Stats
Actions
Tags
From dream-team
Delegates repetitive coding tasks (code generation, refactoring, analysis) to Codex CLI via JetBrains AI. Useful for bulk operations across many files.
How this skill is triggered — by the user, by Claude, or both
Slash command
/dream-team:codexThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use Codex CLI to delegate coding tasks that benefit from parallel AI processing.
Use Codex CLI to delegate coding tasks that benefit from parallel AI processing.
GOOD for Codex:
KEEP in Claude:
Codex is pre-configured with JetBrains AI staging:
jbai-staginggpt-4o-2024-11-20, o1-2024-12-17, o3-mini-2025-01-31codex exec -c model_provider=jbai-staging --model "gpt-4o-2024-11-20" \
--sandbox read-only \
"Analyze the codebase and list all REST endpoints" 2>/dev/null
codex exec -c model_provider=jbai-staging --model "gpt-4o-2024-11-20" \
--sandbox workspace-write --full-auto \
"Generate unit tests for UserService.kt" 2>/dev/null
codex exec -c model_provider=jbai-staging --model "o3-mini-2025-01-31" \
--sandbox read-only \
"Review security vulnerabilities in auth module" 2>/dev/null
echo "continue with the refactoring" | codex exec --skip-git-repo-check resume --last 2>/dev/null
Before delegating to Codex, consider:
| Factor | Use Codex | Keep in Claude |
|---|---|---|
| File count | Many files | Few files |
| Task type | Repetitive/mechanical | Creative/strategic |
| Context needed | Self-contained | Requires conversation context |
| User interaction | None needed | Back-and-forth required |
gpt-4o-2024-11-20 for fast taskso1-2024-12-17 / o3-mini-2025-01-31 for complex reasoningread-only for analysisworkspace-write for edits2>/dev/null to suppress thinking tokens--skip-git-repo-check flagread-only sandbox unless edits neededdanger-full-access without explicit user permission2>/dev/null by defaultnpx claudepluginhub joshuarweaver/cascade-ai-ml-agents-misc-1 --plugin ashchupliak-dream-teamCreates, edits, and verifies skills using a test-driven development approach with pressure scenarios and subagents.