メニュー
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Resolves the latest flagship model from the model registry.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Generates a narrative walkthrough of AI-authored code changes. Use after implementation to explain what changed, why, and how it behaves.
Evaluate plugin commands, agents, and skills against Anthropic Constitution principles. Score alignment on reasoning-based vs rule-based instruction spectrum, identify improvement opportunities. Use when the user wants to audit, score, or review the quality of a command, agent, or skill — e.g. "review this skill", "audit this command", "is this agent well-written", "score this against constitutional principles", or "check this for rule-based patterns".
Grilling session that challenges a plan against the target repo's existing domain model, sharpens terminology, and updates CONTEXT.md + ADRs inline as decisions crystallise. Invoked by /sdlc:plan at step 3.5 to keep architecture aligned with documented language before the plan is drafted.
Post-merge cleanup workflow. Detects PR merge, switches to main, pulls latest, runs tests, and removes worktree if exists. Use after PR is merged to clean up.
Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Resolves the latest flagship model from the model registry.
Evaluates agent judgment quality through scenario-based testing in-conversation. Use when the user wants to test, validate, or stress-test an agent, skill, or command definition — e.g. "test this agent", "evaluate this skill", "does this prompt handle edge cases", "check this agent's judgment", or after writing or modifying any agent/skill/command .md file.
SOC 職業分類に基づく
| name | codex |
| description | Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Resolves the latest flagship model from the model registry. |
Run OpenAI Codex CLI as a delegated reasoning engine for code analysis, refactoring, and automated edits. Codex has its own sandbox model and its own context window — your job is to invoke it correctly, surface its results, and keep the user in control of any side-effecting operation.
danger-full-access without explicit user opt-in.xhigh for code review, flagship + medium for standard refactors, fast model for cheap one-shots.Resolve the registry first, since model IDs change:
Glob(pattern: "**/sdlc/**/config/model-registry.md", path: "~/.claude/plugins") then Readcodex-flagship. Offer codex-fast for cost-sensitive or simple tasks.xhigh / high / medium / low) — the right level depends on task type, so don't pick silently.If the registry load fails, fall back to the table below. Treat the names as possibly stale and say so when reporting.
| Model | Best for | Context | Notes |
|---|---|---|---|
gpt-5.4 | Flagship — code review, agentic coding | 400K / 128K | Frontier |
gpt-5.4-mini | Cost-efficient coding | 400K / 128K | Smaller frontier |
gpt-5.3-codex | Previous flagship | 400K / 128K | 25% faster than 5.1 |
Two flags are non-negotiable on every call, with reasoning attached so you can judge edge cases:
--skip-git-repo-check — Codex aborts when invoked outside a git repo or inside a nested worktree it doesn't recognize. We run it from arbitrary working directories (including non-repo paths the user names), so the check is wrong for our use. Always include it.2>/dev/null appended to every codex exec — Codex streams thinking tokens to stderr. Those tokens land in your conversation context as tool output and pollute downstream reasoning. Drop them by default. The one exception: when the user is actively debugging Codex itself, omit the redirect so they can see what Codex is doing.Sandbox is the safety dial — pick the least privilege the task needs:
--sandbox read-only for analysis, review, planning. The default. Codex can't write or network.--sandbox workspace-write when edits were requested. Codex can write inside the workspace; still no network.--sandbox danger-full-access only when the user has explicitly approved network or out-of-workspace writes. Confirm before using. --full-auto is the other blast-radius flag — same rule, name it before using.Resume sessions with echo "prompt" | codex exec --skip-git-repo-check resume --last 2>/dev/null. Don't insert -c or -m flags between exec and resume — Codex parses them as positional-arg conflicts and rejects the call. The original session's model and config carry over.
A non-zero exit usually means sandbox denial, config error, or model unavailability. Surface the exit code and stderr (re-run without the redirect if needed) so the user sees the real cause — don't silently retry, since retry without diagnosis just burns quota against the same failure.
Tell the user once: "You can resume this Codex session at any time by saying 'codex resume'." The resume flow above exists but has no natural discovery surface, so the one-line hook is what makes it usable at all.
CLI flag reference, sandbox semantics, and the code-review output format live in references/codex-cli-reference.md. Load when you need flag details — don't paraphrase, the examples are the contract:
Glob(pattern: "**/sdlc/**/skills/codex/references/codex-cli-reference.md", path: "~/.claude/plugins") → Read$ARGUMENTS