메뉴
Codex CLI sub-agent for dispatching tasks to OpenAI-compatible models via the `codex` binary. Use for code-focused tasks routed to GPT-5 Codex or any OpenAI-compatible endpoint. Part of the run_agent.py multi-LLM task router — cli=codex target.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
(Industry standard: Parallel Agent) Primary Use Case: Work that can be partitioned into independent sub-tasks running concurrently across multiple agents. Parallel multi-agent execution pattern. Use when: work can be partitioned into independent tasks that N agents can execute simultaneously across worktrees. Includes routing (sequential vs parallel), merge verification, and correction loops.
(Industry standard: Sequential Agent / Agent as a Tool) Primary Use Case: Delegating a well-defined task to a worker agent, verifying its execution, and repeating if necessary. Inner/outer agent delegation pattern. Use when: work needs to be delegated from a strategic controller (Outer Loop) to a tactical executor (Inner Loop) via strategy packets, with verification and correction loops.
(Industry standard: Loop Agent / Single Agent) Primary Use Case: Self-contained research, content generation, and exploration where no inner delegation is required. Self-directed research and knowledge capture loop. Use when: starting a session (Orientation), performing research (Synthesis), or closing a session (Seal, Persist, Retrospective). Ensures knowledge survives across isolated agent sessions.
(Industry standard: Routing Agent / Orchestrator Pattern) Primary Use Case: Analyzing an ambiguous trigger and routing it to one of the specific specialized implementations. Routes triggers to the appropriate agent-loop pattern. Use when: assessing a task, research need, or work assignment and deciding whether to run a simple learning loop, red team review, dual-loop delegation, or parallel swarm. Manages shared closure (seal, persist, retrospective, self-improvement).
(Industry standard: Review and Critique Pattern) Primary Use Case: Iterative generation paired with adversarial review, continuing until an 'Approved' verdict is reached. Orchestrated adversarial review loop. Use when: research, designs, architectures, or decisions need to be reviewed by red team agents (human, browser, or CLI). Iterates in rounds of research → bundle → review → feedback until approved.
(Industry standard: Meta-Learning System / Automated Autoresearch) Primary Use Case: Continuous, self-improving orchestration of an agentic system over multiple sessions. Use when: building a continuous improvement layer that autonomously identifies workflow friction, postulates hypotheses, and tests improved instructions/coding skills against an objective headless benchmark before merging and persisting.
| name | codex-cli-agent |
| plugin | cli-agents |
| description | Codex CLI sub-agent for dispatching tasks to OpenAI-compatible models via the `codex` binary. Use for code-focused tasks routed to GPT-5 Codex or any OpenAI-compatible endpoint. Part of the run_agent.py multi-LLM task router — cli=codex target. |
| allowed-tools | Bash, Read, Write |
Dispatches bounded tasks to the Codex CLI (codex binary). Uses the run_agent.py task router with cli=codex.
[!IMPORTANT] Default model:
gpt-5-codex. RequiresOPENAI_API_KEYin environment. Thecodexbinary must be on PATH.
run_agent.pypython ./scripts/run_agent.py \
<PERSONA_FILE> <INPUT_FILE> <OUTPUT_FILE> "<INSTRUCTION>" \
--cli codex --model gpt-5-codex
The prompt is piped to codex exec via stdin — not passed as a positional arg — to avoid OS ARG_MAX limits and process listing exposure.
python ./scripts/run_agent.py \
agents/refactor-expert.md \
target.py \
refactor.md \
"Refactor this function and explain the top 3 changes." \
--cli codex
python ./scripts/run_agent.py \
agents/security-auditor.md \
target.py \
security.md \
"Find vulnerabilities. Rate severity: CRITICAL / MODERATE / MINOR." \
--cli codex --model gpt-4o
| Use Case | Why codex |
|---|---|
| Code review / refactor | GPT-5 Codex is code-optimized |
| OpenAI endpoint routing | Use any OPENAI_BASE_URL-compatible target |
| Isolated sub-task to GPT-5 | No main agent context bleed |
agents/)| Persona | Use For |
|---|---|
security-auditor.md | Red team, vulnerability scanning |
refactor-expert.md | Code optimization, DRY, readability |
architect-review.md | System design, modularity |
echo "Say hello in one sentence." | codex exec --model gpt-5-codex -
python ./scripts/run_agent.py agents/refactor-expert.md target.py output.md "Summarize this file." --cli codex
echo $OPENAI_API_KEY # must be set
which codex # must be on PATH
codex --version
codex exec --help # verify exec subcommand and available flags