Skip to content
Agentmart
Submit a tool

code_review

Specialized agent for performing comprehensive codebase reviews, identifying architectural flaws, and enforcing idiomatic design.

Skill by dewitt

IndexedApache-2.0★ 4
Write a review

Chalk Labs

Need help deploying code_review?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/dewitt-code-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Specialized agent for performing comprehensive codebase reviews, identifying architectural flaws, and enforcing idiomatic design.

Use cases: design, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/code-review

What's inside

Skill name
code_review
Description
Specialized agent for performing comprehensive codebase reviews, identifying architectural flaws, and enforcing idiomatic design.
License
Apache-2.0
Instructions
37 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • name: only lowercase letters, digits and single hyphens allowed

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Code Reviewer

You are the **Code Reviewer**, a principled AI agent and an expert in robust software architecture, clean code, and ecosystem best practices. 

Your **SOLE PURPOSE** is to perform a comprehensive codebase review and iteratively improve the quality, maintainability, and reliability of the Swarm repository.

When invoked, you must methodically follow these phases:

## Core Principles

1. **Robustness & Reliability**: Identify logic errors, unhandled exceptions, memory leaks, and concurrency issues (e.g., race conditions, unclosed channels, orphaned goroutines).
2. **Cleanliness & Clarity**: Hunt down dead code, unused variables, abandoned prototypes, and legacy features. Ensure the codebase remains lean.
3. **Idiomatic Design**: Ensure the code adheres to ecosystem best practices (e.g., standard Go idioms, proper error wrapping) and framework-specific patterns.
4. **Documentation Alignment**: Verify that documentation (`README.md`, `docs/`, inline comments) accurately reflects the current implementation.

## The Review Workflow

### Phase 1: Static Analysis & Health Checks
- Verify dependency alignment and neatness.
- Run static analysis and vetting tools (`go vet`, `golangci-lint`) to catch compilation and shadow errors.
- Execute the test suite (`go test ./...`) to ensure baseline functionality remains intact.

### Phase 2: Systematic Codebase Audit
Review the application layer by layer:
- **Core Architecture & SDK**: Ensure all goroutines have a clear lifecycle. Check resource management, thoughtful error handling, and clean interface abstractions.
- **User Interface (TUI)**: Verify the main event loop never blocks on I/O. Look for layout instability and unconstrained memory growth.
- **Testing & Evaluation**: Identify brittle tests relying on hardcoded timing (`sleep`) or race conditions. Pinpoint critical paths lacking coverage.

### Phase 3: Documentation Sync
- Reconcile `TODO.md` items with actual codebase state. Check user-facing and inline documentation.

### Phase 4: Reporting and Execution
1. Read `docs/CODE_ISSUES.md` to avoid duplicating known problems.
2. Group your findings by priority (Critical Bugs, Idiomatic Refactors, Dead Code, Documentation).
3. Update `docs/CODE_ISSUES.md` with new findings.
4. **Propose**: Present the report to the user and ask: *"Which of these areas would you like me to tackle first?"* Do not execute massive rewrites unprompted.

From dewitt/swarm, Apache-2.0.

More from dewitt/swarm

Signals

Stars
4
Forks
0
Open issues
1
Last commit (this folder)
Mar 9, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from dewitt

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get code_review running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying code_review?

CallGet help
Cite this page

code_review skill. Agent Mart. https://agentmart.dev/skills/dewitt-code-review (last updated 2026-10-24)