oh-my-customcodex 0.5.12 → 0.5.14

package/README.md

@@ -13,7 +13,7 @@
 
 **[한국어 문서 (Korean)](./README_ko.md)**
 
-50 agents. 120 skills. 22 rules. One command.
+50 agents. 121 skills. 22 rules. One command.
 
 ```bash
 npm install -g oh-my-customcodex && cd your-project && omcustomcodex init
@@ -135,7 +135,7 @@ Each agent declares its tools, model, memory scope, and limitations in YAML fron
 
 ---
 
-### Skills (120)
+### Skills (121)
 
 | Category | Count | Includes |
 |----------|-------|----------|
@@ -288,7 +288,7 @@ your-project/
 │   ├── contexts/               # 4 shared context files
 │   └── ontology/               # Knowledge graph for RAG
 ├── .agents/
-│   └── skills/                 # 120 installed skill modules
+│   └── skills/                 # 121 installed skill modules
 └── guides/                     # 51 reference documents
 ```
 

package/dist/cli/index.js

@@ -3091,7 +3091,7 @@ var init_package = __esm(() => {
     workspaces: [
       "packages/*"
     ],
-    version: "0.5.12",
+    version: "0.5.14",
     requiresCC: ">=2.1.121",
     claudeCode: {
       minimumVersion: "2.1.121",

package/dist/index.js

@@ -2316,7 +2316,7 @@ var package_default = {
   workspaces: [
     "packages/*"
   ],
-  version: "0.5.12",
+  version: "0.5.14",
   requiresCC: ">=2.1.121",
   claudeCode: {
     minimumVersion: "2.1.121",

package/package.json

@@ -3,7 +3,7 @@
   "workspaces": [
     "packages/*"
   ],
-  "version": "0.5.12",
+  "version": "0.5.14",
   "requiresCC": ">=2.1.121",
   "claudeCode": {
     "minimumVersion": "2.1.121",

package/templates/.claude/hooks/hooks.json

@@ -110,7 +110,7 @@
             "command": "bash .codex/hooks/scripts/rtk-intercept.sh"
           }
         ],
-        "description": "RTK auto-intercept — transparently rewrites CLI commands through RTK proxy when available (R015 advisory)"
+        "description": "RTK auto-intercept — transparently rewrites CLI commands through RTK proxy when available (R013 advisory)"
       },
       {
         "matcher": "tool == \"Bash\" && tool_input.command matches \"(rm|git rm|mv|unlink|codex/rules)\"",

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

@@ -75,6 +75,17 @@ disableSkillShellExecution: true  # Disable inline shell execution in skills (v2
 Agent frontmatter `hooks:` fire when the agent runs as a main-thread agent via `--agent` flag in v2.1.116+. Hook JSON output `terminalSequence` field for desktop notifications, window title changes, and terminal bells without controlling terminal added in v2.1.141+. `claude agents --cwd <path>` for directory-scoped session lists added in v2.1.141+. Background agents launched via `/bg` preserve current permission mode in v2.1.141+. `CLAUDE_CODE_PLUGIN_PREFER_HTTPS` and `ANTHROPIC_WORKSPACE_ID` environment variables added in v2.1.141+ for HTTPS plugin clones and workspace-scoped federation.
 -->
 
+<!-- DETAIL: Claude Compatibility Notes for Packaged `.claude` Templates
+This Codex port ships `.claude` compatibility templates. When updating those templates, account for recent Claude Code behavior even though the active runtime surface is Codex/OMX:
+
+- v2.1.159: no user-facing template action required (internal infrastructure release).
+- v2.1.160: `acceptEdits` prompts for build-tool config writes; grep/egrep/fgrep of a single file can satisfy read-before-edit in Claude Code, but Codex agents should still follow the active Codex read/edit policy.
+- v2.1.161: independent parallel tool calls no longer cancel siblings when one Bash call fails; this supports R009 same-message batching for independent work.
+- v2.1.162: `claude agents --json` includes waiting/blocker metadata and explicit `--tools Grep/Glob` behavior is fixed; compatibility prompts may use those fields when diagnosing stuck Claude sessions.
+- v2.1.163: managed `requiredMinimumVersion`/`requiredMaximumVersion`, `/plugin list`, Stop/SubagentStop `hookSpecificOutput.additionalContext`, and skill command literal `\$` escaping are available. Hook/skill template changes should preserve these affordances.
+- v2.1.165: bug-fix/reliability release; no local template change required beyond compatibility confirmation.
+-->
+
 ## Hook Event Types
 
 27 event types documented: SessionStart, UserPromptSubmit, PreToolUse, PermissionRequest, PermissionDenied, PostToolUse, PostToolUseFailure, Notification, SubagentStart, SubagentStop, TaskCreated, TaskCompleted, Stop, StopFailure, TeammateIdle, InstructionsLoaded, ConfigChange, CwdChanged, FileChanged, WorktreeCreate, WorktreeRemove, PreCompact, PostCompact, Elicitation, ElicitationResult, PostMessage, SessionEnd. 4 handler types: command, prompt, http, agent. See full reference table via Read tool.

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

@@ -48,6 +48,20 @@ Quick rule: explicit user preference for plain subagents wins. Otherwise use Tea
 7. Otherwise, use Agent Teams when collaboration or shared state has material value.
 -->
 
+## Gate Transparency
+
+For 3+ agent dispatches, announce the R018 gate result before spawning (Agent Tool fallback reason or Agent Teams choice).
+
+<!-- DETAIL: Gate Transparency
+When the R018 gate resolves to standalone Agent Tool for a 3+ agent dispatch (for example mechanical disjoint-file editing with no review loop), announce the gate result in one line before spawning: `R018 gate: 3 disjoint-file domains, no review loop → Agent Tool fallback`. Silently selecting Agent Tool on a 3+ agent batch loses the gate-evaluation audit trail.
+
+| Anti-pattern | Required |
+|--------------|----------|
+| 3+ 에이전트 병렬 스폰 announce에 게이트 평가 결과 누락 | 스폰 전 한 줄로 Agent Tool 폴백 사유 또는 Agent Teams 선택 사유 명시 |
+
+Origin: #1464.
+-->
+
 ## Spawn Completeness
 
 Spawn all members for a parallel team slice in one message; partial/sequential spawning needs correction.

package/templates/.claude/rules/MUST-completion-verification.md

@@ -67,6 +67,29 @@ Parallel batches return results together, so a same-batch permanent dispatch pro
 
 Example: do not diagnose `triage-dispatch.yml` from memory, create an issue, and delegate a fix in the same parallel call before reading the workflow. If the read later shows a different root cause, the issue, PR, and commit trail become correction debt even when the eventual code direction is acceptable.
 
+## Degraded-Output Re-Verification Gate
+
+When tool output shows provider instability, buffering, truncation, duplicated chunks, `529`, timeout recovery, or `(no result)` while a permanent action is being considered, treat the current read as degraded. Do not characterize corruption, missing files, stale state, release failure, or data loss from that single degraded read.
+
+Before destructive recovery, issue creation, rule/workflow/template edits, release publication, or fix delegation based on degraded output:
+
+1. Re-read the authoritative source with a deterministic command or API call.
+2. Use a second narrow check that can falsify the failure hypothesis, such as `grep -c`, `sort -u`, `git status`, `git show`, `gh api`, or a direct file diff.
+3. Record whether the first read was degraded and whether the re-check confirmed or corrected the hypothesis.
+
+If the deterministic re-check cannot run, halt or reduce the action to a non-destructive diagnostic note.
+
+## Workflow Script Sanity Check
+
+Before invoking or registering generated workflow code, run a Tier-1 sanity pass:
+
+1. Search for unresolved placeholders, malformed identifiers, and known dead-line patterns.
+2. Assemble the exact script body before execution; do not concatenate facts or guardrails after the call starts.
+3. Run the language parser or the narrowest no-side-effect syntax check available.
+4. If syntax validation is unavailable, read the generated body back and perform a focused self-review before launch.
+
+This check is mandatory for workflow scripts that will run automation, mutate GitHub state, or gate a release.
+
 ## Test-Skip Is Not Completion
 
 Skipping tests, lowering coverage thresholds, narrowing the test command, or marking suites as TODO may be a temporary containment step, but it never satisfies completion by itself.

package/templates/.claude/rules/MUST-continuous-improvement.md

@@ -51,6 +51,18 @@ When repeating agent failures or suboptimal routing is detected:
 
 This connects R016's continuous improvement loop with the adaptive-harness skill's learning capability.
 
+## Skill Promotion Threshold
+
+Promote a recurring workflow into a skill only when the evidence is strong enough to justify a durable interface.
+
+| Evidence | Action |
+|----------|--------|
+| One clear occurrence | Record memory or issue; do not create a skill by default |
+| Two direct successful repetitions with stable inputs/outputs | Candidate for `skill-extractor` Phase 1 shortlist |
+| Three or more direct repetitions, or two repetitions plus explicit user confirmation | Confirmed promotion candidate |
+
+Before creating a new skill, verify the candidate is not already covered by an existing skill, rule, guide, hook, or lightweight memory entry. Ambiguous, sensitive, one-off, or ownership-unclear candidates are explicitly skipped with a reason.
+
 ## External Repository Contribution Pre-Check
 
 Before creating or modifying assets for an external repository or upstream contribution target, inspect that repository's local contract before implementing:

package/templates/.claude/rules/MUST-orchestrator-coordination.md

@@ -248,6 +248,19 @@ Known limitation: `arch-documenter` has `disallowedTools: [Bash]`. Do not ask it
 
 The `agent-capability-precheck.sh` hook blocks obvious mismatches so the orchestrator re-routes before spawning an agent that cannot execute the requested work.
 
+### Delegated Path Existence Pre-Check
+
+Before putting concrete file paths in a delegated prompt, verify those paths exist or explicitly mark them as new files. A tool-capability match is insufficient when the prompt names a path.
+
+Required check:
+
+1. Use `rg --files`, `find`, `ls`, or the repository index to prove each existing path.
+2. If a path is missing, locate the current equivalent before delegating.
+3. Include only verified paths in the prompt, or say `create new file: <path>` when creation is intended.
+4. For multi-copy assets, verify all source/template mirrors before assigning the edit. If the copies are expected to match, check content identity (`cmp`, checksum, or `diff -q`) before delegation; if they intentionally differ, document the canonical source and drift rationale in the prompt.
+
+Do not rely on the delegate to repair stale path guesses in shared workflow, rule, guide, or release tasks.
+
 <!-- DETAIL: Autonomous Execution Mode
 
 ## Autonomous Execution Mode

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

@@ -30,15 +30,21 @@ 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; announce 3+ agent gate result**
 5. Running agent stalled (2x+ duration)? → Spawn independent follow-up tasks immediately
+6. Parallel dispatch announced? → put all announced tool calls in the same message
 
 ### Common Violations to Avoid
 
+<!-- DETAIL: Common Violations Short Examples
 ```
 ❌ WRONG: Write(file1.kt) → Write(file2.kt) → ... (sequential)
 ✓ CORRECT: Agent(agent1→file1.kt) + Agent(agent2→file2.kt) + ... (same message, parallel)
+
+❌ WRONG: Announce "milestone 생성 + 구조 확인 병렬" but dispatch only one tool; run the other next turn (announce-execution mismatch)
+✓ CORRECT: When announcing N parallel tools, include ALL N tool calls in the SAME message as the announcement
 ```
+-->
 
 <!-- DETAIL: Full violation examples (4 pairs)
 ❌ WRONG: Writing files one by one
@@ -58,6 +64,10 @@ Before writing/editing multiple files:
 
 > **Agent Teams partial spawn** → See R018 (MUST-agent-teams.md) "Spawn Completeness Check".
 
+<!-- DETAIL: v2.1.161 compatibility
+Claude Code parallel tool calls in a single batch are independent — one failed Bash command no longer cancels sibling calls. This lowers the safety cost of R009 announce-execution consistency for independent work.
+-->
+
 ## Execution Rules
 
 | Rule | Detail |

package/templates/.claude/rules/SHOULD-memory-integration.md

@@ -285,6 +285,30 @@ User Model data feeds into intent-detection (R015) and routing skill confidence
 
 -->
 
+<!-- DETAIL: Attention-Weight Memory Tiering
+> Origin: #1450 (Dual-Brain scout:internalize partial port — attention-weight tiering only)
+
+Memory entries are managed across two orthogonal axes: confidence and attention weight. Confidence answers “how verified is this?”; attention weight answers “how frequently/recently should this be loaded?”.
+
+| Axis | Tag example | Meaning |
+|------|-------------|---------|
+| Confidence | `[confidence: high/medium/low]` | Verification level |
+| Attention Weight | `[tier: hot/warm/cold/archived]` | Loading priority and recency/frequency |
+
+### 4-tier policy
+
+| Tier | Meaning | Handling |
+|------|---------|----------|
+| Hot | Active current-session patterns | Keep near the top of MEMORY.md / active recall |
+| Warm | Recently relevant patterns | Keep in MEMORY.md after Hot entries |
+| Cold | Rarely referenced but still useful | Move to an archive/index when memory budget is tight |
+| Archived | Long-inactive or superseded | Keep only an index/reference unless explicitly recalled |
+
+Promotion happens when an entry is referenced or re-verified. Demotion happens during session-end memory maintenance when an entry has not been referenced across recent sessions. `[permanent]` entries are exempt from automatic demotion.
+
+Budget rule: when approaching the MEMORY.md 200-line prompt budget, prune/archive Cold entries first, then low-confidence Warm entries. Hot entries should remain available unless contradicted by evidence.
+-->
+
 ## Mid-Session Immediate Save
 
 Save memory IMMEDIATELY upon surprising discovery — do not defer to session end.

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

@@ -0,0 +1,221 @@
+---
+name: homework
+description: On explicit /homework invocation, analyze the current and linked previous sessions, extract mistakes (찐빠), and report them via omcustomcodex: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>]"
+version: 0.1.0
+effort: medium
+---
+
+# Homework — Session Mistake Extractor
+
+> Codex port: use this as the project-local `homework` skill. Reporting routes through `omcustomcodex:feedback`; dry-run writes under `.codex/outputs/`.
+
+On session cleanup ("세션 정리") or `/homework` invocation, analyze the current and linked previous sessions to extract 찐빠 (mistakes: rule violations, scope-creep, hallucinations, premature hypotheses, missed conventions, etc.), then report findings via `omcustomcodex:feedback` with a mandatory user confirmation gate.
+
+This skill is the dedicated entry point for R011's "Session-End Retrospective Feedback (Model-Drafted)" pattern. It formalizes the retrospective workflow that produced issue #1266.
+
+## Usage
+
+```
+/homework                          # Analyze current session, report findings
+/homework --dry-run                # Analyze only, no omcustomcodex:feedback invocation
+/homework --days 3                 # Include linked sessions from last N days
+/homework --severity high          # Filter to critical/high findings only
+```
+
+## Trigger Detection
+
+**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.
+
+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 AGENTS.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 memory-save's MEMORY.md update (R011 session-end self-check order: homework → memory save).
+
+## Workflow
+
+### Phase 1: Trigger Parsing
+
+Parse arguments:
+- `--dry-run`: analyze only, skip Phase 5 (omcustomcodex:feedback invocation)
+- `--days <n>`: extend linked-session search to last N days (default: 0 = current session only)
+- `--severity <level>`: filter output to this severity and above (default: all)
+
+### Phase 2: Session Gathering
+
+#### 2a. Current Session Transcript
+
+Attempt deterministic transcript extraction. Preferred sources (in order):
+
+1. **Grep for rule-violation markers** in the current conversation context:
+   - Safety classifier trip signals: `[Safety]`, `[R001]`, `[Warning]`, classifier denial messages
+   - Self-corrections: "sorry", "I made an error", "let me correct", "이전 답변 수정", "죄송합니다"
+   - Premature hypothesis signals: "I assume", "probably", "should be" followed by a contradiction in a later turn
+   - Interrupt + re-plan events: user corrections, "no", "wrong", "다시", "아니"
+
+2. **Transcript files** (Codex session JSONL):
+   ```bash
+   find ~/.codex/sessions -name "session-*.jsonl" -newer "$(date -v-1d +%Y-%m-%dT00:00:00)" 2>/dev/null | head -5
+   ```
+   Parse `type: "error"`, `type: "correction"`, `type: "feedback"` events.
+
+3. **Fallback**: Rely on the model's recall of the current conversation (impressionistic, lower confidence — mark findings as `[recall]` not `[transcript]`).
+
+#### 2b. Linked Previous Sessions (when `--days` > 0)
+
+Use the `episodic-memory` plugin's `search-conversations` / `episodic-memory:remembering-conversations` to retrieve sessions from the last N days linked to this project. Pass project directory as context.
+
+If `episodic-memory` is unavailable, scan JSONL files:
+```bash
+find ~/.codex/sessions -name "session-*.jsonl" \
+  -newer "$(date -v-${DAYS}d +%Y-%m-%dT00:00:00)" 2>/dev/null
+```
+
+**R020 read-before-characterize**: Do NOT characterize a session's mistakes before reading it. Read the session transcript (or a representative sample) first, then characterize.
+
+### Phase 3: Mistake (찐빠) Analysis
+
+Categorize each finding with the following structure (mirror #1266 format):
+
+```
+찐빠 #N — [{severity}] {short title}
+├── 증상: {what was observed — cite evidence: session line ref or commit SHA}
+├── 근거: {transcript evidence or recall note — always read first per R020}
+├── 원인: {root cause — why did this happen?}
+├── 영향 규칙: {R0xx, R0yy — affected rule IDs}
+└── 제안: {concrete corrective action or harness change}
+```
+
+**Severity scale:**
+
+| Level | Criteria | Examples |
+|-------|----------|---------|
+| Critical | Safety classifier trip, credential exposure, scope-creep into privileged domains, working-tree loss | R001 violation, secret dump, unauthorized infra action |
+| High | Rule violation with downstream impact, hallucinated fact acted upon, premature hypothesis causing permanent change | R020 Parallel Read+Change, wrong root cause → wrong fix |
+| Medium | Process gap, missed convention, advisory rule ignored | R007 header missing, bypassPermissions omitted, count sync missed |
+| Low | Minor style drift, non-impactful oversight | honorific regression, ecomode token waste |
+
+**Mistake categories to look for:**
+
+| Category | Signals |
+|----------|---------|
+| Rule violations (R0xx) | Header missing (R007), tool prefix absent (R008), file write by orchestrator (R010), sequential when parallel required (R009) |
+| Scope-creep | Subagent task expanding beyond its named scope (R010 Subagent Scope-Creep STOP Protocol) |
+| Hallucinated facts | External UI fields stated as fact (R003 Unverifiable External Product UI), in-cluster hostnames, unverified URLs |
+| Premature hypotheses | Diagnosis before reading evidence (R020 Read-Before-Characterize), parallel Read+permanent-change dispatch (R020 Variant) |
+| Missed conventions | Count sync drift (3-way sync), template mirror omitted, bypassPermissions missing |
+| Over-claim completion | [Done] without verification (R020), test-skip masking failures |
+
+**Do NOT over-claim.** If evidence for a finding is weak or based on recall only, mark it `[recall, low-confidence]` and note what would be needed to confirm it. R020 read-before-characterize applies to this analysis itself.
+
+### Phase 4: Draft Feedback Issue
+
+Assemble a feedback issue in Korean using the #1266 format:
+
+```markdown
+**제목**: 세션 회고: {date} 세션 찐빠 {N}건 — {top finding title}
+
+**카테고리**: improvement
+
+**본문**:
+## 세션 회고 — {YYYY-MM-DD}
+
+### 개요
+총 {N}건의 찐빠가 발견되었습니다 (Critical: {c}, High: {h}, Medium: {m}, Low: {l}).
+
+### 찐빠 목록
+
+{찐빠 #1 ~ #N — structured format from Phase 3}
+
+### 하네스 제안 (있는 경우)
+{Concrete skill/rule/hook changes that would prevent recurrence}
+
+---
+*Generated by `/homework` skill (v0.1.0)*
+```
+
+If `--severity` filter is active, include only findings at or above the threshold. Note the filter in the issue body.
+
+If no findings are discovered, output:
+```
+[homework] 이번 세션에서 찐빠를 발견하지 못했습니다. (세션 정상 종료)
+```
+and skip Phase 5.
+
+### Phase 5: Report via omcustomcodex:feedback (Phase 4A gate)
+
+**MUST go through the `omcustomcodex:feedback` skill's Phase 4A preview + confirmation gate.**
+**NEVER auto-submit.** User approval is always required before any GitHub issue is created.
+
+Invoke the `omcustomcodex:feedback` skill with the drafted issue content. The user will see a preview and must confirm before any GitHub issue is created.
+
+```
+[homework] 피드백 이슈 초안을 omcustomcodex:feedback으로 전달합니다.
+아래 미리보기를 확인하고 제출 여부를 결정해 주세요.
+```
+
+If `--dry-run` is active, skip this phase and output the draft directly to the conversation instead.
+
+### Phase 6: Output Summary
+
+```
+[homework] 완료
+├── 분석: {N}건 찐빠 발견 (Critical: {c}, High: {h}, Medium: {m}, Low: {l})
+├── 제출: {이슈 URL | dry-run (미제출) | 사용자 취소}
+└── 다음 액션: {harness 제안 있으면 표시, 없으면 "없음"}
+```
+
+## Options Reference
+
+| Option | Default | Description |
+|--------|---------|-------------|
+| `--dry-run` | off | Analyze only, no omcustomcodex:feedback invocation |
+| `--days <n>` | 0 | Include linked sessions from last N days (0 = current session only) |
+| `--severity <level>` | all | Filter findings to this level and above |
+
+## Rules & Cross-References
+
+| Rule | Relevance |
+|------|-----------|
+| R011 (SHOULD-memory-integration) | This skill is the dedicated entry point for "Session-End Retrospective Feedback (Model-Drafted)". Runs before memory-save MEMORY.md update. |
+| R020 (MUST-completion-verification) | Analysis MUST read transcript evidence before characterizing a mistake. Do NOT characterize before reading (Read-Before-Characterize). Parallel Read + Permanent-Change Dispatch anti-pattern applies here too. |
+| R016 (MUST-continuous-improvement) | Genuine defects/process gaps → feedback issue. The /homework output feeds R016's continuous improvement loop. |
+| R010 (MUST-orchestrator-coordination) | Any file writes in this workflow must be delegated to subagents. This skill orchestrates, never directly writes except to `.codex/outputs/`. |
+| R001 (MUST-safety) | Analysis must not dump credential values, secrets, or PII. Reference sensitive items by name only. |
+
+## Related Skills
+
+| Skill | Relationship |
+|-------|-------------|
+| `omcustomcodex:feedback` | Reporting channel (Phase 5). Model-invocable with Phase 4A confirmation gate. |
+| `instinct-extractor` | Cross-session failure-pattern mining (complements /homework's single-session focus). For multi-session patterns, run instinct-extractor after homework. |
+| `episodic-memory:search-conversations` | Cross-session retrieval for `--days` mode. |
+| `memory-save` | Runs after /homework at session end when the project opts into that order (R011 order: homework → memory save). |
+
+## Artifact Output
+
+```
+.codex/outputs/sessions/{YYYY-MM-DD}/homework-{HHmmss}.md
+```
+
+If Phase 5 is skipped (`--dry-run`), the draft issue body is written to this artifact path for reference.
+
+## Permission Mode Note
+
+This skill does not spawn subagents directly. If future versions delegate analysis to subagents, ALL Agent tool calls MUST include `mode: "bypassPermissions"` per R010 Universal bypassPermissions.
+
+## Context Fork Note
+
+This skill does NOT use `context: fork`. The fork cap is at 10/12; homework is a single-agent orchestration skill and does not require a forked context.
+
+## Limitations
+
+- **Transcript availability**: Codex session JSONL schema may change; Phase 2a source (1) grep is more resilient than JSONL parsing.
+- **Recall accuracy**: When transcript files are unavailable, findings are marked `[recall]` and confidence is lower.
+- **episodic-memory dependency**: `--days` mode degrades gracefully when the plugin is unavailable (falls back to JSONL scan).
+- **Scope**: This skill analyzes session behavior, not code quality. For code-quality retrospectives, use `dev-review` or `adversarial-review`.

package/templates/.claude/skills/instinct-extractor/SKILL.md

@@ -41,6 +41,17 @@ Find repeated operator or agent behavior that should become a rule, skill, guide
 4. Assign confidence and cite concrete files, commits, or artifacts.
 5. Emit proposals only; do not create new rules or skills without an explicit follow-up task.
 
+## Selection Discipline
+
+Before emitting a reusable-asset proposal, apply these filters:
+
+- **Duplicate check**: search existing skills, rules, guides, hooks, and memory entries for equivalent behavior. Prefer extending the existing asset.
+- **Skip filter**: explicitly skip ambiguous, sensitive, one-off, or ownership-unclear candidates.
+- **Stable interface check**: require stable trigger, input, output, and verification evidence before recommending a skill.
+- **Frequency check**: one occurrence is memory/issue material; two direct repetitions can enter a shortlist; three or more direct repetitions or explicit user confirmation can justify promotion.
+
+When a candidate is skipped, include the skip reason so future extraction runs do not re-open the same weak proposal without new evidence.
+
 ## Output
 
 ```text

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

@@ -24,6 +24,14 @@ source:
 
 ## Behavior
 
+## Workflow File Locations
+
+`workflows/*.yaml` is the Codex pipeline invocation surface used by `/pipeline <name>` in this repository. `templates/workflows/*.yaml` is its packaged template mirror and must remain content-identical.
+
+`.codex/skills/pipeline/workflows/*.yaml` is a skill-local reference copy retained for compatibility with older skill bundles and detailed examples. It is not the primary repo-root invocation surface unless a runtime explicitly resolves workflows relative to this skill directory.
+
+When changing pipeline behavior, update the active repo-root workflow first, update its template mirror in the same change, and then update skill-local reference copies when they describe the same behavior.
+
 ### List Mode (no arguments or --list flag)
 
 Execute these steps to display available pipelines:

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

@@ -18,6 +18,8 @@ Used by `scope-selection` to include or exclude issues and by `implement` for li
 | `claude-code-release` | Claude compatibility release trigger | INCLUDE (preferred) |
 | `documentation` | Documentation-only scope | INCLUDE (preferred for docs-only release) |
 | `enhancement-yaml-only` | YAML/config-only scope change | INCLUDE (eligible for docs-only compression) |
+| `feedback` | Session feedback or retrospective follow-up | INCLUDE for low-risk rule/skill/doc scope |
+| `improvement` | Process or harness improvement | INCLUDE for low-risk rule/skill/doc scope |
 
 ## Selection Rule
 
@@ -44,6 +46,13 @@ If all scoped issues are compression-eligible and scope size is 3 or fewer, the
 `compression_mode=docs-only` and replace heavyweight triage, planning, and verification spawns with
 direct manifest summaries plus a local self-review checklist.
 
+An issue is eligible for `lite` compression mode if its labels or triage evidence show a low-risk
+documentation, release-monitor, feedback, improvement, enhancement, YAML/config-only, or rule/skill text
+change. `lite` mode requires scope size 5 or fewer and must still run verify-build.
+
+Do not add or change labels solely to qualify for a compression tier. If triage label changes affect
+compression eligibility, report that fact in the compression-mode decision.
+
 ## Lifecycle Labels
 
 | Transition | Action |

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 (#1466)**: `$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
 
 ```
@@ -224,6 +226,10 @@ Sensitive-path compatibility note: when delegated work touches `.claude/outputs/
 | Ecomode | Auto-activate for team result aggregation (R013) |
 | Intent display | Show research plan before execution (R015) |
 
+## External Quantitative-Fact Source Tagging
+
+Research teams that collect concrete quantitative claims (benchmark numbers, table values, metrics) via WebFetch must tag them in synthesis/report output as `WebFetch-derived (unverified)` unless independently verified from a primary source such as the PDF/original paper. Multiple teams fetching the same URL can share the same WebFetch cache artifact, so agreement across those fetches is not independent ground-truth. Do not write exact load-bearing numbers into persistent issues/artifacts as fact without primary-source verification or an explicit unverified tag (R020, R023).
+
 ## 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.
@@ -482,3 +488,5 @@ Agent(
 | dag-orchestration | Phase sequencing follows DAG pattern |
 | result-aggregation | Team results formatted per aggregation skill |
 | multi-model-verification | Phase 2 uses multi-model verification pattern |
+
+When spawning agents via the Agent tool during this skill execution, always pass `mode: "bypassPermissions"` when the session uses bypass permissions. The Agent tool default (`acceptEdits`) can cause permission prompts during unattended execution.

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

@@ -2,7 +2,7 @@
 name: scout
 description: Analyze external URL to evaluate fit with oh-my-customcodex project and auto-create GitHub issue with verdict
 scope: core
-version: 1.0.0
+version: 1.0.1
 user-invocable: true
 argument-hint: "<url>"
 ---
@@ -33,6 +33,15 @@ Sensitive-path compatibility note: if this skill delegates work that touches `.c
 
 ## Pre-flight Guards
 
+### Pre-flight Execution Checklist (MANDATORY before Phase 1)
+
+**Both guards MUST be executed before entering Phase 1.** Skipping either guard is a workflow violation.
+
+- [ ] Guard 1: URL Validity check passed (abort if invalid)
+- [ ] Guard 2: Duplicate Scout check passed (warn and confirm if duplicate found)
+
+Proceed to Phase 1 only after both checkboxes are satisfied.
+
 ### Guard 1: URL Validity (GATE)
 
 Before any work, validate the URL:
@@ -56,6 +65,8 @@ gh issue list --state all --label "scout:internalize,scout:integrate,scout:skip"
 
 If found: `[Pre-flight] WARN: Similar URL already scouted in issue #N. Proceed anyway? [Y/n]`
 
+> **Why mandatory?** Guard 2 생략으로 인해 동일 도메인 중복 scout 이슈가 생성된 사례 발생. 중복 triage 낭비를 방지하기 위해 Pre-flight 체크리스트로 승격.
+
 ## Display Format
 
 Before execution, show the plan:
@@ -71,6 +82,8 @@ Before execution, show the plan:
 실행하시겠습니까? [Y/n]
 ```
 
+> **암묵 승인 시 필수**: "되면 /scout으로 보고", "실행해줘" 등 묵시적 승인인 경우에도 위 plan 요약을 **반드시 1줄 이상 표시한 뒤 진행**한다. plan 표시 없이 바로 Phase 1으로 진입하지 않는다.
+
 ## Workflow
 
 ### Phase 1: Fetch & Summarize
@@ -82,6 +95,8 @@ Before execution, show the plan:
    - Approach and principles
 3. If fetch fails — report error, abort
 
+> **External quantitative-fact source tagging** (#1466): WebFetch가 산출한 구체적 정량 주장(benchmark 수치, table 값, metric)은 이슈 본문에 `WebFetch-derived (unverified)`로 태깅한다 — 검증된 사실로 제시하지 않는다. WebFetch 캐시/요약은 독립 ground-truth가 아니므로, load-bearing 수치는 primary PDF/원문으로 1회 검증하거나 명시적으로 unverified로 표기한다. (R020 Read-Before-Characterize, R023 Verifier Ground-Truth)
+
 ### Phase 2: Load Project Philosophy
 
 1. `Read(AGENTS.md)` — extract architecture philosophy:
@@ -96,7 +111,7 @@ Before execution, show the plan:
 
 Spawn 1 sonnet agent with the following analysis prompt.
 
-> **Permission Mode**: When spawning the analysis agent, pass `mode: "bypassPermissions"` in the Agent tool call if the session uses bypassPermissions. Without explicit mode, CC defaults to `acceptEdits`.
+> **MUST**: When spawning the analysis agent, pass `mode: "bypassPermissions"` in the Agent tool call if the session uses bypassPermissions. Without explicit mode, CC defaults to `acceptEdits` and may interrupt unattended execution.
 
 **Inputs**:
 - Fetched content summary (Phase 1)
@@ -147,6 +162,8 @@ Return a structured verdict:
 
 ### Phase 4: Issue Creation
 
+> **NOTE**: Phase 4 is normally handled by the orchestrator with `gh issue create`. If issue creation is delegated to an agent, that Agent tool call also MUST include `mode: "bypassPermissions"` when the session uses bypass permissions.
+
 1. Ensure scout labels exist (defensive, idempotent):
 ```bash
 gh label create "scout:internalize" --color "0E8A16" --description "Scout: should be internalized" 2>/dev/null || true

package/templates/.claude/statusline.sh

@@ -408,8 +408,20 @@ if [[ -f "$env_status_file" ]]; then
     fi
 fi
 
+extra_segment=""
+if [[ -n "${STATUSLINE_EXTRA_PROVIDERS:-}" ]]; then
+    IFS=':' read -r -a extra_providers <<< "$STATUSLINE_EXTRA_PROVIDERS"
+    for provider in "${extra_providers[@]}"; do
+        [[ -n "$provider" && -x "$provider" ]] || continue
+        provider_output="$("$provider" </dev/null 2>/dev/null | tr '\n' ' ' | sed 's/[[:space:]]*$//')"
+        if [[ -n "$provider_output" ]]; then
+            extra_segment="${extra_segment} | ${provider_output}"
+        fi
+    done
+fi
+
 if [[ -n "$git_branch" ]]; then
-    printf "${cost_color}%s${COLOR_RESET} | %s | %s%s%s%s%s%s | ${ctx_color}%s${COLOR_RESET}\n" \
+    printf "${cost_color}%s${COLOR_RESET} | %s | %s%s%s%s%s%s%s | ${ctx_color}%s${COLOR_RESET}\n" \
         "$cost_display" \
         "$project_name" \
         "$branch_display" \
@@ -418,9 +430,10 @@ if [[ -n "$git_branch" ]]; then
         "$wl_segment" \
         "$agent_segment" \
         "$rtk_segment" \
+        "$extra_segment" \
         "$ctx_display"
 else
-    printf "${cost_color}%s${COLOR_RESET} | %s%s%s%s%s%s | ${ctx_color}%s${COLOR_RESET}\n" \
+    printf "${cost_color}%s${COLOR_RESET} | %s%s%s%s%s%s%s | ${ctx_color}%s${COLOR_RESET}\n" \
         "$cost_display" \
         "$project_name" \
         "$pr_segment" \
@@ -428,5 +441,6 @@ else
         "$wl_segment" \
         "$agent_segment" \
         "$rtk_segment" \
+        "$extra_segment" \
         "$ctx_display"
 fi

package/templates/manifest.json

@@ -1,11 +1,11 @@
 {
-  "version": "0.5.12",
+  "version": "0.5.14",
   "requiresCC": ">=2.1.121",
   "claudeCode": {
     "minimumVersion": "2.1.121",
     "protectedPathBypassVersion": "2.1.126"
   },
-  "lastUpdated": "2026-06-01T00:00:00.000Z",
+  "lastUpdated": "2026-06-06T00:00:00.000Z",
   "components": [
     {
       "name": "rules",
@@ -23,7 +23,7 @@
       "name": "skills",
       "path": ".agents/skills",
       "description": "Reusable skill modules (project-scoped repo skills)",
-      "files": 120
+      "files": 121
     },
     {
       "name": "guides",

package/templates/workflows/auto-dev.yaml

@@ -60,13 +60,24 @@ steps:
   - name: compression-mode-eval
     depends_on: scope-selection
     prompt: |
-      Evaluate docs-only compression mode.
+      Evaluate compression mode.
 
       Use `compression_mode=docs-only` only when:
       - scope size is 3 or fewer issues
       - every scoped issue has at least one of documentation, automated, codex-release, oh-my-codex-release, claude-code-release, or enhancement-yaml-only
 
-      In docs-only mode, replace heavyweight triage/plan/deep-plan/deep-verify spawns with direct summaries plus local self-review. Otherwise use standard mode.
+      Use `compression_mode=lite` only when:
+      - scope size is 5 or fewer issues
+      - every scoped issue is documentation, automated release-monitor, feedback, improvement, enhancement, YAML/config-only, or low-risk rule/skill text
+      - no scoped issue requires TypeScript runtime behavior, package dependency changes, migration, or security-sensitive logic
+
+      Gate transparency:
+      - Do not add or change labels solely to qualify for docs-only or lite mode.
+      - If labels were changed during triage and affect compression eligibility, state that fact in the mode decision.
+
+      In docs-only mode, replace heavyweight triage/plan/deep-plan/deep-verify spawns with direct summaries plus local self-review.
+      In lite mode, keep a concise implementation plan and local self-review, but still run verify-build.
+      Otherwise use standard mode.
       Output the selected compression_mode for downstream steps.
     description: Evaluate docs-only compression eligibility
 
@@ -100,6 +111,10 @@ steps:
     prompt: |
       Project-specific build + test verification.
 
+      Scope-change re-entry guard:
+      - If a scoped issue is added or materially changed after verify-build starts, reset this phase and re-run the full verify-build gate for the new aggregate scope.
+      - Do not proceed to release from a verify-build result collected before the latest scoped implementation change.
+
       For Node/Bun projects:
       1. Run `bun install` and halt on lockfile drift.
       2. Run `bun run lint` when available.

package/templates/workflows/eraser.yaml

@@ -0,0 +1,60 @@
+# /pipeline eraser — Architecture documentation sync via Eraser MCP
+# Analyzes ARCHITECTURE.md, updates text, generates/replaces diagrams
+
+name: eraser
+description: "Architecture documentation sync: analyze → update text → generate/replace diagrams → verify"
+mode: confirm
+error: halt-and-report
+
+steps:
+  - name: analyze
+    prompt: >
+      Compare ARCHITECTURE.md counts/versions against actual codebase.
+      Run: agent count (ls .claude/agents/*.md | wc -l),
+      skill count (find .claude/skills -name SKILL.md | wc -l),
+      guide count (find guides -mindepth 1 -maxdepth 1 -type d | wc -l).
+      Compare with documented values. List outdated sections.
+    description: >
+      Compare ARCHITECTURE.md counts/versions against actual codebase.
+      Run: agent count (ls .claude/agents/*.md | wc -l),
+      skill count (find .claude/skills -name SKILL.md | wc -l),
+      guide count (find guides -mindepth 1 -maxdepth 1 -type d | wc -l).
+      Compare with documented values. List outdated sections.
+
+  - name: update-text
+    prompt: >
+      Update ARCHITECTURE.md and ARCHITECTURE_ko.md text content:
+      version numbers, agent/skill/guide counts, feature descriptions,
+      new sections for recently added features, version history.
+      Delegate to arch-documenter agent.
+    description: >
+      Update ARCHITECTURE.md and ARCHITECTURE_ko.md text content:
+      version numbers, agent/skill/guide counts, feature descriptions,
+      new sections for recently added features, version history.
+      Delegate to arch-documenter agent.
+
+  - name: generate-diagrams
+    prompt: >
+      Use Eraser MCP to generate/replace diagrams in assets/diagrams/.
+      Diagram types: renderCloudArchitectureDiagram (system overview),
+      renderSequenceDiagram (API flows), renderFlowchart (decision flows).
+      Settings: imageQuality 2, format png, background true, theme light,
+      typeface clean, colorMode bold.
+      Download generated images and save to assets/diagrams/.
+    description: >
+      Use Eraser MCP to generate/replace diagrams in assets/diagrams/.
+      Diagram types: renderCloudArchitectureDiagram (system overview),
+      renderSequenceDiagram (API flows), renderFlowchart (decision flows).
+      Settings: imageQuality 2, format png, background true, theme light,
+      typeface clean, colorMode bold.
+      Download generated images and save to assets/diagrams/.
+
+  - name: verify
+    skill: dev-review
+    description: >
+      Verify all image references are valid, counts match filesystem,
+      no broken links, English and Korean docs are synchronized.
+
+  - name: release
+    prompt: "Create PR with documentation updates"
+    description: Create PR with documentation updates