The Code Review Bundle
Skills bundle for advanced code review and testing
Works with any agent that signs in to Agensi, such as Claude, ChatGPT, Claude Code, Cursor and Codex CLI.
One payment, lifetime access. 17 skills unlock instantly in your library.
What's included
17 skillsAutomated git diff auditor that catches leaked secrets, debug code, and missing tests before your pull request.
Identify and remove unused variables, functions, exports, and orphan files across Python and JS/TS projects.
Extract engineering metrics, bus factor risks, and code hotspots from git history.
Static WCAG 2.2 accessibility auditor for HTML, JSX, Vue, and Svelte templates.
Automated Python code modernization for f-strings, type hints, and legacy syntax patterns.
Build, test, and audit regular expressions for ReDoS risks and cross-language portability.
Project LLM API costs and token usage by analyzing prompts, datasets, and traffic volumes.
Audit CSS for unused selectors, high specificity, and inconsistent design tokens across web frameworks.
Profile CSV/JSONL files for data quality, PII, and statistics while generating SQL schemas and HTML reports.
Analyze npm and Python dependencies to generate risk-aware, batched upgrade plans with live registry data.
Detect exact and near-duplicate code clones across any codebase with normalization and CI gate support.
Security audit and threat modeling tool for LLM agents and RAG systems based on the OWASP Top 10 (2025).
Evaluate LLM prompts and models with repeatable test suites, semantic checks, and statistical comparisons.
Automated SQL migration generator for diffing schemas and creating safe, dialect-specific up/down scripts.
Identify untested code and high-risk gaps via static analysis of source symbols and test references.
Identifies recurring support issues and transforms resolved tickets into PII-scrubbed knowledge base articles.
Statically deobfuscate malicious PowerShell commands and extract IOCs without execution.
See it in action
Code Review Aid
Example session with this skill installed
Run a code review on my staged changes. I have modified a user authentication controller and added a new database migration.
- Read your context and instructions
- Compiled the code review aid
I have analyzed the staged changes in your repository. The diff includes 3 files with approximately 140 lines of code.
Code Review Report
| Category | Finding | Severity |
|---|---|---|
| Security | Hard-coded internal URL detected in auth_controller.rb:42 | High |
| Hygiene | Leftover console.log(user_data) found in session_helper.js:12 | Low |
| Architecture | Large function validate_and_reconcile_session (62 lines) exceeds recommended limit | Med |
| Testing | Source auth_controller.rb changed, but no matching files in /spec found | High |
| Risk | Schema migration 20231027_add_role_to_users.rb modifies a core table | Med |
Inline Comments
auth_controller.rb:42
endpoint = "http://internal.dev.auth.service/v1"
Suggestion: Move this URL to an environment variable or credentials encrypted file to avoid hard-coding environment-specific endpoints.
session_helper.js:12
console.log("Debug session:", data);
Suggestion: Remove debug statements before merging to production.
20231027_add_role_to_users.rb
Caution: This migration adds a column to the users table. Ensure you have checked for potential table locking if this table has millions of rows.
Next steps
- Remove the debug
console.logand move the auth URL toconfig/settings.yml. - Add a unit test in
spec/controllers/auth_controller_spec.rbto cover the new logic. - Verify the migration execution time on a staging database clone.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads these skills and uses them on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every skill in this bundle goes through our trust checks.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.