claudecode-omc 4.8.2 → 4.8.4

package/docs/PERFORMANCE-MONITORING.md

@@ -9,7 +9,7 @@ Comprehensive guide to monitoring, debugging, and optimizing Claude Code and oh-
 - [Overview](#overview)
 - [Built-in Monitoring](#built-in-monitoring)
   - [Agent Observatory](#agent-observatory)
-  - [Token & Cost Analytics](#token--cost-analytics)
+  - [Session-End Summaries](#session-end-summaries)
   - [Session Replay](#session-replay)
 - [HUD Integration](#hud-integration)
 - [Debugging Techniques](#debugging-techniques)
@@ -29,8 +29,7 @@ oh-my-claudecode provides comprehensive monitoring capabilities for tracking age
 |--------|------|-------------|
 | Agent lifecycle | Agent Observatory | Per-agent |
 | Tool timing | Session Replay | Per-tool call |
-| Token usage | Analytics System | Per-session/agent |
-| API costs | Analytics System | Per-session/daily/monthly |
+| Session-end summary | Session-end hook | Per-session |
 | File ownership | Subagent Tracker | Per-file |
 | Parallel efficiency | Observatory | Real-time |
 
@@ -83,66 +82,42 @@ Agent Observatory (3 active, 85% efficiency)
 | `files:N` | Files being modified |
 | `bottleneck` | Slowest repeated tool operation |
 
-### Token & Cost Analytics
+### Session-End Summaries
 
-OMC automatically tracks token usage and costs across all sessions.
+The legacy analytics workflow described in older docs (`omc-analytics`, `omc cost`, `omc backfill`, and the `analytics` HUD preset) is no longer part of current `dev`.
 
-#### CLI Commands
+The supported monitoring surfaces on current builds are:
 
-```bash
-# View everything (default dashboard)
-omc
-
-# View daily/weekly/monthly cost reports
-omc cost daily
-omc cost weekly
-omc cost monthly
+- **Agent Observatory** in the HUD / API
+- **Session Replay** logs in `.omc/state/agent-replay-*.jsonl`
+- **Session-end summaries** in `.omc/sessions/<sessionId>.json`
+- **Session-end notifications** emitted through configured callbacks
 
-# View session history
-omc sessions
+#### Supported Inspection Commands
 
-# Agent observability is shown in HUD/replay logs
-# (legacy standalone agent-breakdown command was removed)
-
-# Export data
-omc export cost csv ./costs.csv
+```bash
+omc hud
+tail -20 .omc/state/agent-replay-*.jsonl
+ls .omc/sessions/*.json
 ```
 
-#### Real-time HUD Display
+#### HUD Display
 
-Enable the analytics preset for detailed cost tracking in your status line:
+Use a supported preset such as `focused` or `full` for agent and context visibility:
 
 ```json
 {
   "omcHud": {
-    "preset": "analytics"
+    "preset": "focused"
   }
 }
 ```
 
 This shows:
-- Session cost and tokens
-- Cost per hour
-- Cache efficiency (% of tokens from cache)
-- Budget warnings (>$2 warning, >$5 critical)
-
-#### Backfill Historical Data
-
-Analyze historical Claude Code transcripts:
-
-```bash
-# Preview available transcripts
-omc backfill --dry-run
-
-# Backfill all transcripts
-omc backfill
-
-# Backfill specific project
-omc backfill --project "*my-project*"
-
-# Backfill recent only
-omc backfill --from "2026-01-01"
-```
+- Active agents and their status
+- Todos / PRD progress
+- Context and rate-limit state
+- Background tasks
 
 ### Session Replay
 
@@ -355,12 +330,12 @@ Track Claude's performance across standard benchmarks:
 
 ## Best Practices
 
-### 1. Monitor Token Usage Proactively
+### 1. Monitor Session Health Proactively
 
 ```bash
 # Set up budget warnings in HUD
 /oh-my-claudecode:hud
-# Select "analytics" preset
+# Select "focused" or "full"
 ```
 
 ### 2. Use Appropriate Model Tiers
@@ -442,15 +417,15 @@ cleanupReplayFiles(process.cwd()); // Keeps last 10 sessions
 3. Review file_ownership in agent state
 4. Use `swarm` mode with explicit task isolation
 
-### Missing Analytics Data
+### Missing Session-End Summaries
 
-**Symptoms**: Empty cost reports, no session history
+**Symptoms**: No `.omc/sessions/*.json` files after a session finishes
 
 **Solutions**:
-1. Run `omc backfill` to import historical transcripts
-2. Verify HUD is running: `/oh-my-claudecode:hud setup`
-3. Check `.omc/state/` directory exists
-4. Review `token-tracking.jsonl` for raw data
+1. End the session normally so the `session-end` hook runs
+2. Verify HUD / hooks are installed: `/oh-my-claudecode:hud setup`
+3. Check the current workspace `.omc/sessions/` directory
+4. Review `.omc/state/agent-replay-*.jsonl` if you need timing/activity evidence instead
 
 ### Stale Agent State
 
@@ -525,6 +500,6 @@ cleanupReplayFiles(directory: string): number
 
 ## See Also
 
-- [Analytics System](./ANALYTICS-SYSTEM.md) - Detailed token tracking documentation
+- [Analytics System](./ANALYTICS-SYSTEM.md) - Historical note on the removed analytics subsystem and current replacements
 - [Reference](./REFERENCE.md) - Complete feature reference
 - [Architecture](./ARCHITECTURE.md) - System architecture overview

package/docs/REFERENCE.md

@@ -8,10 +8,10 @@ Complete reference for oh-my-claudecode. For quick start, see the main [README.m
 
 - [Installation](#installation)
 - [Configuration](#configuration)
-- [CLI Commands: ask/team](#cli-commands-askteam)
+- [CLI Commands: ask/team/session](#cli-commands-askteamsession)
 - [Legacy MCP Team Runtime Tools (Deprecated)](#legacy-mcp-team-runtime-tools-deprecated)
 - [Agents (28 Total)](#agents-28-total)
-- [Skills (38 Total)](#skills-38-total)
+- [Skills (34 Total)](#skills-34-total)
 - [Slash Commands](#slash-commands)
 - [Hooks System](#hooks-system)
 - [Magic Keywords](#magic-keywords)
@@ -81,7 +81,7 @@ Configure omc for all Claude Code sessions:
 | Feature           | Without     | With omc Config            |
 | ----------------- | ----------- | -------------------------- |
 | Agent delegation  | Manual only | Automatic based on task    |
-| Keyword detection | Disabled    | ultrawork, search, analyze |
+| Keyword detection | Disabled    | ultrawork, search |
 | Todo continuation | Basic       | Enforced completion        |
 | Model routing     | Default     | Smart tier selection       |
 | Skill composition | None        | Auto-combines skills       |
@@ -190,7 +190,7 @@ Tag behavior:
 
 ---
 
-## CLI Commands: ask/team
+## CLI Commands: ask/team/session
 
 ### `omc ask`
 
@@ -218,6 +218,19 @@ omc team api claim-task --input '{"team_name":"auth-review","task_id":"1","worke
 
 Supported entrypoints: direct start (`omc team [N:agent] "<task>"`), `status`, `shutdown`, and `api`.
 
+### `omc session search`
+
+```bash
+omc session search "team leader stale"
+omc session search notify-hook --since 7d
+omc session search provider-routing --project all --json
+```
+
+- Defaults to the current project/worktree scope
+- Use `--project all` to search across all local Claude project transcripts
+- Supports `--limit`, `--session`, `--since`, `--context`, `--case-sensitive`, and `--json`
+- MCP/tool surface: `session_search` returns structured JSON for agents and automations
+
 ---
 
 ## Legacy MCP Team Runtime Tools (Deprecated, Opt-In Only)
@@ -279,7 +292,7 @@ Always use `oh-my-claudecode:` prefix when calling via Task tool.
 | **Pre-Planning** | -                       | -                     | `analyst`           |
 | **Testing**      | -                       | `qa-tester`           | -                   |
 | **Security**     | `security-reviewer-low` | -                     | `security-reviewer` |
-| **Build**        | -                       | `build-fixer`         | -                   |
+| **Build**        | -                       | `debugger`            | -                   |
 | **TDD**          | -                       | `test-engineer`       | -                   |
 | **Code Review**  | -                       | -                     | `code-reviewer`     |
 | **Data Science** | -                       | `scientist`           | `scientist-high`    |
@@ -299,7 +312,7 @@ Always use `oh-my-claudecode:` prefix when calling via Task tool.
 | UI component                 | `designer`                    | sonnet |
 | Complex UI system            | `designer-high`               | opus   |
 | Write docs/comments          | `writer`                      | haiku  |
-| Research docs/APIs           | `document-specialist`         | sonnet |
+| Research docs/APIs           | `document-specialist` (repo docs first; optional Context Hub / `chub`) | sonnet |
 | Analyze images/diagrams      | `vision`                      | sonnet |
 | Strategic planning           | `planner`                     | opus   |
 | Review/critique plan         | `critic`                      | opus   |
@@ -307,8 +320,8 @@ Always use `oh-my-claudecode:` prefix when calling via Task tool.
 | Test CLI interactively       | `qa-tester`                   | sonnet |
 | Security review              | `security-reviewer`           | opus   |
 | Quick security scan          | `security-reviewer-low`       | haiku  |
-| Fix build errors             | `build-fixer`                 | sonnet |
-| Simple build fix             | `build-fixer` (model=haiku)   | haiku  |
+| Fix build errors             | `debugger`                    | sonnet |
+| Simple build fix             | `debugger` (model=haiku)      | haiku  |
 | TDD workflow                 | `test-engineer`               | sonnet |
 | Quick test suggestions       | `test-engineer` (model=haiku) | haiku  |
 | Code review                  | `code-reviewer`               | opus   |
@@ -319,22 +332,21 @@ Always use `oh-my-claudecode:` prefix when calling via Task tool.
 
 ---
 
-## Skills (38 Total)
+## Skills (34 Total)
 
-Includes **37 canonical skills + 1 deprecated alias** (`psm`).
+Includes **33 canonical skills + 1 deprecated alias** (`psm`).
 
 | Skill                     | Description                                                      | Manual Command                              |
 | ------------------------- | ---------------------------------------------------------------- | ------------------------------------------- |
-| `analyze`                 | Deep analysis and investigation                                  | `/oh-my-claudecode:analyze`                 |
 | `ask-codex`               | Ask Codex via `omc ask codex` and store an ask artifact          | `/oh-my-claudecode:ask-codex`               |
+| `ai-slop-cleaner`         | Anti-slop cleanup workflow with optional reviewer-only `--review` pass | `/oh-my-claudecode:ai-slop-cleaner`         |
 | `ask-gemini`              | Ask Gemini via `omc ask gemini` and store an ask artifact        | `/oh-my-claudecode:ask-gemini`              |
 | `autopilot`               | Full autonomous execution from idea to working code              | `/oh-my-claudecode:autopilot`               |
-| `build-fix`               | Fix build and TypeScript errors                                  | `/oh-my-claudecode:build-fix`               |
 | `cancel`                  | Unified cancellation for active modes                            | `/oh-my-claudecode:cancel`                  |
 | `ccg`                     | Tri-model workflow via `ask-codex` + `ask-gemini`, then Claude synthesis | `/oh-my-claudecode:ccg`                     |
-| `code-review`             | Comprehensive code review                                        | `/oh-my-claudecode:code-review`             |
 | `configure-notifications` | Configure notifications (Discord/Telegram/Slack/OpenClaw)        | `/oh-my-claudecode:configure-notifications` |
-| `configure-openclaw`      | Configure OpenClaw notification bridge                           | `/oh-my-claudecode:configure-openclaw`      |
+| `configure-openclaw`      | Configure OpenClaw gateway (deprecated, use configure-notifications) | `/oh-my-claudecode:configure-openclaw`      |
+| _OpenClaw routing_        | Normalized native/HTTP routing contract for clawhip consumers    | [`docs/OPENCLAW-ROUTING.md`](./OPENCLAW-ROUTING.md) |
 | `deep-interview`          | Socratic deep interview with ambiguity gating                    | `/oh-my-claudecode:deep-interview`          |
 | `deepinit`                | Generate hierarchical AGENTS.md docs                             | `/oh-my-claudecode:deepinit`                |
 | `external-context`        | Parallel document-specialist research                            | `/oh-my-claudecode:external-context`        |
@@ -346,7 +358,6 @@ Includes **37 canonical skills + 1 deprecated alias** (`psm`).
 | `omc-doctor`              | Diagnose and fix installation issues                             | `/oh-my-claudecode:omc-doctor`              |
 | `omc-help`                | Show OMC usage guide                                             | `/oh-my-claudecode:omc-help`                |
 | `omc-plan`                | Planning workflow (`/plan` safe alias)                           | `/oh-my-claudecode:omc-plan`                |
-| `omc-security-review`     | Security review workflow (`/security-review` safe alias)         | `/oh-my-claudecode:omc-security-review`     |
 | `omc-setup`               | One-time setup wizard                                            | `/oh-my-claudecode:omc-setup`               |
 | `omc-teams`               | Legacy compatibility wrapper for `omc team` CLI                  | `/oh-my-claudecode:omc-teams`               |
 | `project-session-manager` | Manage isolated dev environments (git worktrees + tmux)          | `/oh-my-claudecode:project-session-manager` |
@@ -355,9 +366,9 @@ Includes **37 canonical skills + 1 deprecated alias** (`psm`).
 | `ralph-init`              | Initialize PRD for structured ralph execution                    | `/oh-my-claudecode:ralph-init`              |
 | `ralplan`                 | Consensus planning alias for `/omc-plan --consensus`             | `/oh-my-claudecode:ralplan`                 |
 | `release`                 | Automated release workflow                                       | `/oh-my-claudecode:release`                 |
+| `setup`                   | Unified setup entrypoint for install, diagnostics, and MCP configuration | `/oh-my-claudecode:setup`              |
 | `sciomc`                  | Parallel scientist orchestration                                 | `/oh-my-claudecode:sciomc`                  |
 | `skill`                   | Manage local skills (list/add/remove/search/edit)                | `/oh-my-claudecode:skill`                   |
-| `tdd`                     | Test-first workflow enforcement                                  | `/oh-my-claudecode:tdd`                     |
 | `team`                    | Coordinated multi-agent workflow                                 | `/oh-my-claudecode:team`                    |
 | `trace`                   | Show orchestration trace timeline                                | `/oh-my-claudecode:trace`                   |
 | `ultraqa`                 | QA cycle until goal is met                                       | `/oh-my-claudecode:ultraqa`                 |
@@ -370,26 +381,26 @@ Includes **37 canonical skills + 1 deprecated alias** (`psm`).
 
 ## Slash Commands
 
-All skills are available as slash commands with the prefix `/oh-my-claudecode:`.
+All installed skills are available as slash commands with the prefix `/oh-my-claudecode:`. Compatibility keyword modes like `deep-analyze` and `tdd` are prompt-triggered behaviors, not standalone slash commands.
 
 | Command                                     | Description                                                                                   |
 | ------------------------------------------- | --------------------------------------------------------------------------------------------- |
+| `/oh-my-claudecode:ai-slop-cleaner <target>`  | Run the anti-slop cleanup workflow (`--review` for reviewer-only pass)                       |
 | `/oh-my-claudecode:autopilot <task>`        | Full autonomous execution                                                                     |
 | `/oh-my-claudecode:ultrawork <task>`        | Maximum performance mode with parallel agents                                                 |
 | `/oh-my-claudecode:team <N>:<agent> <task>` | Coordinated native team workflow                                                              |
 | `/oh-my-claudecode:ralph-init <task>`       | Initialize PRD for structured task tracking                                                   |
-| `/oh-my-claudecode:ralph <task>`            | Self-referential loop until task completion                                                   |
+| `/oh-my-claudecode:ralph <task>`            | Self-referential loop until task completion (`--critic=architect|critic|codex`)               |
 | `/oh-my-claudecode:ultraqa <goal>`          | Autonomous QA cycling workflow                                                                |
 | `/oh-my-claudecode:omc-plan <description>`  | Start planning session (supports consensus structured deliberation)                           |
 | `/oh-my-claudecode:ralplan <description>`   | Iterative planning with consensus structured deliberation (`--deliberate` for high-risk mode) |
 | `/oh-my-claudecode:deep-interview <idea>`   | Socratic interview with ambiguity scoring before execution                                    |
 | `/oh-my-claudecode:deepinit [path]`         | Index codebase with hierarchical AGENTS.md files                                              |
-| `/oh-my-claudecode:analyze <target>`        | Deep analysis and investigation                                                               |
 | `/oh-my-claudecode:sciomc <topic>`          | Parallel research orchestration                                                               |
-| `/oh-my-claudecode:tdd <feature>`           | TDD workflow enforcement                                                                      |
 | `/oh-my-claudecode:learner`                 | Extract reusable skill from session                                                           |
 | `/oh-my-claudecode:note <content>`          | Save notes to notepad.md                                                                      |
 | `/oh-my-claudecode:cancel`                  | Unified cancellation                                                                          |
+| `/oh-my-claudecode:setup`                   | Unified setup entrypoint (`setup`, `setup doctor`, `setup mcp`)                              |
 | `/oh-my-claudecode:omc-setup`               | One-time setup wizard                                                                         |
 | `/oh-my-claudecode:omc-doctor`              | Diagnose and fix installation issues                                                          |
 | `/oh-my-claudecode:omc-help`                | Show OMC usage guide                                                                          |
@@ -399,6 +410,19 @@ All skills are available as slash commands with the prefix `/oh-my-claudecode:`.
 | `/oh-my-claudecode:trace`                   | Show orchestration trace timeline                                                             |
 | `/oh-my-claudecode:psm <arguments>`         | Deprecated alias for project session manager                                                  |
 
+### Skill Pipeline Metadata (Preview)
+
+Built-in skills and slash-loaded skills can now declare a lightweight pipeline/handoff contract in frontmatter:
+
+```yaml
+pipeline: [deep-interview, omc-plan, autopilot]
+next-skill: omc-plan
+next-skill-args: --consensus --direct
+handoff: .omc/specs/deep-interview-{slug}.md
+```
+
+When present, OMC appends a standardized **Skill Pipeline** section to the rendered skill prompt so the current stage, handoff artifact, and explicit next `Skill("oh-my-claudecode:...")` invocation are carried forward consistently.
+
 ---
 
 ## Hooks System
@@ -512,8 +536,9 @@ Use these trigger phrases in natural language prompts to activate enhanced modes
 | ------------------------------------------------------- | --------------------------------------------------------------------------------------------- |
 | `ultrawork`, `ulw`                                      | Activates parallel agent orchestration                                                        |
 | `autopilot`, `build me`, `I want a`                     | Full autonomous execution                                                                     |
+| `deslop`, `anti-slop`, cleanup/refactor + slop smells         | Anti-slop cleanup workflow (`ai-slop-cleaner`)                                               |
 | `ralph`, `don't stop`, `must complete`                  | Persistence until verified complete                                                           |
-| `team`, `coordinated team`                              | Team pipeline orchestration                                                                   |
+| `ccg`, `claude-codex-gemini`                            | Claude-Codex-Gemini orchestration                                                             |
 | `ralplan`                                               | Iterative planning consensus with structured deliberation (`--deliberate` for high-risk mode) |
 | `deep interview`, `ouroboros`                           | Deep Socratic interview with mathematical clarity gating                                      |
 | `deepsearch`, `search the codebase`, `find in codebase` | Codebase-focused search mode                                                                  |
@@ -564,8 +589,8 @@ stopomc
 | Platform    | Install Method              | Hook Type      |
 | ----------- | --------------------------- | -------------- |
 | **Windows** | WSL2 recommended (see note) | Node.js (.mjs) |
-| **macOS**   | curl or npm                 | Bash (.sh)     |
-| **Linux**   | curl or npm                 | Bash (.sh)     |
+| **macOS**   | Claude Code Plugin          | Bash (.sh)     |
+| **Linux**   | Claude Code Plugin          | Bash (.sh)     |
 
 > **Note**: Bash hooks are fully portable across macOS and Linux (no GNU-specific dependencies).
 
@@ -629,28 +654,28 @@ For complete documentation, see **[Performance Monitoring Guide](./PERFORMANCE-M
 | Feature                 | Description                                     | Access                               |
 | ----------------------- | ----------------------------------------------- | ------------------------------------ |
 | **Agent Observatory**   | Real-time agent status, efficiency, bottlenecks | HUD / API                            |
-| **Token Analytics**     | Cost tracking, usage reports, budget warnings   | HUD (`analytics` preset), `omc cost` |
+| **Session-End Summaries** | Persisted per-session summaries and callback payloads | `.omc/sessions/*.json`, `session-end` |
 | **Session Replay**      | Event timeline for post-session analysis        | `.omc/state/agent-replay-*.jsonl`    |
+| **Session Search**      | Search prior local transcript/session artifacts  | `omc session search`, `session_search` |
 | **Intervention System** | Auto-detection of stale agents, cost overruns   | Automatic                            |
 
 ### CLI Commands
 
 ```bash
-omc                # Default analytics dashboard
-omc cost daily     # Daily cost report
-omc cost weekly    # Weekly cost report
-omc backfill       # Import historical transcript data
-# Agent breakdown: use HUD observatory / replay logs
+omc hud                              # Render the current HUD statusline
+omc team status <team-name>          # Inspect a running team job
+tail -20 .omc/state/agent-replay-*.jsonl
+ls .omc/sessions/*.json
 ```
 
-### HUD Analytics Preset
+### HUD Presets
 
-Enable detailed cost tracking in your status line:
+Enable a supported preset for agent and context visibility in your status line:
 
 ```json
 {
   "omcHud": {
-    "preset": "analytics"
+    "preset": "focused"
   }
 }
 ```
@@ -747,11 +772,13 @@ To manually update, re-run the plugin install command or use Claude Code's built
 
 ### Uninstall
 
-```bash
-curl -fsSL https://raw.githubusercontent.com/Yeachan-Heo/oh-my-claudecode/main/scripts/uninstall.sh | bash
+Use Claude Code's plugin management:
+
+```
+/plugin uninstall oh-my-claudecode@oh-my-claudecode
 ```
 
-Or manually:
+Or manually remove the installed files:
 
 ```bash
 rm ~/.claude/agents/{architect,document-specialist,explore,designer,writer,vision,critic,analyst,executor,qa-tester}.md

package/docs/TIERED_AGENTS_V2.md

@@ -199,8 +199,9 @@ Output escalation recommendation:
 | document-specialist | Sonnet | Same | Comprehensive research |
 
 **Shared Constraints**:
-- ALWAYS cite sources with URLs
-- Prefer official docs
+- Check repo docs first when the question is project-specific
+- ALWAYS cite sources with URLs (or stable curated-doc IDs when a URL is unavailable)
+- Prefer Context Hub / `chub` (or another curated docs backend already configured) for external API/framework correctness when available, then official docs
 - Note version compatibility
 - Flag outdated information
 

package/docs/design/SKILL_AUDIT_1445.md

@@ -0,0 +1,75 @@
+# Issue #1445 Skill Audit
+
+Date: 2026-03-08
+
+## Goal
+
+Audit the seven questioned-value skills called out in issue #1445 and decide whether they are ready for deprecation, should remain built-in, or need follow-up instrumentation before any removal decision.
+
+## Skills Reviewed
+
+| Skill | Lines | Initial concern | Audit verdict |
+| --- | ---: | --- | --- |
+| `configure-notifications` | 1213 | Large for a narrow task | Keep for now; too much behavior to deprecate without usage data |
+| `sciomc` | 510 | Niche scientific workflow | Keep for now; niche is not the same as unused |
+| `deep-interview` | 551 | Complex and unclear frequency | Keep for now; keyword-triggered planning surface still exists |
+| `project-session-manager` | 564 | Overlaps with native worktrees | Keep for now; still provides tmux/session orchestration beyond plain git worktrees |
+| `writer-memory` | 443 | Domain-specific | Keep for now; domain specificity alone is not sufficient removal evidence |
+| `external-context` | 83 | Thin wrapper concern | Candidate for later consolidation, but not enough evidence for removal today |
+| `release` | 87 | Project-specific | Keep for now; project-specific maintenance workflows are expected in this repo |
+
+## Existing Evidence Sources
+
+The repository already has useful observability surfaces that can support a future deprecation decision:
+
+- `src/hooks/subagent-tracker/flow-tracer.ts`
+- `src/hooks/subagent-tracker/session-replay.ts`
+- `src/tools/trace-tools.ts`
+- `docs/PERFORMANCE-MONITORING.md`
+- `skills/learn-about-omc/SKILL.md`
+
+These surfaces provide session-level traces, replay data, and aggregate summaries. They are enough to support a structured manual audit before adding new opt-in telemetry.
+
+## Why This Issue Is Not Deprecation-Ready Yet
+
+A removal/deprecation decision still lacks three things:
+
+1. **A denominator** — whether usage should be measured against canonical skills only, canonical + deprecated aliases, or by user sessions.
+2. **A time window** — there is no agreed threshold for "<5% usage" across days, weeks, or releases.
+3. **A privacy posture** — adding new telemetry would require explicit opt-in scope and retention rules.
+
+Without those, immediate removals would be arbitrary and hard to defend.
+
+## Recommended Evaluation Rubric
+
+Before any future deprecation PR, require all of the following:
+
+1. At least one release cycle of trace-derived usage data or a clearly documented manual sampling method.
+2. A written threshold for low usage, including the population being measured.
+3. A migration path for any command that remains user-facing.
+4. A replacement surface, if the skill is removed because native tools or other skills already cover the use case.
+
+## Recommended Next Steps
+
+### Keep as-is for now
+
+- `configure-notifications`
+- `sciomc`
+- `deep-interview`
+- `project-session-manager`
+- `writer-memory`
+- `release`
+
+### Revisit later with stronger evidence
+
+- `external-context`
+
+### Follow-up work if maintainers want harder data
+
+1. Document a trace-based audit workflow using existing `trace_summary` and replay data.
+2. Decide whether `learn-about-omc` should surface that audit view directly.
+3. Only then consider new opt-in telemetry if the trace workflow proves insufficient.
+
+## Conclusion
+
+Issue #1445 is valid as an audit request, but it does **not** currently justify removing any of the reviewed skills. The correct outcome today is an audit record plus a clearer decision framework, not a deprecation batch.

package/docs/ko/MIGRATION.md

@@ -242,7 +242,7 @@ npm install -g claudecode-omc
 | `/oh-my-claudecode:plan "description"` | 자연스럽게 플래닝 시작                                     | ✅ 예               |
 | `/oh-my-claudecode:review [path]`      | 기존과 동일하게 호출                                       | ✅ 예 (변경 없음)   |
 | `/oh-my-claudecode:deepsearch "query"` | "find" 또는 "search"라고 말하기                            | ✅ 예 (자동 감지)   |
-| `/oh-my-claudecode:analyze "target"`   | "analyze" 또는 "investigate"라고 말하기                    | ✅ 예 (자동 감지)   |
+| `/oh-my-claudecode:analyze "target"`   | "analyze"라고 말하기 — debugger/architect 에이전트로 라우팅 | ✅ 예 (키워드 라우트) |
 | `/oh-my-claudecode:deepinit [path]`    | 기존과 동일하게 호출                                       | ✅ 예 (변경 없음)   |
 | `/oh-my-claudecode:git-master`         | "git", "commit", "atomic commit"이라고 말하기              | ✅ 예 (자동 감지)   |
 | `/oh-my-claudecode:frontend-ui-ux`     | "UI", "styling", "component", "design"이라고 말하기        | ✅ 예 (자동 감지)   |
@@ -637,7 +637,7 @@ npm update -g claudecode-omc
 
 - `review` - explore → architect → critic → executor
 - `implement` - planner → executor → tdd-guide
-- `debug` - explore → architect → build-fixer
+- `debug` - explore → architect → debugger
 - `research` - parallel(document-specialist, explore) → architect → writer
 - `refactor` - explore → architect-medium → executor-high → qa-tester
 - `security` - explore → security-reviewer → executor → security-reviewer-low

package/docs/ko/REFERENCE.md

@@ -9,7 +9,7 @@ oh-my-claudecode의 전체 레퍼런스입니다. 빠른 시작은 메인 [READM
 - [설치](#설치)
 - [설정](#설정)
 - [에이전트 (28개)](#에이전트-28개)
-- [스킬 (37개)](#스킬-37개)
+- [스킬 (33개)](#스킬-33개)
 - [슬래시 명령어](#슬래시-명령어)
 - [훅 시스템](#훅-시스템)
 - [매직 키워드](#매직-키워드)
@@ -80,7 +80,7 @@ oh-my-claudecode의 전체 레퍼런스입니다. 빠른 시작은 메인 [READM
 | 기능            | 미설정 시   | omc 설정 시                |
 | --------------- | ----------- | -------------------------- |
 | 에이전트 위임   | 수동만 가능 | 작업에 따라 자동           |
-| 키워드 감지     | 비활성화    | ultrawork, search, analyze |
+| 키워드 감지     | 비활성화    | ultrawork, search |
 | 할 일 연속 실행 | 기본        | 완료 강제                  |
 | 모델 라우팅     | 기본값      | 스마트 티어 선택           |
 | 스킬 조합       | 없음        | 자동 스킬 결합             |
@@ -183,7 +183,7 @@ Task 도구를 통해 호출할 때는 항상 `oh-my-claudecode:` 접두사를
 | **사전 플래닝**     | -                       | -                     | `analyst`           |
 | **테스트**          | -                       | `qa-tester`           | -                   |
 | **보안**            | `security-reviewer-low` | -                     | `security-reviewer` |
-| **빌드**            | -                       | `build-fixer`         | -                   |
+| **빌드**            | -                       | `debugger`            | -                   |
 | **TDD**             | `tdd-guide-low`         | `tdd-guide`           | -                   |
 | **코드 리뷰**       | -                       | -                     | `code-reviewer`     |
 | **데이터 사이언스** | -                       | `scientist`           | `scientist-high`    |
@@ -211,8 +211,8 @@ Task 도구를 통해 호출할 때는 항상 `oh-my-claudecode:` 접두사를
 | CLI 대화형 테스트      | `qa-tester`                   | sonnet |
 | 보안 리뷰              | `security-reviewer`           | opus   |
 | 빠른 보안 스캔         | `security-reviewer-low`       | haiku  |
-| 빌드 오류 수정         | `build-fixer`                 | sonnet |
-| 간단한 빌드 수정       | `build-fixer` (model=haiku)   | haiku  |
+| 빌드 오류 수정         | `debugger`                    | sonnet |
+| 간단한 빌드 수정       | `debugger` (model=haiku)      | haiku  |
 | TDD 워크플로우         | `tdd-guide`                   | sonnet |
 | 빠른 테스트 제안       | `tdd-guide-low`               | haiku  |
 | 코드 리뷰              | `code-reviewer`               | opus   |
@@ -223,7 +223,7 @@ Task 도구를 통해 호출할 때는 항상 `oh-my-claudecode:` 접두사를
 
 ---
 
-## 스킬 (37개)
+## 스킬 (33개)
 
 ### 코어 스킬
 
@@ -249,15 +249,10 @@ Task 도구를 통해 호출할 때는 항상 `oh-my-claudecode:` 접두사를
 | ----------------- | ----------------------------------------- | ----------------------------------- |
 | `deepinit`        | 계층적 AGENTS.md 코드베이스 문서화        | `/oh-my-claudecode:deepinit`        |
 | `deepsearch`      | 다중 전략 코드베이스 검색                 | `/oh-my-claudecode:deepsearch`      |
-| `analyze`         | 심층 분석 및 조사                         | `/oh-my-claudecode:analyze`         |
 | `sciomc`          | 병렬 scientist 오케스트레이션             | `/oh-my-claudecode:sciomc`          |
 | `frontend-ui-ux`  | 디자이너 출신 개발자의 UI/UX 전문성       | (자동 활성화)                       |
 | `git-master`      | 원자적 커밋 및 히스토리를 위한 Git 전문가 | (자동 활성화)                       |
-| `tdd`             | TDD 강제: 테스트 우선 개발                | `/oh-my-claudecode:tdd`             |
 | `learner`         | 세션에서 재사용 가능한 스킬 추출          | `/oh-my-claudecode:learner`         |
-| `build-fix`       | 빌드 및 TypeScript 오류 수정              | `/oh-my-claudecode:build-fix`       |
-| `code-review`     | 종합 코드 리뷰                            | `/oh-my-claudecode:code-review`     |
-| `security-review` | 보안 취약점 탐지                          | `/oh-my-claudecode:security-review` |
 
 ### 유틸리티 스킬
 
@@ -298,9 +293,7 @@ Task 도구를 통해 호출할 때는 항상 `oh-my-claudecode:` 접두사를
 | `/oh-my-claudecode:review [plan-path]`       | critic을 통한 플랜 리뷰                   |
 | `/oh-my-claudecode:deepsearch <query>`       | 다중 전략 코드베이스 검색                 |
 | `/oh-my-claudecode:deepinit [path]`          | 계층적 AGENTS.md 파일로 코드베이스 인덱싱 |
-| `/oh-my-claudecode:analyze <target>`         | 심층 분석 및 조사                         |
 | `/oh-my-claudecode:sciomc <topic>`           | 병렬 리서치 오케스트레이션                |
-| `/oh-my-claudecode:tdd <feature>`            | TDD 워크플로우 강제                       |
 | `/oh-my-claudecode:learner`                  | 세션에서 재사용 가능한 스킬 추출          |
 | `/oh-my-claudecode:note <content>`           | notepad.md에 메모 저장                    |
 | `/oh-my-claudecode:cancel`                   | 통합 취소                                 |
@@ -606,28 +599,27 @@ oh-my-claudecode에는 에이전트 성능, 토큰 사용량 및 병렬 워크
 | 기능                    | 설명                                    | 접근 방법                         |
 | ----------------------- | --------------------------------------- | --------------------------------- |
 | **Agent Observatory**   | 실시간 에이전트 상태, 효율성, 병목 현상 | HUD / API                         |
-| **Token Analytics**     | 비용 추적, 사용량 보고서, 예산 경고     | HUD(`analytics` 프리셋), `omc cost` |
+| **Session-End Summaries** | 세션 종료 시 기록되는 요약 및 콜백 페이로드 | `.omc/sessions/*.json`, `session-end` |
 | **Session Replay**      | 세션 후 분석을 위한 이벤트 타임라인     | `.omc/state/agent-replay-*.jsonl` |
 | **Intervention System** | 정체된 에이전트, 비용 초과 자동 감지    | 자동                              |
 
 ### CLI 명령어
 
 ```bash
-omc                # 기본 분석 대시보드
-omc cost daily     # 일일 비용 보고서
-omc cost weekly    # 주간 비용 보고서
-omc backfill       # 과거 트랜스크립트 데이터 가져오기
-# 에이전트 분석: HUD observatory / replay 로그 사용
+omc hud                              # 현재 HUD 상태줄 렌더링
+omc team status <team-name>          # 실행 중인 팀 작업 확인
+tail -20 .omc/state/agent-replay-*.jsonl
+ls .omc/sessions/*.json
 ```
 
-### HUD Analytics 프리셋
+### HUD 프리셋
 
-상태 표시줄에서 상세 비용 추적을 활성화합니다:
+상태 표시줄에서 에이전트/컨텍스트 가시성을 높이려면 지원되는 프리셋을 사용하세요:
 
 ```json
 {
   "omcHud": {
-    "preset": "analytics"
+    "preset": "focused"
   }
 }
 ```