Imlazy code review
Token-efficient tier-routed agent orchestrator 40+ skills, 19 agents, Obsidian vault. Works with Claude Code, OpenCode, Codex CLI.
npx -y skills add hnikoloski/imlazy --skill imlazy-code-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 26 days oldThe repository was created 26 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Two roles — request a code review (dispatch reviewer subagent) and receive a code review (process feedback rigorously). Use after each task in planning full mode, before merge, or when stuck
SKILL.md
2.3 KB, as published. Nobody here has run it
code-review
When to use
- After each task in
planning(full mode) - Before merging a feature
- When stuck (fresh perspective unblocks you)
- After fixing a complex bug
Requesting a review
Step 1: Get git SHAs
BASE_SHA=$(git rev-parse HEAD~1) # or origin/main for pre-merge review
HEAD_SHA=$(git rev-parse HEAD)
Step 2: Dispatch code reviewer subagent using the template at code-reviewer.md (next to this skill). Fill in:
{DESCRIPTION}— brief summary of what was built{PLAN_OR_REQUIREMENTS}— what it should do{BASE_SHA}/{HEAD_SHA}— the commit range{GIT_DIFF}— output ofgit diff BASE_SHA..HEAD_SHA
Step 3: Act on feedback
- Critical → fix immediately, re-review
- Important → fix before proceeding
- Minor → note for later
- Reviewer is wrong → push back with technical reasoning and evidence; don't blind-implement
Never skip review because "it's simple". Never ignore Critical issues. Never proceed with unfixed Important issues.
Receiving a review
When you receive code review feedback, apply this process before implementing anything:
-
Verify the feedback is technically correct. Read the cited file and line. Does the issue actually exist there?
-
Distinguish severity. Critical issues block progress. Important issues should be fixed. Minor issues are optional. If the reviewer didn't label severity, ask for clarification.
-
Never blind-implement Critical feedback without checking it first. A reviewer can be wrong. If something feels off, verify with a test or look at the actual code.
-
Push back when the reviewer is wrong. "The test at line 42 already covers that edge case — here is the assertion: [paste test]." Technical evidence beats assertion.
-
Fix, then re-request review. Don't mark "fixed" without actually running the test suite.
Common pitfalls:
- Implementing all feedback without verifying — can introduce new bugs
- Dismissing feedback without checking — misses real issues
- Treating Minor as Critical — wastes time on low-impact polish