feat: check under- and over-logging in the code review gate

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>

assets/agents/code-reviewer/config.yaml

@@ -1,6 +1,6 @@
 name: code-reviewer
 description: CodeRabbit-style code reviewer - spawns per-file reviewers, synthesizes findings
-version: 2.2.0
+version: 2.3.0
 
 auto_continue: true
 max_auto_continues: 20
@@ -76,6 +76,7 @@ instructions: |
   ## MUST DO
   - Load `code-review` and `ai-slop-remover` skills before reading any code
   - Load `transactional-integrity` as well if this file's diff touches state-changing code (DB writes, transactions, queue/webhook/job handlers, retries, external side effects)
+  - Load `logging-discipline` as well if this file's diff touches boundaries, error paths, background jobs, or state transitions
   - Apply all loaded skill checklists to the diff
   - Use targeted fs_read with offset/limit; max 5 file reads
   - End with REVIEW_COMPLETE

assets/agents/file-reviewer/config.yaml

@@ -1,12 +1,13 @@
 name: file-reviewer
 description: Reviews a single file's diff for bugs, style issues, and cross-cutting concerns
-version: 2.1.0
+version: 2.2.0
 
 skills_enabled: true
 enabled_skills:
   - code-review
   - ai-slop-remover
   - transactional-integrity
+  - logging-discipline
 
 variables:
   - name: project_dir
@@ -32,6 +33,8 @@ instructions: |
 
   Additionally load `transactional-integrity` when the diff touches state-changing code — database writes, transaction blocks, queue/webhook/job handlers, retry logic, or calls to external state-holding systems. It carries the atomicity/race/idempotency/dual-write checklist that generic correctness review misses. Skip it for pure reads, UI, and stateless computation.
 
+  Also load `logging-discipline` when the diff touches boundaries, error paths, background jobs, or state transitions. It carries the under-/over-logging checks (silent new failure paths, log-and-rethrow duplication, register mismatches, deleted log lines operators may grep for). Skip it for diffs with no operational surface.
+
   Apply every loaded checklist in every review. Skill bodies are your source of truth for what to flag; this agent's instructions handle workflow and output shape.
 
   ## Your Mission