23,553 tagged Building agents, measured the same way as everything else here.
Browse within: agentic-ai 233LLM 217agent 200agents 151skills 145agentic-workflow 110agent-orchestration 86openai 86antigravity 79agentic-framework 73cli 73ai-skills 71Autonomous Agents 67agent-framework 63
Skill Claude CodeCodex
Use for configurable, high-rigor app execution across repos. Selects the lightest safe workflow mode from an app profile, creates or uses a slice manifest, and routes product, tracker, code-intelligence, UI/UX, and verification gates without hard-coding one app's rules.
Skill Claude Code
Delegate coding tasks to OpenAI Codex CLI. Supports presets (turbo/balanced/quality/max) or custom model+effort selection. Use when user wants to leverage GPT-5.5/Codex models for code analysis, refactoring, security audits, or complex transformations. Also covers MCP server management and advanced CLI features.
Skill Claude CodeCodex
Generate CLAUDE.md / AGENTS.md + TODO.md for the current project, following the minimal HumanLayer pattern and Karpathy 4 rules. Bakes a Session Maintenance Protocol into the root file so future agents auto-update rules and TODO when they load the file. Use when user mentions CLAUDE.md, AGENTS.md, project rules, init…
Skill Claude Code
Use when the user wants a coding task executed with a strong planner model first and a faster/cheaper executor model after the first successful implementation edit.
laruss/recursive-task-optimizer
Skill Claude CodeCodex
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…
langlanglanglanglang/rules-architect
Skill Claude Code
A set of rules for organizing Claude Code instructions across hooks, personal memory, path-specific rules, shared project instructions, and team lessons. It is written partly in Chinese and includes a five-question placement process.
Skill Claude CodeCodex
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.
Tang1206cc/Codex-Device-Migration-Assistant
Skill Codex
Inspect, verify, transactionally restore, and audit a Codex migration package on a new computer. Use when the user has transferred Codex “行李”, a codex-move ZIP or age-encrypted package, and asks to receive, import, unpack, restore, or complete a move on macOS, Windows, or Linux.
luhfilho/kimi-plugin-cross-platform
Skill Claude CodeCodex
Use when implementation should be delegated to Kimi Code.
Not-Dev-Tech/codex-insights-local
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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…
Skill Codex
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…
tharanee-bit/Codex-Dynamic-Workflows
Skill Codex
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…
Skill Codex
Fail-closed local routing guidance for Codex agent profiles and the bundled codex-tier dispatcher.
Skill Claude CodeCodex
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…
RuriLothlorien/codex-dsh-routing-suite
Skill Claude Code
A routing suite that chooses a working mode for a coding-agent session based on the first request. It supports modes for detailed specification work, fast implementation work, or uncertain cases, with status checks and one-off subprocess modes.
Skill Claude CodeCodex
An orchestrator mode that divides a large coding task into separate jobs and assigns them to worker agents that can run in parallel.
Skill Claude CodeCodex
A guide to reducing token use in Codex conversations, where tokens are the units of text sent to and from the language model.
Skill Claude CodeCodex
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.
rodrigorpassos/claude-codex-failover
Skill Claude CodeCodex
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).…
tharanee-bit/Codex-Auto-Reasoning-Effort
Skill Codex
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…
Skill Claude Code
Complexity-based routing of tasks across four model tiers — frontier (T3), strong workhorse (T2), fast executor (T1), cheapest recon (T0). Use when planning any multi-step work, when deciding which subagent should execute a task, when writing a dispatch brief, or when an executor fails and escalation is needed.
agentic-control-plane/codex-acp-plugin
Skill Claude Code
Generate a cost X-ray report for your agent from ACP's metering — cache economics, context composition, tool bloat, loop share — before you ship it (or whenever spend surprises you).
hashgraph-online/registry-broker-codex-plugin
Skill Claude CodeCodex
Use Registry Broker to discover and summon specialist agents for focused subtasks from inside Codex.
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: