Results for “dex”

Claude Code（.claude）と Codex（.codex / .agents / AGENTS.md）に分裂したエージェント設定を、 実ファイル1つ + symlink と双方向変換で単一化・同期するスキル。 実ファイルをどちら側に置くか（symlink の向き）は共通設定 source で選べる。 プロジェクト単位の導入ウィザード、既に分裂しているリポジトリを危険度の低い順に解決する手順、 片方しか無いリポジトリへもう片方を生成する scaffold、書き換え前のバックアップと復元、常駐の管理を含む。 「エージェント設定を同期して」「.codex と .claude がずれている」「Codex でも同じスキルを使いたい」 「AGENTS.md と CLAUDE.md を一本化したい」「MCP を Codex でも使えるようにして」 「サブエージェントを Codex 側にも作って」「設定の分裂を解消して」「元に戻して」 「agents-sync」「同期デーモン」などと言われたら使う。 Keywords: agents-sync, エージェント設定同期, .claude, .codex, .agents, AGENTS.md, symlink 統合, symlink の向き, 実ファイルを置く側, 双方向同期, scaffold, 分裂解消, MCP 同期, hooks 同期, サブエージェント同期, バックアップ, 復元, fswatch, launchd, 常駐デーモン

The English summary is being prepared. Showing the original description.

Check skills before distributing them to Codex or Cursor. Identify unsupported metadata fields, Claude-specific variables in shell examples, and inconsistencies between source skills and their installation copies using the project's compatibility checker.

• Check a new skill before opening a pull request
• Review skill copies for Codex or Cursor
• Investigate compatibility findings from CI

Create a custom animated Codex pet from text or reference images. Generate consistent poses, assemble them into a spritesheet, an image containing animation frames, and package the result with configuration files, visual checks, and preview videos.

• Create a Codex pet from a text concept
• Turn character art into an animated pet
• Repair inconsistent animation poses

Present results returned by a Codex helper while preserving findings, severity, file references, and uncertainty. This internal guidance also covers reporting edited files, failed runs, and setup requirements, with user confirmation before fixing review findings.

• Present review findings in order of severity
• Keep observed evidence separate from inferences
• Report files changed by Codex

Delegate coding, analysis, refactoring, or reviews from Claude Code to Codex CLI. The skill explains unattended execution, permission settings, output capture, parallel tasks, and independent checks of changed files and test results.

• Delegate implementation while retaining planning responsibility
• Get a second opinion on code changes
• Split independent tasks across separate git worktrees

Complete the PUA survey through a guided flow in Codex CLI and save responses to a local JSON file. This alias provides the equivalent of Claude Code’s /pua:survey command without sending answers anywhere.

• Complete the PUA survey in Codex CLI
• Save survey answers to a local JSON file
• Use the equivalent of /pua:survey from Codex

Inspect Bing link data, compare sites you manage, and submit new URLs through IndexNow, a service for notifying participating search engines of updates. Use it to support indexing and prepare pages for potential Microsoft Copilot citations.

• Submit new page URLs through IndexNow
• Compare Bing link data for two managed sites
• Verify the IndexNow key setup

Switch Codex from Weave Router back to its default provider without logging out or deleting the router configuration. The change applies the next time Codex starts and can be reversed with `$router-on`.

• Return Codex to its default provider
• Turn routing off while keeping its configuration
• Check when the provider switch takes effect

Delegate a self-contained coding task to Codex CLI from another agent using ChatGPT subscription authentication. Run independent implementation, request a second opinion, or verify changes, with separate working copies for parallel tasks.

• Delegating a clearly scoped feature or bug fix
• Running independent implementation tasks in parallel
• Getting a second opinion on code

Audit XML sitemaps by checking their structure and listed URLs against actual page conditions. Find errors, redirects, pages excluded from indexing, missing eligible pages, and inaccurate modification dates to identify sitemap problems affecting indexing.

• Investigating sitemap errors in Search Console
• Finding URLs that should be removed from a sitemap
• Checking for indexable pages missing from a sitemap

codex exec review を基本に、必要なら codex exec を使ってコード変更のレビューを依頼し、指摘事項を報告する。通常 / 厳しめ (--strict) / 敵対的 (--adversarial、実装を壊しにいく red team) の 3 モードを持つ。「codexでレビューして」「codex-review」「/codex-review」「敵対的にレビューして」で発火。Codex 単体での単独レビュー用途。複数エージェント並行レビューは cross-review、差分ではなくコードベース全体の監査は audit を使う。

The English summary is being prepared. Showing the original description.

Save project context and task handoffs as local Markdown documents that Claude, Codex, and other agents can share. The skill guides searching prior knowledge, recording evidence and remaining work, and checking the shared memory vault for structural problems.

• Handing work from Claude to Codex
• Saving project context for a later session
• Finding earlier decisions and supporting evidence

Use OpenAI Codex CLI to review code changes, challenge an implementation by looking for ways it could fail, or discuss technical questions. Three modes provide an independent opinion, with follow-up questions supported in ongoing consultations.

• Get an independent review of code changes
• Challenge code to uncover possible failures
• Continue a technical consultation with follow-up questions

Manage command-line tools connected to OmniRoute through its API. Inspect tool status, read or change settings, manage Codex profiles and backups, and invoke tool plugins for automation tasks.

• Reviewing settings across connected tools
• Managing Codex profiles
• Checking tool status and logs

Audit conflicting search indexing settings across robots.txt, noindex directives, and canonical tags that identify preferred URLs. Identify why pages may be included or excluded unexpectedly, and review changes that align the settings with the intended outcome.

• Investigating pages that remain in Google's index
• Checking pages unexpectedly excluded from search
• Reviewing robots.txt and noindex conflicts

Resume unfinished Codex work in Muse Code by reading a local session log selected by the user. Recover the latest request, decisions, and pending changes, then check current files and continue the task.

• Continue unfinished Codex work in Muse Code
• Resume work from a session ID or log path
• Recover prior decisions before continuing a task

Delegate code analysis and implementation to Codex CLI without an interactive session. The skill reads ordered output events, extracts the final agent response, and reports errors, with a read-only sandbox used by default.

• Review code in a read-only sandbox
• Delegate implementation to Codex
• Get a second coding agent's assessment

Read provider usage, limits, credits, and installation or configuration health through CodexBar. Returns JSON for enabled providers or a selected provider, while hiding secrets and leaving configuration and authentication unchanged.

• Checking usage and limits across enabled providers
• Checking credits for a selected provider
• Diagnosing installation or configuration health

Disables PUA's always-on mode from Codex CLI and sets feedback frequency to zero. The alias updates the local configuration while preserving unknown fields, then reports completion with evidence from the executed command.

• Disabling PUA's always-on mode in Codex CLI
• Setting PUA feedback frequency to zero
• Using a Codex equivalent of Claude Code's /pua:off

Find available Codex skills in a curated list and install them by name or GitHub path. Supports multiple skills in one run, custom destinations, and private repositories using available credentials.

• Browse curated skills and see which are already installed
• Install a curated skill by name
• Add skills from a public or private GitHub repository

Coordinates a named team of Codex workers with concrete responsibilities and shared progress records. It selects available collaboration tools, manages communication and separate working copies when needed, and handles integration, team archival, and cleanup after the work ends.

• Splitting related implementation work across cooperating agents
• Investigating several aspects of a clearly defined problem
• Inspecting team progress and member responsibilities

SUPERSEDED by /claudex-loop (formerly /crucible; adds a Phase 0 research/recon pass + rebuilt interview) — prefer that skill unless you explicitly want this one. Two-act plan hardening. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan or design, one question at a time, recommending an answer for each and exploring the codebase when it can answer itself, until every branch of the decision tree is resolved. ACT 2 (Claude ↔ Codex) — Claude writes the locked plan to PLAN.md and OpenAI Codex adversarially reviews it in a read-only sandbox (VERDICT:APPROVED/REVISE), Claude revises and re-submits to the SAME Codex session until APPROVED or a MAX_ROUNDS cap, then you sign off before any code. Use when the user says "/grill-me-codex", "grill me then have codex review", "grill me and stress-test the plan", "interview me about this plan then get a second model on it", or is about to build something high-stakes (auth, schema, concurrency, migrations, payments) and wants both alignment AND a cross-model sanity check before implementation. Builds on Matt Pocock's grill-me (MIT). For the docs-aware variant use /grill-with-docs-codex; if you already have a plan and want only the Codex review use /codex-review. NOT for reviewing already-written code (use /codex:review) and NOT for trivial changes.

The English summary is being prepared. Showing the original description.

Browse available Codex skills and install them from a curated list or a specified GitHub location. Supports experimental skills, private repositories with credentials, and installing several skill folders in one operation.

• Browse available skills and see which are already installed
• Install a named skill from the curated list
• Add a skill from a private GitHub repository

Review estimated spending, token usage, and cache hit ratios across Claude Code, Codex, and Grok using local logs. Filter by time, project, or provider, while keeping currencies separate and identifying models without pricing.

• Reviewing estimated spending for the past seven days
• Comparing usage across providers and models
• Checking costs for a specific project or time range