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>
This commit is contained in:
2026-08-25 13:19:09 -06:00
co-authored by Sisyphus
parent 9e652f7801
commit 5a32219178
2 changed files with 6 additions and 2 deletions
+2 -1
View File
@@ -1,6 +1,6 @@
name: code-reviewer name: code-reviewer
description: CodeRabbit-style code reviewer - spawns per-file reviewers, synthesizes findings description: CodeRabbit-style code reviewer - spawns per-file reviewers, synthesizes findings
version: 2.2.0 version: 2.3.0
auto_continue: true auto_continue: true
max_auto_continues: 20 max_auto_continues: 20
@@ -76,6 +76,7 @@ instructions: |
## MUST DO ## MUST DO
- Load `code-review` and `ai-slop-remover` skills before reading any code - 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 `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 - Apply all loaded skill checklists to the diff
- Use targeted fs_read with offset/limit; max 5 file reads - Use targeted fs_read with offset/limit; max 5 file reads
- End with REVIEW_COMPLETE - End with REVIEW_COMPLETE
+4 -1
View File
@@ -1,12 +1,13 @@
name: file-reviewer name: file-reviewer
description: Reviews a single file's diff for bugs, style issues, and cross-cutting concerns 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 skills_enabled: true
enabled_skills: enabled_skills:
- code-review - code-review
- ai-slop-remover - ai-slop-remover
- transactional-integrity - transactional-integrity
- logging-discipline
variables: variables:
- name: project_dir - 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. 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. 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 ## Your Mission