Каталог навыков агентов

QA the omo Codex Light edition (lazycodex / packages/omo-codex) itself, in strict isolation so ONLY our plugin is exerci...

Use OpenAI Codex CLI to answer questions about code, analyze files, or perform read-only codebase exploration. Invoke th...

Check OpenAI Codex CLI rate limit status (daily/weekly quotas) using local session logs. Portable Python script. Reads ~...

Optimize Codex Plus/Pro usage before and during coding tasks. Use when the user wants to save Codex quota/credits, reduc...

Send an IFTTT mobile push "codex rate limit detected" when an OpenAI Codex CLI run hits a rate/usage limit. The companio...

Read and integrate response from Codex. Use when user says codex read, get codex response, or check codex results.

Run the Codex Readiness integration test. Use when you need an end-to-end agentic loop with build/test scoring.

Run the Codex Readiness unit test report. Use when you need deterministic checks plus in-session LLM evals for AGENTS.md...

Use when the user asks to analyze, investigate, explain why something happens, trace architecture or behavior across fil...

Codex guided reasoning mode for complex fixes with explicit checkpoints.

Force deliberate, evidence-backed, non-generic reasoning for complex engineering work. Use when the user asks for deeper...

Use when you need Codex to coordinate multiple agents through Relaycast for peer-to-peer messaging, lead/worker handoffs...

Query Codex banked reset credits from the local Codex Desktop login state and report available reset count plus expirati...

Internal guidance for presenting Codex helper output back to the user

Use to resume a previous Codex conversation. Triggers on "continue codex", "resume codex", "pick up where codex left off...

Use when you want Codex to review its own recent history (last N days or specific period) and improve its behavior. Prod...

Code review workflows with Codex CLI including automated reviews, diff analysis, and PR improvements. Use for code revie...

Professional code review with auto CHANGELOG generation, integrated with Codex AI

OpenAI Codex CLI code review with GPT-5.2-Codex, CI/CD integration

Runs a single Codex (ChatGPT/OpenAI) review check-fix cycle on a PR using gh CLI. Use this skill whenever the user wants...

Run an independent cross-model code review of any git scope — uncommitted changes, a commit range, a merge commit, a PR,...

Have OpenAI Codex review the current branch with documentation research. Use for second-opinion code reviews or when you...

Professional code review with auto CHANGELOG generation, integrated with Codex AI. Use when you want professional code r...

Integrates OpenAI Codex CLI as an MCP server to provide second-opinion reviews. Use when user mentions 'Codex レビュー', 'セカ...

Step-by-step guidance for codex review.

規模判定 → Codex規模別レビュー → Claude Code修正 → 再レビュー（ok: trueまで反復）

Perform code reviews using OpenAI Codex CLI to identify bugs, security vulnerabilities, performance issues, and code qua...

Run an independent code review using the OpenAI Codex CLI in headless mode. Gets a second opinion from a different model...

Iterative code review and planning discussion between the local agent and Codex CLI. Orchestrates an automatic back-and-...

Ask Codex CLI with its configured model for an independent code review of uncommitted changes, a branch diff, a commit,...

Cross-model code review via the OpenAI Codex CLI. This is the codex half of /deep-review, not a general reviewer — for o...

Run AI-powered code review using the codex CLI. Use when the user asks to "codex review", "run codex review", or "review...

Cross-vendor code review: this agent reviews the other agent's diff and the other agent reviews this one's, so the final...

Review implementation quality and regression risks via claude-delegator (Code Reviewer expert). Use after implementation...

Git管理外のファイルをcodex CLIでレビュー。「このファイルをcodexでレビュー」「設定ファイルをレビュー」時に使用

Use for role-scoped FE/BE/DevOps/Admin/QA project docs under .codex/project-docs to preserve micro-context across long p...

Analyze Codex rollout/session JSONL files and PwrAgent/Codex profile data for expensive tool-output behavior, cached-tok...

Use Sol as the advisor and coordinator for coding work, delegating investigation and implementation to Luna subagents.

Use when operating Codex CLI itself (config, profiles, sandbox, approvals, and safe usage patterns).

Format Arabic-script RTL prose, including Persian (Farsi), Arabic, Urdu, Dari, Pashto, and Kurdish Sorani, for reliable...

Enforce repo execution discipline: keep PRs small; run migration-smoke when invariants change; never hand-edit vendored...

Shared native Codex stage, checkpoint, goal, and agent-adapter contract.

Use at the start of a Codex task to inspect repo readiness, project profile, monorepo shape, role docs, spec status, kno...

Use Codex CLI sandbox mode to try risky changes safely. Isolated experimentation with network disabled and directory res...

Run code in Codex fully isolated sandbox - network disabled, CWD only, Seatbelt/Docker isolation

Run codex sandbox evidence.

Use at the start of a Codex session (especially sandboxed) to run `scripts/codex-sandbox-preflight.sh` and interpret net...

Install and operate a Scrum-oriented subagent kit for Codex projects. Use when work should follow Scrum roles or ceremon...

Architect-level guidance, workflows, and scripts for building agentic coding systems with OpenAI Codex. Use for Codex SD...

Investigate the @openai/codex-sdk API by first inspecting installed .d.ts typings in node_modules, then cloning and sear...

Use when asked to introduce Codex SDK usage for automation (CI/CD, bots, internal tools) and provide a minimal, safe sta...

Search the web using OpenAI Codex CLI to find current documentation, best practices, solutions, and technical informatio...

Apply layered security routing for network, infrastructure, application security, compliance, and DevSecOps concerns. Us...

Lisp machine self-modification patterns via MCP Tasks and Narya bridge types

Keep Codex Desktop conversation history visible when bridging between a ChatGPT personal account and an API proxy. This...

List and inspect local Codex session history by reading `~/.codex/session_index.jsonl`, `~/.codex/sessions/`, and `~/.co...

Search Codex local session history stored in SQLite and session_index.jsonl. Use this skill when the user wants to list,...

Diagnose, privately back up, compact, verify, and hand off stalled or extremely slow Codex CLI sessions through the offi...

Diagnose and repair local Codex Desktop/CLI session JSONL files when a thread cannot resume or compact because of contex...

Use when Codex Desktop sidebar sessions disappear, fail with systemError, or cannot continue after a model_provider swit...

Use this skill when the user wants to inspect, search, export, verify, clean up, delete, restore, or purge local Codex s...

Codex CLI 用の .codex/ と AGENTS.md を導入・更新する。Use when user mentions '/codex-setup', codex cli setup, codex config, or wants...

Run a political science pre-submission audit with journal-aware personas, stage-aware standards, and evidence-grounded i...

Non-interactive automation mode using OpenAI Codex

Use when user asks to leverage codex, gpt-5, or gpt-5.1 to implement something (usually implement a plan or feature desi...

Build, improve, package, and review Codex skills from rough ideas, workflows, scripts, README/API/CLI docs, or existing...

Create or update Codex skills that follow the repository skill format, trigger cleanly, and stay concise. Use when addin...

Codex CLI用のスキル作成ガイド。YAML frontmatter、ディレクトリ構造、ベストプラクティスを解説。Use when creating new Codex skills, updating existing skills,...

Create, research, revise, restyle, present, inspect, and export Codex Slides slide decks from Codex, including scenario...

Compatibility entry point for opening and operating Codex Slides in Codex's in-editor Browser, including scenario select...

Compatibility entry point for scenario-led creation, Design Files, brand systems, inspecting, revising, restyling, and e...

Diagnose and recover from Codex Slides plugin, MCP, Browser handoff, local runtime, durable run, project resume, renderi...

Compatibility entry point for researching a current topic into a source-backed Markdown brief and turning it into a Code...

Collect and persist structured presentation requirements for Codex Slides, including scenario choice, audience, page cou...

Verify that Codex Slides changes are durably reflected in project state and visibly reflected in the exact Codex Browser...

Use for prototype, MVP, fullstack feature, from-scratch feature, or multi-domain work that needs a SPEC.md before planni...

Use when one milestone is too large for a single spec or plan and needs several brainstorm-and-plan rounds before it shi...

Check the current status of Codex collaboration. Use when user says codex status, check codex, or collaboration status.

Launch Codex CLI as an isolated subagent for bounded coding, review, or verification tasks.

Helps you to run a subagent using codex exec

Route Codex delegation design, subagent prompting, reusable catalog-asset design, and custom-agent template review.

Use when an approved plan has independent tasks ready for delegated execution with fresh subagents and two-stage review.

Run named GPT tasks through the local codex-subagents-for-claude-code runner with Bash. Use for direct or parallel deleg...

Route Codex work to the right supercharged workflow. Use when the user asks to improve their Codex setup, choose among s...

OpenAI Codex-native multi-agent swarm orchestration for parallel coding. Use when spawning multiple Codex CLI agents to...

Kill stale OpenAI Codex plugin processes (orphaned app-server brokers, codex app-server/exec orphans) and clean their cx...

Install and operate a portable OpenAI Symphony + Linear orchestration setup in any Git repository. Use when the user wan...

Codex CLI handles planning, design, and complex code implementation. Use for: architecture design, implementation planni...

PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional reasoning and task completion abilities. C...

Use for bugs, test failures, broken behavior, or unexpected results; enforces 4-phase root-cause debugging before fixes.

Run in-session task loops via the codex-taskloop-plugin MCP server and stop hook.

Coordinate multiple Codex agents.

通用多角色协作方法：由协调者按任务启用顾问/探索者/执行者/测试者/审查者/记录者，编译可验收的工作包、独立审查、失败返回修复并做最终验收。与执行后端解耦，默认使用宿主可用的原生子代理。

Use before feature, bugfix, or refactor implementation when behavior can be tested; enforces Red-Green-Refactor discipli...

Validate integration impact and regression risks via claude-delegator (Code Reviewer expert). Use for complex tasks or A...

A test local skill for Codex. Use when testing Codex-specific local skills.