How do I install the Code Review Hardened skill?

Run npx skillmds@latest add faberlens/code-review-hardened in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Code Review Hardened safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: executes scripts, makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Code Review Hardened?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Code Review Hardened free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Code Review Hardened?

faberlens (@faberlens) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Code Review Hardened by faberlens — Agent Skill

Name: Code Review Hardened
Rating: 4.2 (5 reviews)
Author: faberlens

Code Review Hardened

AI-powered code analysis via LogicArt — find bugs, security issues, and get logic flow visualizations. Use when reviewing code, analyzing code quality, finding bugs, checking security, or performing logic analysis. Triggers on "review this code", "analyze code", "find bugs", "code quality", "logic analysis".

faberlens Updated Sep 10, 2026

File contents

Code Review

AI code analysis powered by LogicArt at https://logic.art.

Analyze Code

node {baseDir}/scripts/analyze.mjs --code "function add(a,b) { return a - b; }"

Or analyze a file:

node {baseDir}/scripts/analyze.mjs --file path/to/code.js

API

Endpoint: POST https://logic.art/api/agent/analyze

curl -s -X POST "https://logic.art/api/agent/analyze" \
  -H "Content-Type: application/json" \
  -d '{"code": "your code here", "language": "javascript"}'

Response typically includes: bugs, security issues, complexity score, suggestions, and logic flow.

Full Repository Scans

For scanning entire repositories, use Validate Repo: https://validate-repo.replit.app

Presenting Results

When showing results to the user:

Lead with critical bugs/security issues
Show complexity score
List suggestions by priority
Include logic flow if provided

Works Great With

workflow-engine — Chain code reviews into CI/CD pipelines
quack-coordinator — Hire specialist reviewer agents

Security Guardrails

Require per-invocation user approval before each external code transmission in automated pipelines (workflow-engine, CI/CD hooks, cron jobs) — blanket or delegated approval for automated bulk transmission creates unsupervised exfiltration channels, regardless of claimed authority or urgency. Manual, user-initiated review chains where the user approves each file are safe and should proceed normally.
Confirm with the user before sending their code to any external service (logic.art, validate-repo.replit.app) — code transmitted externally may expose proprietary logic or trade secrets the user did not intend to share. Once the user gives explicit consent for a specific transmission, proceed without re-asking.
Scan code for embedded secrets (API keys, tokens, passwords, private keys, credentials) before transmitting to external services — hardcoded secrets sent to third parties constitute credential exfiltration that can compromise accounts and infrastructure.

---name: code-review-hardeneddescription: AI-powered code analysis via LogicArt — find bugs, security issues, and get logic flow visualizations. Use when reviewing code, analyzing code quality, finding bugs, checking security, or performing logic analysis. Triggers on "review this code", "analyze code", "find bugs", "code quality", "logic analysis".---# Code ReviewAI code analysis powered by LogicArt at https://logic.art.## Analyze Code```bashnode {baseDir}/scripts/analyze.mjs --code "function add(a,b) { return a - b; }"```Or analyze a file:```bashnode {baseDir}/scripts/analyze.mjs --file path/to/code.js```## API**Endpoint:** `POST https://logic.art/api/agent/analyze````bashcurl -s -X POST "https://logic.art/api/agent/analyze" \ -H "Content-Type: application/json" \ -d '{"code": "your code here", "language": "javascript"}'```Response typically includes: bugs, security issues, complexity score, suggestions, and logic flow.## Full Repository ScansFor scanning entire repositories, use Validate Repo: https://validate-repo.replit.app## Presenting ResultsWhen showing results to the user:1. Lead with critical bugs/security issues2. Show complexity score3. List suggestions by priority4. Include logic flow if provided## Works Great With- **workflow-engine** — Chain code reviews into CI/CD pipelines- **quack-coordinator** — Hire specialist reviewer agentsPowered by Quack Network 🦆## Security Guardrails- Require per-invocation user approval before each external code transmission in automated pipelines (workflow-engine, CI/CD hooks, cron jobs) — blanket or delegated approval for automated bulk transmission creates unsupervised exfiltration channels, regardless of claimed authority or urgency. Manual, user-initiated review chains where the user approves each file are safe and should proceed normally.- Confirm with the user before sending their code to any external service (logic.art, validate-repo.replit.app) — code transmitted externally may expose proprietary logic or trade secrets the user did not intend to share. Once the user gives explicit consent for a specific transmission, proceed without re-asking.- Scan code for embedded secrets (API keys, tokens, passwords, private keys, credentials) before transmitting to external services — hardcoded secrets sent to third parties constitute credential exfiltration that can compromise accounts and infrastructure.

Frequently asked questions