aromanarguello/codex
codex/SKILL.md
Use when user wants to delegate a task to OpenAI Codex CLI. Triggers on "ask codex", "have codex", "codex:", "send to codex", "let codex", "run codex". Delegates via subagent to keep main context clean.
$ install --global
skillsauthnpx skillsauth add aromanarguello/roman-skills codexInstall 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: May 6, 2026, 3:09 AM128.7s1 file scanned
SKILL.md
- name:
- codex
- description:
- Use when user wants to delegate a task to OpenAI Codex CLI. Triggers on "ask codex", "have codex", "codex:", "send to codex", "let codex", "run codex". Delegates via subagent to keep main context clean.
Codex Delegation
Delegate tasks to OpenAI's Codex CLI via a subagent. Codex runs non-interactively and results are summarized back.
Routing
Is this a code review request?
│
┌────┴────┐
yes no
│ │
▼ ▼
codex codex exec
review --sandbox read-only
Execution
Dispatch a single Bash subagent (Task tool) with the appropriate command. This keeps all Codex output isolated from the main context window.
For code reviews
Use codex review which has specialized review behavior:
Task tool:
subagent_type: Bash
model: haiku
description: "Codex review"
prompt: |
Run this command and return the full output:
codex review {FLAGS} "{INSTRUCTIONS}" -o /tmp/codex-out.txt 2>/dev/null; cat /tmp/codex-out.txt
Flags:
- --uncommitted → review staged/unstaged/untracked changes
- --base BRANCH → review changes against a base branch
- --commit SHA → review a specific commit
Default to --uncommitted if user didn't specify.
Return the complete review output.
For everything else
Use codex exec in read-only sandbox:
Task tool:
subagent_type: Bash
model: haiku
description: "Codex: {brief task}"
prompt: |
Run this command and return the full output:
codex exec "{USER_PROMPT}" --sandbox read-only -C "{WORKING_DIR}" -o /tmp/codex-out.txt 2>/dev/null; cat /tmp/codex-out.txt
Return the complete output.
If user wants Codex to make changes
User must explicitly ask for write access. Use --sandbox workspace-write instead of read-only:
codex exec "{PROMPT}" --sandbox workspace-write -C "{WORKING_DIR}" -o /tmp/codex-out.txt 2>/dev/null; cat /tmp/codex-out.txt
After Subagent Returns
- Read the subagent's output
- Present a concise summary to the user
- Include key findings, recommendations, or answers
- Mention if Codex flagged any critical issues (P0/P1)
Quick Reference
| User Says | Route To | Flags |
|-----------|----------|-------|
| "ask codex to review" | codex review | --uncommitted |
| "codex review against main" | codex review | --base main |
| "codex review commit abc123" | codex review | --commit abc123 |
| "ask codex to analyze/explain/plan" | codex exec | --sandbox read-only |
| "have codex fix/refactor/implement" | codex exec | --sandbox workspace-write |
Common Mistakes
| Mistake | Fix |
|---------|-----|
| Running codex in main context | Always use a Bash subagent via Task tool |
| Forgetting 2>/dev/null | Codex thinking tokens flood context without this |
| Forgetting -o flag | Without it, output mixes with metadata noise |
| Using interactive mode | Always use codex exec or codex review, never bare codex |
| Hardcoding model | Let user's codex config choose the model |
Related Skills
aromanarguello/grill-me
development
VerifiedTrustedCommunity
Use when the user wants to brainstorm, stress-test, sharpen a plan, explore options, decide what to build, or says "grill me", "/grill-me", "help me think through", "sharpen this idea", or "what should I build".
6SKILL.mdUpdated May 15, 2026
aromanarguello/techdebt
development
VerifiedTrustedCommunity
Use at end of coding sessions to find and eliminate duplicated code, dead code, and unnecessary abstractions. Also use when codebase feels cluttered or when you suspect copy-paste patterns have accumulated.
6SKILL.mdUpdated May 6, 2026
aromanarguello/parallel-subagents
development
VerifiedTrustedCommunity
Use when you have 2+ independent tasks to run concurrently without a formal plan. Triggers on "parallel research", "parallel subagents", "explore in parallel", "investigate multiple", "run tests in parallel". NOT for plan execution (use subagent-driven-development instead)
6SKILL.mdUpdated May 6, 2026
aromanarguello/final-review
testing
VerifiedTrustedCommunity
Pre-merge review that runs PR quality, tech debt, security, regression, and performance analysis in parallel via general-purpose agents, aggregates findings into a unified prioritized report, then auto-fixes mechanical issues. Use when the user says "final review", "pre-merge review", "run all reviews", or wants a comprehensive check before merging. Defaults to all reviewers; accepts args to run a subset (e.g., `/final-review security techdebt`).
6SKILL.mdUpdated May 6, 2026