)'
+        'quality:Quality & review (code-review, security-audit, testgen, hygiene)'
+        'observe:Observability (vitals, dora, retro, stream, activity, replay)'
+        'release:Release & deploy (release, release-manager, changelog, deploy)'
+        'intel:Intelligence (predict, intelligence, strategic, optimize)'
         'init:Quick tmux setup — one command, no prompts'
         'setup:Guided setup — prerequisites, init, doctor'
         'session:Create a new tmux window for a Claude team'
@@ -39,13 +44,6 @@ _shipwright() {
         'connect:Team connect — sync local state'
         'remote:Remote machines — manage distributed workers'
         'launchd:Process supervision — auto-start on boot'
-        'intelligence:Intelligence engine analysis'
-        'optimize:Self-optimization based on DORA'
-        'predict:Predictive risk assessment'
-        'adversarial:Adversarial Agent Code Review'
-        'simulate:Developer simulation workflow'
-        'architecture:Architecture Model & Enforcer'
-        'vitals:Pipeline vitals — real-time scoring'
         'docs:Documentation keeper — auto-sync docs'
         'tmux:tmux health — doctor, install, fix'
         'github:GitHub context — repo metadata'
@@ -62,7 +60,42 @@ _shipwright() {
     local -a checkpoint_cmds connect_cmds remote_cmds launchd_cmds
     local -a dashboard_cmds github_cmds checks_cmds deploys_cmds docs_cmds
     local -a tmux_cmds decompose_cmds pr_cmds
+    local -a agent_cmds quality_cmds observe_cmds release_cmds intel_cmds
 
+    agent_cmds=(
+        'recruit:Agent recruitment & talent management'
+        'swarm:Dynamic agent swarm management'
+        'standup:Automated daily standups'
+        'guild:Knowledge guilds & cross-team learning'
+        'oversight:Quality oversight board'
+    )
+    quality_cmds=(
+        'code-review:Clean code & architecture analysis'
+        'security-audit:Comprehensive security auditing'
+        'testgen:Autonomous test generation'
+        'hygiene:Repository organization & cleanup'
+    )
+    observe_cmds=(
+        'vitals:Pipeline vitals — real-time scoring'
+        'dora:DORA metrics dashboard'
+        'retro:Sprint retrospective engine'
+        'stream:Live terminal output streaming'
+        'activity:Live agent activity stream'
+        'replay:Pipeline DVR — view past runs'
+        'status:Team status dashboard'
+    )
+    release_cmds=(
+        'release:Release train automation'
+        'release-manager:Autonomous release pipeline'
+        'changelog:Automated release notes'
+        'deploy:Deployments — deployment history'
+    )
+    intel_cmds=(
+        'predict:Predictive risk assessment'
+        'intelligence:Intelligence engine analysis'
+        'strategic:Strategic intelligence agent'
+        'optimize:Self-optimization based on DORA'
+    )
     pipeline_cmds=(
         'start:Start a new pipeline run'
         'resume:Resume from last stage'
@@ -193,6 +226,21 @@ _shipwright() {
             ;;
         args)
             case "${words[1]}" in
+                agent)
+                    _describe -t agent-cmds 'agent command' agent_cmds
+                    ;;
+                quality)
+                    _describe -t quality-cmds 'quality command' quality_cmds
+                    ;;
+                observe)
+                    _describe -t observe-cmds 'observe command' observe_cmds
+                    ;;
+                release)
+                    _describe -t release-cmds 'release command' release_cmds
+                    ;;
+                intel)
+                    _describe -t intel-cmds 'intel command' intel_cmds
+                    ;;
                 pipeline)
                     _describe -t pipeline-cmds 'pipeline command' pipeline_cmds
                     _arguments '*:options:_pipeline_options'
@@ -268,6 +316,8 @@ _shipwright() {
                 loop)
                     _arguments \
                         '1:goal:' \
+                        '--repo[Directory path]:directory:_directories' \
+                        '--local[Local-only mode (no GitHub)]' \
                         '--test-cmd[Test command]:command:' \
                         '--max-iterations[Max iterations]:count:' \
                         '--model[Model to use]:model:(opus sonnet haiku)' \
@@ -312,6 +362,8 @@ _pipeline_options() {
     _arguments \
         '--issue[GitHub issue number]:issue:' \
         '--goal[Goal description]:goal:' \
+        '--repo[Directory path]:directory:_directories' \
+        '--local[Local-only mode (no GitHub)]' \
         '--worktree[Use isolated worktree]' \
         '--template[Pipeline template]:file:_files' \
         '--skip-gates[Auto-proceed all gates]'

package/completions/shipwright.bash

@@ -9,14 +9,34 @@ _shipwright_completions() {
     cur="${COMP_WORDS[COMP_CWORD]}"
     prev="${COMP_WORDS[COMP_CWORD-1]}"
 
-    # Top-level commands
-    local commands="init setup session status ps logs templates doctor cleanup reaper upgrade loop pipeline worktree prep daemon fleet memory cost db fix dashboard jira linear tracker heartbeat checkpoint webhook decompose connect remote launchd intelligence optimize predict adversarial simulate architecture vitals docs tmux github checks deploys pr context help version"
+    # Top-level commands (includes groups and flat commands)
+    local commands="agent quality observe release intel init setup session status ps logs templates doctor cleanup reaper upgrade loop pipeline worktree prep daemon fleet memory cost db fix dashboard jira linear tracker heartbeat checkpoint webhook decompose connect remote launchd intelligence optimize predict adversarial simulate architecture vitals docs tmux github checks deploys pr context help version"
 
     case "$prev" in
         shipwright|sw|cct)
             COMPREPLY=( $(compgen -W "$commands" -- "$cur") )
             return 0
             ;;
+        agent)
+            COMPREPLY=( $(compgen -W "recruit swarm standup guild oversight" -- "$cur") )
+            return 0
+            ;;
+        quality)
+            COMPREPLY=( $(compgen -W "code-review security-audit testgen hygiene" -- "$cur") )
+            return 0
+            ;;
+        observe)
+            COMPREPLY=( $(compgen -W "vitals dora retro stream activity replay status" -- "$cur") )
+            return 0
+            ;;
+        release)
+            COMPREPLY=( $(compgen -W "release release-manager changelog deploy" -- "$cur") )
+            return 0
+            ;;
+        intel)
+            COMPREPLY=( $(compgen -W "predict intelligence strategic optimize" -- "$cur") )
+            return 0
+            ;;
         pipeline)
             COMPREPLY=( $(compgen -W "start resume status test" -- "$cur") )
             return 0
@@ -111,13 +131,13 @@ _shipwright_completions() {
     if [[ "$cur" == -* ]]; then
         case "${COMP_WORDS[1]}" in
             pipeline)
-                COMPREPLY=( $(compgen -W "--issue --goal --worktree --template --skip-gates" -- "$cur") )
+                COMPREPLY=( $(compgen -W "--issue --goal --repo --local --worktree --template --skip-gates --test-cmd --model --agents --base --reviewers --labels --no-github --no-github-label --ci --ignore-budget --dry-run --slack-webhook --self-heal --max-iterations --max-restarts --fast-test-cmd --completed-stages" -- "$cur") )
                 ;;
             prep)
                 COMPREPLY=( $(compgen -W "--check --with-claude --verbose" -- "$cur") )
                 ;;
             loop)
-                COMPREPLY=( $(compgen -W "--test-cmd --max-iterations --model --agents --audit --audit-agent --quality-gates --definition-of-done --resume --skip-permissions" -- "$cur") )
+                COMPREPLY=( $(compgen -W "--repo --local --test-cmd --fast-test-cmd --fast-test-interval --max-iterations --model --agents --roles --worktree --skip-permissions --max-turns --resume --max-restarts --verbose --audit --audit-agent --quality-gates --definition-of-done --no-auto-extend --extension-size --max-extensions" -- "$cur") )
                 ;;
             fix)
                 COMPREPLY=( $(compgen -W "--repos" -- "$cur") )

package/completions/shipwright.fish

@@ -7,8 +7,13 @@
 for cmd in shipwright sw cct
     complete -c $cmd -f
 
-    # Top-level commands
-    set -l all_cmds session status ps logs templates doctor cleanup reaper upgrade loop pipeline worktree prep daemon memory cost init help version
+    # Top-level commands (includes groups and flat commands)
+    set -l all_cmds agent quality observe release intel session status ps logs templates doctor cleanup reaper upgrade loop pipeline worktree prep daemon memory cost init help version
+    complete -c $cmd -n "not __fish_seen_subcommand_from $all_cmds" -a "agent" -d "Agent management (recruit, swarm, standup, guild, oversight)"
+    complete -c $cmd -n "not __fish_seen_subcommand_from $all_cmds" -a "quality" -d "Quality & review (code-review, security-audit, testgen, hygiene)"
+    complete -c $cmd -n "not __fish_seen_subcommand_from $all_cmds" -a "observe" -d "Observability (vitals, dora, retro, stream, activity, replay)"
+    complete -c $cmd -n "not __fish_seen_subcommand_from $all_cmds" -a "release" -d "Release & deploy (release, release-manager, changelog, deploy)"
+    complete -c $cmd -n "not __fish_seen_subcommand_from $all_cmds" -a "intel" -d "Intelligence (predict, intelligence, strategic, optimize)"
     complete -c $cmd -n "not __fish_seen_subcommand_from $all_cmds" -a "session" -d "Create a new tmux window for a Claude team"
     complete -c $cmd -n "not __fish_seen_subcommand_from $all_cmds" -a "status" -d "Show dashboard of running teams and agents"
     complete -c $cmd -n "not __fish_seen_subcommand_from $all_cmds" -a "ps" -d "Show running agent processes and status"
@@ -29,6 +34,40 @@ for cmd in shipwright sw cct
     complete -c $cmd -n "not __fish_seen_subcommand_from $all_cmds" -a "help" -d "Show help message"
     complete -c $cmd -n "not __fish_seen_subcommand_from $all_cmds" -a "version" -d "Show version"
 
+    # agent subcommands
+    complete -c $cmd -n "__fish_seen_subcommand_from agent" -a "recruit" -d "Agent recruitment & talent management"
+    complete -c $cmd -n "__fish_seen_subcommand_from agent" -a "swarm" -d "Dynamic agent swarm management"
+    complete -c $cmd -n "__fish_seen_subcommand_from agent" -a "standup" -d "Automated daily standups"
+    complete -c $cmd -n "__fish_seen_subcommand_from agent" -a "guild" -d "Knowledge guilds & cross-team learning"
+    complete -c $cmd -n "__fish_seen_subcommand_from agent" -a "oversight" -d "Quality oversight board"
+
+    # quality subcommands
+    complete -c $cmd -n "__fish_seen_subcommand_from quality" -a "code-review" -d "Clean code & architecture analysis"
+    complete -c $cmd -n "__fish_seen_subcommand_from quality" -a "security-audit" -d "Comprehensive security auditing"
+    complete -c $cmd -n "__fish_seen_subcommand_from quality" -a "testgen" -d "Autonomous test generation"
+    complete -c $cmd -n "__fish_seen_subcommand_from quality" -a "hygiene" -d "Repository organization & cleanup"
+
+    # observe subcommands
+    complete -c $cmd -n "__fish_seen_subcommand_from observe" -a "vitals" -d "Pipeline vitals — real-time scoring"
+    complete -c $cmd -n "__fish_seen_subcommand_from observe" -a "dora" -d "DORA metrics dashboard"
+    complete -c $cmd -n "__fish_seen_subcommand_from observe" -a "retro" -d "Sprint retrospective engine"
+    complete -c $cmd -n "__fish_seen_subcommand_from observe" -a "stream" -d "Live terminal output streaming"
+    complete -c $cmd -n "__fish_seen_subcommand_from observe" -a "activity" -d "Live agent activity stream"
+    complete -c $cmd -n "__fish_seen_subcommand_from observe" -a "replay" -d "Pipeline DVR — view past runs"
+    complete -c $cmd -n "__fish_seen_subcommand_from observe" -a "status" -d "Team status dashboard"
+
+    # release subcommands
+    complete -c $cmd -n "__fish_seen_subcommand_from release" -a "release" -d "Release train automation"
+    complete -c $cmd -n "__fish_seen_subcommand_from release" -a "release-manager" -d "Autonomous release pipeline"
+    complete -c $cmd -n "__fish_seen_subcommand_from release" -a "changelog" -d "Automated release notes"
+    complete -c $cmd -n "__fish_seen_subcommand_from release" -a "deploy" -d "Deployments — deployment history"
+
+    # intel subcommands
+    complete -c $cmd -n "__fish_seen_subcommand_from intel" -a "predict" -d "Predictive risk assessment"
+    complete -c $cmd -n "__fish_seen_subcommand_from intel" -a "intelligence" -d "Intelligence engine analysis"
+    complete -c $cmd -n "__fish_seen_subcommand_from intel" -a "strategic" -d "Strategic intelligence agent"
+    complete -c $cmd -n "__fish_seen_subcommand_from intel" -a "optimize" -d "Self-optimization based on DORA"
+
     # pipeline subcommands
     complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -a "start" -d "Start a new pipeline run"
     complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -a "resume" -d "Resume from last stage"
@@ -81,16 +120,28 @@ for cmd in shipwright sw cct
     complete -c $cmd -n "__fish_seen_subcommand_from prep" -l verbose -d "Verbose output"
 
     # loop flags
+    complete -c $cmd -n "__fish_seen_subcommand_from loop" -l repo -d "Change to directory before running" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from loop" -l local -d "Local-only mode (no GitHub)"
     complete -c $cmd -n "__fish_seen_subcommand_from loop" -l test-cmd -d "Test command to verify each iteration" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from loop" -l fast-test-cmd -d "Fast/subset test command" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from loop" -l fast-test-interval -d "Run full tests every N iterations" -r
     complete -c $cmd -n "__fish_seen_subcommand_from loop" -l max-iterations -d "Maximum loop iterations" -r
     complete -c $cmd -n "__fish_seen_subcommand_from loop" -l model -d "Claude model to use" -ra "opus sonnet haiku"
     complete -c $cmd -n "__fish_seen_subcommand_from loop" -l agents -d "Number of agents" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from loop" -l roles -d "Role per agent" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from loop" -l worktree -d "Use git worktrees for isolation"
     complete -c $cmd -n "__fish_seen_subcommand_from loop" -l audit -d "Enable self-reflection each iteration"
     complete -c $cmd -n "__fish_seen_subcommand_from loop" -l audit-agent -d "Use separate auditor agent"
     complete -c $cmd -n "__fish_seen_subcommand_from loop" -l quality-gates -d "Enable automated quality checks"
     complete -c $cmd -n "__fish_seen_subcommand_from loop" -l definition-of-done -d "Custom completion checklist" -rF
+    complete -c $cmd -n "__fish_seen_subcommand_from loop" -l no-auto-extend -d "Disable auto-extension"
+    complete -c $cmd -n "__fish_seen_subcommand_from loop" -l extension-size -d "Additional iterations per extension" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from loop" -l max-extensions -d "Max number of auto-extensions" -r
     complete -c $cmd -n "__fish_seen_subcommand_from loop" -l resume -d "Resume interrupted loop"
+    complete -c $cmd -n "__fish_seen_subcommand_from loop" -l max-restarts -d "Max session restarts" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from loop" -l max-turns -d "Max API turns per session" -r
     complete -c $cmd -n "__fish_seen_subcommand_from loop" -l skip-permissions -d "Skip permission prompts"
+    complete -c $cmd -n "__fish_seen_subcommand_from loop" -l verbose -d "Show full Claude output"
 
     # logs flags
     complete -c $cmd -n "__fish_seen_subcommand_from logs" -l follow -d "Tail logs in real time"
@@ -104,4 +155,31 @@ for cmd in shipwright sw cct
 
     # reaper flags
     complete -c $cmd -n "__fish_seen_subcommand_from reaper" -l watch -d "Continuous watch mode"
+
+    # pipeline flags
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l issue -d "GitHub issue number" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l goal -d "Goal description" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l repo -d "Change to directory before running" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l local -d "Local-only mode (no GitHub)"
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l pipeline -d "Pipeline template" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l template -d "Pipeline template" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l test-cmd -d "Test command to run" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l model -d "AI model to use" -ra "opus sonnet haiku"
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l agents -d "Number of agents" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l skip-gates -d "Auto-approve all gates"
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l base -d "Base branch for PR" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l reviewers -d "PR reviewers" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l labels -d "PR labels" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l no-github -d "Disable GitHub integration"
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l no-github-label -d "Don't modify issue labels"
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l ci -d "CI mode (non-interactive)"
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l ignore-budget -d "Skip budget enforcement"
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l worktree -d "Run in isolated worktree"
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l dry-run -d "Show what would happen"
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l slack-webhook -d "Slack webhook URL" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l self-heal -d "Build retry cycles" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l max-iterations -d "Max build loop iterations" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l max-restarts -d "Max session restarts" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l fast-test-cmd -d "Fast/subset test command" -r
+    complete -c $cmd -n "__fish_seen_subcommand_from pipeline" -l completed-stages -d "Skip these stages" -r
 end