Every plugin for OpenAI Codex on GitHub — repos with a .codex-plugin/plugin.json or a Codex marketplace. Install with codex plugin marketplace add owner/repo then codex plugin add name@marketplace. Many work in both tools; see Claude Code plugins.
Run any third-party LLM provider with an Anthropic-compatible API as real Claude Code agent-team teammates (terminal claude inside tmux or iTerm2) or one-shot subagents via the cc-fleet CLI — driven just like native teammates; your main session's own auth (OAuth or API key) is untouched, provider workers bill the provider key.
Classical formal logic from G. Chelpanov's textbook: concepts, judgments, syllogisms, induction, fallacies, laws of thought. Two text modes — logical review (logika:review, analysis-only report) and argument fixing (rewrite with corrected logic) — plus solving logic textbook problems. Russian-language references distilled from the source book.
Двенадцать площадок РФ и Китая (Wildberries, Ozon, Яндекс Маркет, Авито, Циан, AliExpress, Taobao, Детский мир, Мегамаркет, Lamoda, DNS, Ситилинк) как MCP-серверы и 15 навыков. Сравнение цен без ключей API.
Use when you want a delegated second opinion or implementation from GPT (Codex), Gemini, Grok (xAI), or OpenRouter (config-driven, 400+ models) - eight expert subagents (Architect, Plan Reviewer, Scope Analyst, Code Reviewer, Security Analyst, Researcher, Debugger, Writing Editor) and bundled ask-gpt/ask-gemini/ask-grok/ask-openrouter/ask-all/consensus commands, advisory (read-only) or implementation (write; only Gemini can implement - GPT, Grok, and OpenRouter are advisory-only).
Set up Kapso, state an objective with its evaluation, launch and follow the experiments, review and deploy the result, learn from the run, author a harness
Write original instrumental music as editable notes: the agent composes and arranges every note, and the skill checks the score, plays it on licensed sampled instruments (pianos, guitars, basses, drums, a full orchestra, saxophones, organ and world instruments), built-in synthesizers or Surge XT presets with player-like timing and dynamics, mixes it through buses and generated reverbs, and masters it with MIDI, stems and an MP3. No audio-generation model is involved.
Message Grok Bot from Codex, Claude Code, and Cursor. Codex/Claude tools use local sockets on the user's registered machines only (no remote transport); from the Grok Bot box, run gbot via Grok Bot Shell with a machineId.
14 AI agents for all software engineering work: architecture, tested code, security audit, CI/CD, documentation. Adaptive routing with 10 execution modes. Same skills/ as the Claude Code plugin.
Agent-ready writing studio for Chinese WeChat articles, English essays, research writing, human voice editing, source-bound data storytelling, and statistical graphics.
Simplify an AI response, surface important facts, restate a request, recap work, get an independent decision, render a status board, or follow one lane on a ladder.
Bundle of 9 X (Twitter) marketing skills for Claude Code and Codex with X-native hook formulas, single-tweet and auto-thread writing, a unified humanizer (rewrite plus `--mode audit` pre-publish check), viral hook extraction, reply and quote-tweet drafting, and a weekly content planner. Tweets and threads ship via Publora, which auto-splits long content into numbered threads.
Recognize the past you reached for — a session, line of work, topic, or concept — in a story on records you can reopen: it took place, not that it still holds — /recollect (ἀνάμνησις: a recollecting)
Recognize what the work rests on — what was settled and from where, what rests on weak or unreached ground, what only you decide — /inquire (αἴτησις: a requesting)
Use when analyzing, selecting, validating, or communicating models for insurance, actuarial, financial-risk, or other consequential uncertain outcomes. Covers regression, generalized linear models, frequency-severity, panel and longitudinal data, survival, time series, credibility, reserving, tail risk, calibration, and model governance. Do not use for generic software forecasting, ordinary SaaS financial models, or credentialed actuarial, investment, legal, or regulatory advice without the relevant specialist review.
Write, review, and maintain architecture decision records with clear context, alternatives, consequences, confirmation links, and lifecycle governance. Use when a consequential technical decision or its enforceable architectural constraint must remain understandable. Do not use for system-wide evolutionary architecture design, general observability, or operating a named test or CI tool.
Run a structured multi-agent debate by spawning a panel of expert agents on any question, with convergence-aware iteration and typed synthesis output via the `agent-council` CLI. Use when a decision has genuine tradeoffs, high stakes, or hidden assumptions worth adversarial collaboration, or when confidence diagnostics matter more than a single recommendation. Compatible with any AI agent harness that supports agentskills.io skills (Claude Code, Cursor, Hermes Agent, OpenHands, etc.). Do not use for simple factual lookups, tasks with a clear correct answer, routine single-perspective work, or code execution and tool orchestration beyond debate.