oh-my-customcode 0.166.0 → 0.168.0

package/dist/cli/index.js

@@ -241,7 +241,7 @@ var init_package = __esm(() => {
     workspaces: [
       "packages/*"
     ],
-    version: "0.166.0",
+    version: "0.168.0",
     description: "Batteries-included agent harness for Claude Code",
     type: "module",
     bin: {

package/dist/index.js

@@ -2031,7 +2031,7 @@ var package_default = {
   workspaces: [
     "packages/*"
   ],
-  version: "0.166.0",
+  version: "0.168.0",
   description: "Batteries-included agent harness for Claude Code",
   type: "module",
   bin: {

package/package.json

@@ -3,7 +3,7 @@
   "workspaces": [
     "packages/*"
   ],
-  "version": "0.166.0",
+  "version": "0.168.0",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {

package/templates/.claude/rules/MUST-agent-teams.md

@@ -76,6 +76,16 @@ Quick rule: User explicitly preferred plain subagents this session? → use Agen
 ╚══════════════════════════════════════════════════════════════════╝
 -->
 
+### Gate Transparency
+
+When the gate resolves to **Agent Tool** for a 3+ agent dispatch (e.g. mechanical disjoint-file editing with no review loop), announce the gate result in one line BEFORE spawning — e.g. `R018 게이트: 3개 disjoint-file 도메인, 리뷰 사이클 없음 → Agent Tool 폴백`. Silently selecting Agent Tool on a 3+ agent batch loses the gate-evaluation audit trail and reads as if the R018/R009 Self-Check #4 gate was skipped.
+
+| Anti-pattern | Required |
+|--------------|----------|
+| 3+ 에이전트 병렬 스폰 announce에 게이트 평가 결과 누락 | 스폰 전 한 줄로 게이트 결과 명시 (Agent Tool 폴백 사유 또는 Agent Teams 선택 사유) |
+
+Origin: #1293 (Session 110 retrospective, Low).
+
 ### Spawn Completeness Check
 
 All members must be spawned in a single message. Partial spawning needs correction per R018 and R009.
@@ -331,6 +341,8 @@ Agent Teams member completion MUST be verified by deterministic ground-truth —
 
 Cross-reference: R020 ("actual outcome ≠ attempt" — verifying that a command ran is not the same as verifying it succeeded).
 
+> **CC v2.1.162+**: `claude agents --json` now includes a `waitingFor` field showing what a waiting session is blocked on (e.g. a permission prompt). Use it as an additional deterministic ground-truth signal — a member with a non-empty `waitingFor` is blocked on input (needs unblocking), NOT silently stalled (reassign per stall handling below). This distinguishes the two failure modes the verification is meant to separate.
+
 **Stall handling**: When a member shows no task progress within ~2 minutes despite spawn + owner assignment + SendMessage coordination, reassign the work to a standalone Agent (R009) rather than continuing to nudge the stalled member. Stalled Teams members waste tokens on idle polling and delay the overall workflow.
 
 Observed instance: v0.159.0 release (session 105) — members assigned to disjoint-file cleanup tasks went idle without executing; deterministic git-diff check exposed the gap; work was reassigned to standalone parallel Agents. References: #1261, #1262.

package/templates/.claude/rules/MUST-parallel-execution.md

@@ -30,7 +30,7 @@ Before writing/editing multiple files:
 1. Are files independent? → YES: spawn parallel agents
 2. Using Write/Edit sequentially for 2+ files? → parallelize instead
 3. Specialized agent available? → Use it (not general-purpose)
-4. Agent Teams available? → **Check R018 criteria before spawning 2+ agents**
+4. Agent Teams available? → **Check R018 criteria before spawning 2+ agents; for a 3+ agent batch, announce the gate result (Agent Tool fallback reason or Agent Teams choice) — see R018 Self-Check "Gate Transparency"**
 5. Running agent stalled (2x+ duration)? → Spawn independent follow-up tasks immediately
 6. Announced a parallel dispatch in prose? → ALL announced tool calls MUST be in the SAME message as the announcement (announce-execution consistency)
 

package/templates/.claude/skills/homework/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: homework
-description: On session cleanup ("세션 정리") or /homework invocation, analyze the current and linked previous sessions, extract mistakes (찐빠), and report them via omcustom-feedback with a confirmation gate. Use when wrapping up a session or auditing recent work for harness gaps.
+description: On explicit /homework invocation, analyze the current and linked previous sessions, extract mistakes (찐빠), and report them via omcustom-feedback with a confirmation gate. Auto-activation on session cleanup/session-end signals is OPT-IN (default OFF) — requires an explicit project/user directive. Use when explicitly auditing recent work for harness gaps.
 scope: harness
 user-invocable: true
 argument-hint: "[--dry-run] [--days <n>] [--severity <critical|high|medium|low>]"
@@ -25,13 +25,15 @@ This skill is the dedicated entry point for R011's "Session-End Retrospective Fe
 
 ## Trigger Detection
 
-Activate when the user says any of:
-- "세션 정리" / "숙제" / "회고"
-- "homework" / "session cleanup" / "wrap up"
-- Explicit `/homework` invocation
-- Session-end signals: "끝", "종료", "마무리", "done", "end session"
+**Default: OFF for auto-activation.** This skill does NOT auto-run on session cleanup or session-end signals unless explicitly enabled. The default is `false` — silence is a non-trigger.
 
-When activated as a session-end signal, this skill runs BEFORE sys-memory-keeper's MEMORY.md update (R011 session-end self-check order: homework → memory save).
+Activate ONLY when:
+- **Explicit `/homework` invocation** (always runs)
+- **Explicit opt-in**: the user/project has explicitly directed homework to run on session cleanup — e.g., a CLAUDE.md directive such as "run homework on every session cleanup", or a settings flag. A one-off explicit request ("회고 돌려줘", "homework 실행") also counts.
+
+If no explicit opt-in exists, treat session-cleanup / session-end phrases ("세션 정리", "숙제", "회고", "끝", "종료", "마무리", "done", "wrap up", "session cleanup", "end session") as **NON-triggers** — do NOT auto-run. You MAY briefly remind the user that `/homework` is available, then proceed with normal session-end handling.
+
+When auto-activation IS explicitly enabled and fires as a session-end signal, this skill runs BEFORE sys-memory-keeper's MEMORY.md update (R011 session-end self-check order: homework → memory save).
 
 ## Workflow
 

package/templates/.claude/skills/pipeline/SKILL.md

@@ -152,7 +152,7 @@ The `auto-dev.yaml` (and other workflow YAML files) exist in **4 locations**. On
 **Key rules:**
 - The runtime source is `.claude/skills/pipeline/workflows/` (skill base dir). Do NOT confuse with repo-root `workflows/`.
 - When modifying any workflow YAML, update **all applicable mirrors** to prevent drift. `verify-template-sync.sh` (#1286) detects drift automatically on CI.
-- Repo-root `workflows/` is a legacy `/omcustom:workflow` remnant — it also contains `eraser.yaml`. Do not delete without checking for other references.
+- Repo-root `workflows/` is a legacy `/omcustom:workflow` remnant. It contains `eraser.yaml`, **deprecated as of v0.167.0 (#1289)** — retained but unmaintained: its ARCHITECTURE.md-sync function moved to the release workflow + validate-docs, and its diagram generation to the `eraser-diagrams` plugin skill. Not reachable via `/pipeline`. Do not delete without checking for other references.
 
 ## Error Handling
 

package/templates/.claude/skills/research/SKILL.md

@@ -117,6 +117,8 @@ fi
 
 **Action**: `[Pre-flight] WARN: Context usage at {pct}%. 10-team research typically adds 30-40% context. Consider /compact before proceeding, or results may be truncated.`
 
+> **File-absent branch (#1298)**: `$CONTEXT_FILE`가 존재하지 않으면 입력이 측정 불가하다 — `PASS (context budget unmeasured — file absent)`로 보고하고 WARN을 내지 않는다. 파일을 읽지 않고 WARN 상태를 특성화하지 않는다(R020 Read-Before-Characterize). WARN은 파일이 존재하고 context_pct > 40 일 때만 emit한다.
+
 ### Display Format
 
 ```
@@ -226,6 +228,10 @@ Reference: `feedback_sensitive_path_tmp_bypass.md`, R006 sensitive-path handling
 | Ecomode | Auto-activate for team result aggregation (R013) |
 | Intent display | Show research plan before execution (R015) |
 
+## External Quantitative-Fact Source Tagging
+
+research 팀이 WebFetch로 구체적 정량 주장(benchmark 수치, table 값)을 수집하면, synthesis/report는 출처별로 태깅해야 한다: `WebFetch-derived (unverified)` vs `PDF/primary-verified`. WebFetch는 small fast model + URL당 15분 캐시를 사용하므로, N개 팀이 동일 URL을 fetch하는 것은 독립 교차검증이 아니다(팀 간 합의가 공유 캐시 artifact일 수 있음). primary source에서 검증 불가한 cross-cutting fact는 verifier에게 명시적 ground-truth로 제공해야 한다(R023). 영구 이슈/아티팩트에 정확한 수치를 primary-source 검증 또는 명시적 unverified 태그 없이 사실로 기재하지 않는다.
+
 ## Retrieval-Reasoning Separation
 
 Retrieval and reasoning are distinct cognitive operations that benefit from explicit role separation. Mixing them in a single agent degrades both: retrieval becomes biased by premature conclusions, and reasoning gets polluted by search noise.

package/templates/.claude/skills/scout/SKILL.md

@@ -91,6 +91,8 @@ Before execution, show the plan:
    - Approach and principles
 3. If fetch fails — report error, abort
 
+> **External quantitative-fact source tagging** (#1298): WebFetch가 산출한 구체적 정량 주장(benchmark 수치, table 값, metric)은 이슈 본문에 `WebFetch-derived (unverified)`로 태깅한다 — 검증된 사실로 제시하지 않는다. WebFetch는 small fast model + 15분 URL 캐시를 사용하므로, 동일 URL을 여러 번 fetch해도 독립 교차검증이 아니다. load-bearing 수치는 primary PDF/원문으로 1회 검증하거나 명시적으로 unverified로 표기한다. (R020 Read-Before-Characterize, R023 Verifier Ground-Truth for cross-cutting facts)
+
 ### Phase 2: Load Project Philosophy
 
 1. `Read(CLAUDE.md)` — extract architecture philosophy:

package/templates/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "0.166.0",
+  "version": "0.168.0",
   "lastUpdated": "2026-05-20T00:00:00.000Z",
   "omcustomMinClaudeCode": "2.1.121",
   "omcustomMinClaudeCodeReason": "Sensitive-path direct Write/Edit on .claude/** under bypassPermissions (R010 deprecation, #1101)",