Use when the user says "/model-loop", "model loop", "rival loop", "claudex this", or "crucible this plan"; asks a different coding CLI (agy, Cursor agent, Codex, Claude Code) to attack a plan before implementation; or is about to build high-stakes work (auth, schema, concurrency, migrations, payments, greenfield…
A coding workflow for planning changes, writing tests before or alongside code, and reviewing the result. TDD, or test-driven development, means using tests to guide the implementation.
Bootstrap a new project with multi-CLI agent config — drops AGENTS.md + CLAUDE.md from the cc-templates templates/ directory into a target project, patches its .gitignore, and prints verification commands. The "multi-agent" here means multi-CLI (Claude Code + Codex CLI + Antigravity CLI), not multiple internal…
Manage Yandex Tracker spaces through the REST API. Use when Codex needs to work with any documented Tracker API function: issues, issue filters, checklists, comments, attachments, bulk operations, fields, projects, portfolios, goals, queues, automation, boards, dashboards, components, issue types, statuses…
A text-based tutor for learning C# and .NET, the Microsoft platform used to build applications and services. It guides learners from first programs toward junior backend development.
Generate terminal-style demo GIFs and PNG cover images from real command transcripts, shell output, CLI logs, or user-provided terminal text. Use when asked to create a demo GIF, terminal animation, README-ready command-line visual, CLI walkthrough, or proof-backed visual artifact from command execution.
Stop the active Loop in this Codex CLI session — stop re-arming clock.sleep and close out the turn the loop was running in. Use ONLY when the user explicitly asks to stop, end, kill, or cancel the loop. Never invoke this on your own initiative while a loop is running.
Comprehensive project and business advisor & coach that orchestrates specialist subagents (market, competition, finance, strategy, marketing, product, risk) with mandatory critical verification, FARO coaching, accountability, OKRs and persistent project memory. Use whenever the user asks for advice or coaching on…
Inspect Skill Manager's locally installed Claude Code, Codex, Muse, or Grok skills before non-trivial work, report the smallest clearly relevant set already active, temporarily activate relevant inactive skills, load all selected instructions, and clean up any receipt it creates before finishing. Use at the start of…
Use for bounded native Codex multi-agent orchestration when a task has at least two independent workstreams or independent verification would materially improve confidence: broad or high-risk multi-step work, audits, migrations, multi-area review-and-fix, adversarial verification, cross-checked research, or explicit…
Build production-ready AI agents in Python using Google Agent Development Kit (ADK). Use when creating agentic Python applications with LlmAgent, workflow agents (SequentialAgent, ParallelAgent, LoopAgent), multi-agent orchestration, tool development (function tools, MCP, OpenAPI), session and state management…
Runs a systematic debugging workflow for bugs, regressions, flaky behavior, and performance surprises. Use when something is broken, failing, throwing, slow, flaky, or when the user asks to debug or diagnose a specific problem.
Runs a domain-neutral, evidence-based tournament in which independent candidates are reviewed, anonymized, and scored by a blind judge against a rubric fixed before judging. Use when comparing competing plans, designs, implementations, documents, tools, vendors, strategies, or other substantial options; when the user…
A delivery workflow for Android APK files, the installable packages used to distribute Android apps. It reads the app version, gives the file a dated name, and copies it to a local network SMB share, a shared folder protocol.
Prepare a durable specification and handoff for a bounded engineering workflow the user wants Codex to pursue as a persistent goal. Use for Codex goal delegation, not ordinary long-running work or a request merely to save session state.
Run a project-start interview against the live engineering rules pack, decide which engineering domains apply, put the highest-consequence questions first, and record terminology, decisions, risks, and build gates. Use when a user explicitly asks for an Engineering Grill before building or substantially redesigning a…
Acionamento MANUAL de failover cross-provider — LADO CLAUDE (Opus). Use quando o GPT/Codex está indisponível e o Opus está UP: o Claude ASSUME a sessão interrompida do Codex e a continua (event=gpt-down); ou quando o GPT/Codex volta, o Claude disponibiliza o estado e o Codex realinha a própria casa (event=gpt-up).…
Autonomously choose the smallest suitable reasoning effort for each task, lowering effort for simple or low-risk work and raising it when ambiguity, risk, stakes, or repeated failures warrant deeper reasoning. Use as a broad implicit runtime policy for all Codex tasks, especially when reasoning effort could otherwise…
Use when reviewing a pull request or branch diff with fixed perspectives and unified findings. Orchestrates code-reviewer, silent-failure-hunter, pr-test-analyzer, comment-analyzer, type-design-analyzer, and code-simplifier viewpoints.
Level design fundamentals, pacing, difficulty progression, environmental storytelling, and spatial design for engaging gameplay experiences.
★not rated 1 2mo agoA23 tokens
originalApache-2.0
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: