alekspetrov/navigator/nav-features

PLUGIN_DIR="${CLAUDE_PLUGIN_ROOT:-$(cat "${NAVIGATOR_CONFIG_HOME:-${XDG_CONFIG_HOME:-$HOME/.config}/navigator}/plugin-root" 2>/dev/null)}"
[ -d "$PLUGIN_DIR/skills" ] || PLUGIN_DIR="$HOME/.claude/plugins/marketplaces/navigator-marketplace"
python3 "$PLUGIN_DIR/skills/nav-features/functions/feature_manager.py" show

v<version> Features:
 
┌─────────────────────────┬────────┬───────────────────────────────────────────────┐
│ Feature                 │ Status │ Description                                   │
├─────────────────────────┼────────┼───────────────────────────────────────────────┤
│ task_mode               │ [x]    │ Auto-detects task complexity, defers to sk... │
│ tom_features            │ [x]    │ Verification checkpoints, user profile, di... │
│ loop_mode               │ [ ]    │ Autonomous loop execution (enable when nee... │
│ simplification          │ [x]    │ Post-implementation code cleanup with Opus    │
│ auto_update             │ [x]    │ Update notice on session start                │
│ knowledge_graph         │ [x]    │ Unified project knowledge + experiential m... │
│ compact_hook            │ [x]    │ Injects rich summary into compacted sessions  │
│ workflow_enforcer_hook  │ [x]    │ Enforces WORKFLOW CHECK block before task ... │
│ read_guard_hook         │ [x]    │ Warns on excessive Reads (push to agents)     │
│ workflow_state_hook     │ [x]    │ Tracks current task/phase across the session  │
│ task_graph_sync_hook    │ [x]    │ Auto-syncs task files into the knowledge g... │
│ profile_sync_hook       │ [x]    │ Auto-captures preferences/corrections into... │
│ dispatcher              │ [x]    │ Single hook dispatcher runtime (nav_dispat... │
│ tier1                   │ [ ]    │ Zero-token answers for whitelisted prompts    │
│ stop_completion         │ [ ]    │ Completion gate on Stop (decision:block)      │
│ reject_log              │ [x]    │ One JSONL line per refusal (.agent/.nav-re... │
│ jit_memory              │ [ ]    │ Injects relevant memories after tool use      │
│ subagent_context        │ [ ]    │ Injects project context into subagents (2k)   │
│ failure_diagnosis       │ [ ]    │ Surfaces graph pitfalls on tool failures      │
│ judge                   │ [ ]    │ Jev judgments overlay the prompt scorers      │
│ adhd_mode               │ [ ]    │ Per-person reply shaping (one next action,... │
│ ste_mode                │ [ ]    │ STE sentence rules, personal switch           │
│ config_guard            │ [x]    │ Warns when .nav-config.json edits break JSON  │
│ setup_hook              │ [x]    │ One-line runtime status on the Setup event    │
└─────────────────────────┴────────┴───────────────────────────────────────────────┘
 
All v<version> features configured.

PLUGIN_DIR="${CLAUDE_PLUGIN_ROOT:-$(cat "${NAVIGATOR_CONFIG_HOME:-${XDG_CONFIG_HOME:-$HOME/.config}/navigator}/plugin-root" 2>/dev/null)}"
[ -d "$PLUGIN_DIR/skills" ] || PLUGIN_DIR="$HOME/.claude/plugins/marketplaces/navigator-marketplace"
# Enable a feature
python3 "$PLUGIN_DIR/skills/nav-features/functions/feature_manager.py" enable task_mode
 
# Disable a feature
python3 "$PLUGIN_DIR/skills/nav-features/functions/feature_manager.py" disable loop_mode
 
# Personal toggle (team repo): write to .agent/.nav-config.local.json, not the shared file
python3 "$PLUGIN_DIR/skills/nav-features/functions/feature_manager.py" disable judge --local

Task Mode (v5.6.0)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Auto-detects task complexity and routes appropriately:
- Simple tasks → Direct execution
- Skill matches → Defers to skill workflow
- Substantial → Task Mode phases (RESEARCH→COMPLETE)
 
Config: task_mode.enabled, complexity_threshold (0.5)

Theory of Mind (v5.0.0)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Human-AI collaboration improvements:
- Verification checkpoints for high-stakes skills
- User profile (nav-profile) - remembers preferences
- Quality detection (nav-diagnose) - catches drift
 
Config: tom_features.verification_checkpoints, profile_enabled

Loop Mode (v5.1.0)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
"Run until done" capability:
- Structured completion signals (NAVIGATOR_STATUS)
- Dual-condition exit (heuristics + EXIT_SIGNAL)
- Stagnation detection prevents infinite loops
 
Trigger: "run until done", "loop mode"
Config: loop_mode.enabled, max_iterations (5)

Code Simplification (v5.4.0)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Automatic code clarity improvements:
- Runs post-implementation, before commit
- Clarity over brevity, functionality preserved
- Uses Opus model for best results
 
Trigger: "simplify this code"
Config: simplification.enabled, trigger, scope

Auto-Update (v5.5.0)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Read-only update notice on session start (v8: Navigator never updates itself from a hook):
- Compares the running version with the latest GitHub release, at most every
  `check_interval_hours`, never under Pilot
- Shows `claude plugin update navigator@navigator-marketplace` when one is newer
- "Start my Navigator session" applies it (nav-start Step 1.5); restart Claude Code after
- Never blocks session start; disabled means no check and no notice
- Under `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` the engine refuses the fetch; opt in with
  `curl_fallback: true` to repeat the same GET through curl (ships off)
 
Config: auto_update.enabled, check_interval_hours (1), curl_fallback (false)

# Show all features
python3 feature_manager.py show
 
# Show for first session (includes welcome message)
python3 feature_manager.py show --first-session
 
# Enable a feature
python3 feature_manager.py enable task_mode
 
# Disable a feature
python3 feature_manager.py disable loop_mode
 
# Disable only for this contributor (.agent/.nav-config.local.json, gitignored)
python3 feature_manager.py disable judge --local
 
# Get feature details
python3 feature_manager.py info task_mode

❌ .nav-config.json not found
 
Run "Initialize Navigator in this project" first.