oh-my-customcode 0.169.0 → 0.171.0

package/README.md

@@ -213,7 +213,7 @@ All commands are invoked inside the Claude Code conversation.
 | Priority | Count | Purpose |
 |----------|-------|---------|
 | **MUST** | 14 | Safety, permissions, agent design, identification, orchestration, verification, completion, enforcement |
-| **SHOULD** | 6 | Interaction, error handling, memory, HUD, ecomode, ontology routing |
+| **SHOULD** | 8 | Interaction, error handling, memory, HUD, ecomode, ontology routing, wiki sync, verification ladder |
 | **MAY** | 1 | Optimization |
 
 Key rules: R010 (orchestrator never writes files), R009 (parallel execution mandatory), R017 (sauron verification before push), R020 (completion verification before declaring done), R021 (advisory-first enforcement model).
@@ -271,7 +271,7 @@ your-project/
 ├── .claude/
 │   ├── agents/                 # 49 agent definitions
 │   ├── skills/                 # 116 skill modules
-│   ├── rules/                  # 22 governance rules (R000-R021)
+│   ├── rules/                  # 23 governance rules (R000-R023)
 │   ├── hooks/                  # 15 lifecycle hook scripts
 │   ├── schemas/                # Tool input validation schemas
 │   ├── specs/                  # Extracted canonical specs

package/dist/cli/index.js

@@ -241,7 +241,7 @@ var init_package = __esm(() => {
     workspaces: [
       "packages/*"
     ],
-    version: "0.169.0",
+    version: "0.171.0",
     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: "0.169.0",
+  version: "0.171.0",
   description: "Batteries-included agent harness for Claude Code",
   type: "module",
   bin: {

package/package.json

@@ -3,7 +3,7 @@
   "workspaces": [
     "packages/*"
   ],
-  "version": "0.169.0",
+  "version": "0.171.0",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {

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

@@ -90,7 +90,7 @@
             "command": "bash .claude/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 \"git (reset|clean|checkout|restore|switch|rebase|merge)\"",

package/templates/.claude/rules/MAY-optimization.md

@@ -10,6 +10,8 @@
 | Caching | Same data accessed repeatedly | Cache file contents, reuse search results |
 | Lazy Loading | Large datasets, partial use | Read only needed files, stream results |
 
+> **Tool-availability assumption (#1307 찐빠 #3)**: On first exploration, do NOT assume a tool (e.g., `Glob`) is available without confirming. Prefer `Bash` (`find`/`grep`) for initial search when the available-tool set is unconfirmed, to avoid "No such tool available" round-trips.
+
 ### Capability-Aware Tool Scheduling
 
 When dispatching parallel tool calls, consider per-tool capabilities to optimize scheduling:

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

@@ -356,6 +356,8 @@ description: Brief desc    # One-line summary
 
 Key optional fields: `scope`, `context`, `version`, `effort`, `model`, `agent`, `hooks`, `paths`, `shell`, `allowed-tools`, `keep-coding-instructions`. Skill `effort` takes precedence over agent `effort` when both specified. See full optional fields via Read tool.
 
+> **v2.1.163+**: In skill `command` bodies, use `\$` to emit a literal `$` before a number (e.g., `\$1`) — previously ambiguous with shell variable expansion. Relevant when authoring skills with `shell:` or inline command steps that include dollar signs not intended as variables.
+
 <!-- DETAIL: Skill Optional Fields (full yaml block)
 ```yaml
 scope: core                # core | harness | package (default: core)

package/templates/.claude/rules/MUST-enforcement-policy.md

@@ -17,6 +17,8 @@ oh-my-customcode uses an **advisory-first enforcement model**. Most rules are en
 | Advisory (proactive) | UserPromptSubmit hook | R007, R008 (`r007-r008-drift-advisor.sh`, #1229) | Reads last assistant turn; emits stderr advisory before next response if header/prefix absent. Complements retroactive Stop-hook (`session-reflection.sh`, #1190). |
 | Prompt-based | CLAUDE.md + rules/ + PostCompact | All MUST rules | Behavioral guidance in context |
 
+> **v2.1.163+**: Stop and SubagentStop hooks can return `hookSpecificOutput.additionalContext` (JSON) to feed structured feedback back into Claude's context without triggering a hook error label. This enables advisory-style enforcement via Stop/SubagentStop hooks (e.g., `session-reflection.sh`, omcustom-loop SubagentStop) to pass richer context — replacing plain stderr text — without disrupting the turn continuation behavior that advisory-first enforcement relies on.
+
 ## Why Advisory-First
 
 1. **Agent flexibility**: Hard blocks can trap agents in unrecoverable states

package/templates/.claude/rules/MUST-safety.md

@@ -25,6 +25,21 @@ The following git commands have caused working tree loss in past sessions (#1146
 
 **Recovery hint**: If working tree loss occurs, check `git reflog` immediately — most operations are recoverable within 30 days.
 
+### Pre-Delegation Blast-Radius Enumeration
+
+> Origin: #1307 찐빠 #1 (High) — user chose "discard local changes and pull", and `git reset --hard origin/develop` was delegated immediately → user rejected (interrupt). The blast radius — that "discard local changes" included 18 files of *intended* uncommitted work (rule edits, new skills, new guides), not just a version downgrade — was never enumerated for the user.
+
+Before delegating ANY destructive git command (the table above), the orchestrator MUST first enumerate the EXACT discard targets and present them for explicit approval. Do NOT delegate a destructive git op on a paraphrased intent ("로컬 변경 버리기" / "discard local changes") without showing what will actually be lost.
+
+| Required before delegation | Command |
+|----------------------------|---------|
+| List modified/staged tracked files | `git status --short` |
+| Show uncommitted diff scope | `git diff --stat` (and `git diff --stat --cached`) |
+| Show stashable work scope | `git stash show --stat` (when a stash is involved) |
+| Show untracked files at risk (for `clean`) | `git clean -nd` |
+
+Enumerate ALL affected work — intended uncommitted edits (rule changes, new skills/guides) count too, not just the symptom the user named. Prefer a non-destructive alternative (`git stash`) when the user's goal (e.g., "reach remote state") can be met without permanent loss.
+
 ## Credential & Privileged-Scope Guardrails
 
 > Origin: #1266 ① (Critical) — a subagent dumped `.env` and Gmail OAuth credentials into the transcript (Credential Exploration) and ran an unauthorized credential-rotation flow that caused a dashboard data outage.

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

@@ -364,6 +364,19 @@ Related records from session v0.87.2~v0.88.0 (issue #869):
 - `feedback_bun_mock_module.md`
 -->
 
+## Safety-Related Feedback Memory Framing
+
+> Origin: #1307 찐빠 #2 (Medium) — a sys-memory-keeper delegation prompt framed a learning as "오탐으로 판단하고 진행한다" (conclude it's a false positive and proceed), tripping the memory-poisoning safety classifier and requiring a rewrite.
+
+Safety-related feedback memories MUST be written in **verification-obligation form**, NOT **conclusion form**. Conclusion-form framing ("ignore the warning and proceed", "오탐이므로 무시") risks future sessions ignoring genuine threat warnings (memory-poisoning).
+
+| Anti-pattern (conclusion form) | Required (verification-obligation form) |
+|--------------------------------|------------------------------------------|
+| "이 경고는 오탐이므로 무시하고 진행" | "이 패턴은 X 검증을 트리거; 검증 통과 시에만 진행, 실패 시 STOP" |
+| "warning is false positive, proceed" | "warning triggers a duty to verify Y; proceed only if verified, else STOP" |
+
+Write safety learnings as triggers (what to check) + STOP conditions (when to halt), never as standing permission to dismiss a class of warnings.
+
 ## Session-End Auto-Save
 
 ### Trigger

package/templates/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "0.169.0",
+  "version": "0.171.0",
   "lastUpdated": "2026-05-20T00:00:00.000Z",
   "omcustomMinClaudeCode": "2.1.121",
   "omcustomMinClaudeCodeReason": "Sensitive-path direct Write/Edit on .claude/** under bypassPermissions (R010 deprecation, #1101)",