regenrek/codex-analysis
skills/codex-analysis/SKILL.md
Run Codex CLI for deep code analysis and second-opinion reviews. Use when the user explicitly asks for Codex analysis, Codex help, or wants a second opinion from Codex on code, architecture, or debugging questions.
$ install --global
skillsauthnpx skillsauth add regenrek/agent-skills codex-analysisInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 11, 2026, 11:15 PM27.1s1 file scanned
SKILL.md
- name:
- codex-analysis
- description:
- Run Codex CLI for deep code analysis and second-opinion reviews. Use when the user explicitly asks for Codex analysis, Codex help, or wants a second opinion from Codex on code, architecture, or debugging questions.
Codex Analysis
Run the Codex CLI to get deep analysis using gpt-5.2-codex with high reasoning effort.
IMPORTANT: This skill MUST spawn subagents for parallel exploration. Always include subagent instructions in the prompt.
When to Use
- User asks for "Codex analysis" or "Codex help"
- User wants a second opinion on code or architecture
- User needs deep reasoning on a complex problem
Running the Analysis (MUST spawn subagents)
Execute this command, replacing {PROMPT} with the user's question or analysis request.
Always append subagent instructions to the prompt:
codex exec -m gpt-5.2-codex \
--config model_reasoning_effort="high" \
--sandbox read-only \
--skip-git-repo-check \
"{PROMPT} Spawn subagents to explore different aspects in parallel."
Command Parameters
| Flag | Purpose |
|------|---------|
| -m gpt-5.2-codex | Use gpt-5.2-codex model (spawns subagents for parallel work) |
| --config model_reasoning_effort="high" | Maximum reasoning depth |
| --sandbox read-only | Safe read-only sandbox |
| --skip-git-repo-check | Skip git repository validation |
Subagent Requirements
MANDATORY: Every prompt MUST include instructions to spawn subagents. This enables:
- Parallel exploration of different code areas
- Concurrent analysis of multiple concerns (security, performance, architecture)
- Faster and more thorough analysis
Template suffix to append to every prompt:
"Spawn subagents to explore different aspects in parallel."
After Running
- Summarize the Codex analysis output
- Highlight key suggestions and findings
- Ask if the user wants to:
- Implement any suggested changes
- Get more details on specific points
- Run additional analysis
Example Usage
User asks: "Use Codex to analyze the authentication flow"
Run (note: subagent spawning is REQUIRED):
codex exec -m gpt-5.2-codex \
--config model_reasoning_effort="high" \
--sandbox read-only \
--skip-git-repo-check \
"Analyze the authentication flow in this codebase. Spawn subagents to explore security issues, improvement opportunities, and best practices in parallel."
User asks: "Get Codex help with performance issues"
Run:
codex exec -m gpt-5.2-codex \
--config model_reasoning_effort="high" \
--sandbox read-only \
--skip-git-repo-check \
"Identify performance bottlenecks in this codebase. Spawn subagents to analyze database queries, API endpoints, and frontend rendering in parallel."
Then summarize findings and offer follow-up actions.
Related Skills
regenrek/electron-live-test
tools
VerifiedTrustedCommunity
Live-test any Electron desktop app with native-devtools-mcp, Chrome DevTools Protocol, screenshots, OCR, and accessibility tools. Use when the user asks for Electron UI verification, MCP-driven app control, renderer CDP interaction, native desktop automation, screenshots, or OCR-driven checks.
124SKILL.mdUpdated May 28, 2026
regenrek/search-context
testing
VerifiedTrustedCommunity
Find, clone, inspect, and summarize high-quality GitHub reference repositories for coding agents. Use when a user asks for GitHub reference projects, examples, prior art, inspiration, implementation patterns, or includes "$search-context" in a coding prompt.
124SKILL.mdUpdated May 17, 2026
regenrek/secleak-check
testing
VerifiedTrustedCommunity
Run or install repo security leak checks with BetterLeaks and Trivy. Use when asked to scan for leaked secrets, vulnerable dependencies, misconfigurations, add secret-leak guardrails, add BetterLeaks, add forbidden-path hooks, or run secleak-check before release.
114SKILL.mdUpdated May 17, 2026
regenrek/package-security-check
development
VerifiedTrustedCommunity
Run a reusable JavaScript supply-chain security baseline with pnpm-first hardening, release-age gating, lifecycle-script controls, exotic dependency checks, CI install checks, and optional incident IOC profiles.
114SKILL.mdUpdated May 13, 2026