Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 275,028 indexed, measured the same four ways as everything else here.
Build, configure, run, inspect, or troubleshoot agent-agnostic recursive improvement loops for a repository or artifact. Use when a task should be attempted repeatedly by Claude Code, Codex CLI, Hermes, or another CLI agent; when candidates must inherit mutable task instructions, a self-improving meta-procedure, and…
Use when doing non-trivial coding with Hermes, OpenClaw, Claude Code, Codex CLI, or similar autonomous coding agents. Orchestrates Karpathy-style minimal-change discipline, grill-plan intake, TDD, systematic debugging, subagent-driven implementation, spikes, and pre-commit review into one end-to-end workflow.
Build and modify EdgeSpark apps. Use when a project has edgespark.toml, the user mentions EdgeSpark, or work involves the edgespark CLI, server SDK types, storage/auth/database workflows, deployment, or @edgespark/web.
A workflow for collecting and packaging a user’s local Codex setup before moving to another computer. Codex is an AI coding assistant, and the package is prepared for later restoration.
Create, customize, validate, locally install, and test theme packs for Codex Desktop from generated background artwork, a landscape image, brand palette, or style brief. Use when a user asks to make a Codex theme, generate or convert artwork into a Codex background/theme pack, prepare free or branded theme assets…
Gere um relatório local e somente leitura sobre sessões, tokens, modelos, reasoning effort, profiles, MCPs, ferramentas, skills, prompts repetidos, finalidades e objetivos do Codex CLI. Use para auditoria de consumo e recomendações de configuração.
Use when profiling or optimizing this Angular 21 habits app for faster initial load, smaller bundles, smoother rendering, or reduced change-detection work. Covers route-level code splitting, @defer, signals/computed state, template hot paths, and validation of performance changes.
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…
★not rated 1 2mo agoA105 tokens
originalMIT
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: