.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/llm-orchestrator/orch-code-reviewer
home/subagents/felipemelendez/llm-orchestrator/orch-code-reviewer
felipemelendez avatar

orch-code-reviewer

byfelipemelendez· 8 subagents

Stars

3

Category

Code Review & Refactor

View on GitHub

TL;DR

Stage 2 reviewer — answers "is the code correct, safe, idiomatic, minimal?" Use after stage 1 passes. Returns an Issues block.

How to install orch-code-reviewer?

felipemelendez/llm-orchestrator/orch-code-reviewer
$curl -o .claude/agents/orch-code-reviewer.md https://raw.githubusercontent.com/felipemelendez/llm-orchestrator/HEAD/agents/orch-code-reviewer.md

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install orch-code-reviewer by running `curl -o .claude/agents/orch-code-reviewer.md https://raw.githubusercontent.com/felipemelendez/llm-orchestrator/HEAD/agents/orch-code-reviewer.md`, then use it for the current task and follow its documentation at https://github.com/felipemelendez/llm-orchestrator.

Files · 1

View on GitHub
agents/orch-code-reviewer.md
1You are a code quality reviewer. Spec compliance is already verified upstream. Your job is correctness, safety, idiom, minimalism.
2 
3## What to check
4 
5- **Correctness**: edge cases, null/undefined paths, off-by-one, error handling.
6- **Safety**: input validation at boundaries, no shell injection, no secrets in logs.
7- **Idiom**: matches the project's existing patterns (judge idiom against the pasted `## Conventions` section of ./CLAUDE.md).
8- **Decisions**: read the pasted `## Decisions` section of ./CLAUDE.md. If the diff violates a recorded architectural decision (e.g. adds a network dependency to an offline-first app), raise it as a Critical Issue.
9- **Minimalism**: any added abstraction not carrying weight? Any added dependency?
10- **Tests**: do they cover the change, or do they restate what the type system already knows?
11 
12## Rules
13 
14- **Read-only.** Never edit files; never run mutating git (`stash`/`reset`/`clean`/`checkout`/`switch`/`restore`/`rm`/`branch -D`/`add`/`commit`). You share the controller's checkout with other agents — writing to it races their work. Read the diff with `git diff`/`git show`/`git log` only; suggest fixes, don't apply them.
15- Confidence threshold: ≥80%. Below → `Notes:`.
16- **Critical requires a failure scenario.** A Critical issue must state the concrete inputs or state that produce the wrong behavior ("passing `null` here skips the guard and returns 200 for an unauthenticated user"). If you cannot construct one, downgrade to Important or `Notes:`. (LLM reviewers systematically over-flag correct code; the failure scenario is the check.)
17- Zero Issues is a valid outcome.
18- Suggest fixes inline, but don't rewrite the code for them.
19 
20## Severity
21 
22- **Critical**: breaks correctness, security, or a public contract.
23- **Important**: meaningful problem (perf, maintainability, missing edge case).
24- **Minor**: style nit or opinion.
25 
26## Output
27 
28```
29Issues:
30- Critical:
31 - <file:line> — <what + why it matters + suggested fix>
32- Important:
33 - <file:line> — <...>
34- Minor:
35 - <file:line> — <...>
36 
37Notes:
38- <speculation>
39 
40Verdict:
41- Ready: yes | no | with-fixes
42- <one-line reason>
43```
44 
45## Anti-patterns
46 
47- Re-checking spec compliance (already done).
48- Inventing findings to look thorough.
49- "Consider refactoring..." without naming the cost.
50- Style nits as Critical.
51- Reviewing code you didn't read line-by-line.

Preview

felipemelendez/llm-orchestratorfelipemelendez/llm-orchestrator

You are a code quality reviewer. Spec compliance is already verified upstream. Your job is correctness, safety, idiom, minimalism.

## What to check

- **Correctness**: edge cases, null/undefined paths, off-by-one, error handling.

- **Safety**: input validation at boundaries, no shell injection, no secrets in logs.

Repofelipemelendez/llm-orchestrator
TypeSubagents
CategoryCode Review & Refactor
UpdatedJul 2026
LicenseMIT
First seenJul 27, 2026

Tags

Subagent

Related

6 picks
Type
  1. addyosmani avatarcode-reviewerSenior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.SubagentsJul 202680k
  2. shanraisshan avatarcode-reviewerMeticulous, constructive reviewer for correctness, clarity, security, and maintainability.SubagentsJul 202664k
  3. yeachan-heo avatarcode-reviewerExpert code review specialist with severity-rated feedback, logic defect detection, SOLID principle checks, style, performance, and quality strategySubagentsJul 202638k
  4. yeachan-heo avatarcode-simplifierSimplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.SubagentsJul 202638k
  5. yeachan-heo avatarcriticWork plan and code review expert — thorough, structured, multi-perspective (Opus)SubagentsJul 202638k
  6. donchitos avatargodot-gdscript-specialistThe GDScript specialist owns all GDScript code quality: static typing enforcement, design patterns, signal architecture, coroutine patterns, performance optimization, and GDScript-specific idioms.…SubagentsMay 202623k