---
title: "Agent Tooling Agent Plugins, page 7 of 7"
description: "Plugins that build, inspect, or extend AI agents themselves: MCP server builders, skill and plugin authoring kits, memory and context management, prompt engineering, agent evaluation and observability."
canonical: https://agentpluginsdirectory.com/categories/agent-tooling/page/7
last-updated: 2026-10-11
---

# Agent Tooling Agent Plugins, page 7 of 7

Plugins that build, inspect, or extend AI agents themselves: MCP server builders, skill and plugin authoring kits, memory and context management, prompt engineering, agent evaluation and observability.

| Name | Description | Repo |
| --- | --- | --- |
| [wom.hermes-closure-gate](https://agentpluginsdirectory.com/plugins/wom.hermes-closure-gate) | Portable companion package for the Hermes pre_verify closure gate. | wommy/agents-wom-plugins |
| [delegation](https://agentpluginsdirectory.com/plugins/delegation) | Agent Plugin that provides Kiro agent orchestration via delegation. | thimslugga/agent-plugins |
| [mcp-builder](https://agentpluginsdirectory.com/plugins/mcp-builder--agentplugin-net) | Portable Agent Plugin packaging of the mcp-builder Agent Skill. | agentplugin-net/portable-agent-plugins |
| [keep-agent-running](https://agentpluginsdirectory.com/plugins/keep-agent-running) | Keep Claude Code, Codex, and other coding-agent terminals available after disconnects, using the least infrastructure that works. | Anchras/terminalbox-tools |
| [engineering-foundation-core](https://agentpluginsdirectory.com/plugins/engineering-foundation-core) | Task contracts, bounded planning and orchestration, surgical implementation, debugging, research, review, verification, and handoff. | EgoistDeveloper/codex-skills-foundation |
| [j-space](https://agentpluginsdirectory.com/plugins/j-space) | Inference-time workspace control for long-horizon work. Wraps the upstream J-Space Cognition Suite skill; does not invent runtime behavior. | atebites-hub/atebites-plugins |
| [moe-crew](https://agentpluginsdirectory.com/plugins/moe-crew) | Launch, control and monitor Claude Code, Codex, and Pi workers over tmux. | zak-keown/moe |
| [nanlabs-core](https://agentpluginsdirectory.com/plugins/nanlabs-core) | Recommended install: setup/onboarding, orchestrator, companion, handshake, Pyright report-only typing, PR fallback, knowledge sync, and code-reviewer agent | nanlabs/agent-toolkit |
| [plugin-installer](https://agentpluginsdirectory.com/plugins/plugin-installer--okyongchoi) | List and securely install catalogued plugins from local mirrors or pinned Git sources. | OkYongChoi/air-gapped-agent-plugins |
| [rad-repo](https://agentpluginsdirectory.com/plugins/rad-repo) | An Agent Plugins 1.0.0 package for repository context, typed recall, handoffs, scoped checks, and guarded Git shipping in Codex. Its opinionated model and heuristics cannot prove code or production health. | RadOrigin-LLC/rad-plugins |
| [tricritical](https://agentpluginsdirectory.com/plugins/tricritical--nisavid) | Tricritical: independently planned intent, runtime, and structure critics, adjudication, authority-gated revision, and one fixed-point loop. | nisavid/provingkit |
| [agentic-bundle-skill-author](https://agentpluginsdirectory.com/plugins/agentic-bundle-skill-author) | Portable skills-only "Skill Author" plugin from Agentic Awesome Skills. | sickn33/agentic-awesome-skills |
| [skill-manager](https://agentpluginsdirectory.com/plugins/skill-manager) | 在对话里用自然语言管理技能：搜索并安装技能市场里的技能、用打包的 skill-creator 技能从零创建你自己的私有技能、编辑修改已有私有技能的内容、把私有技能申请上架到技能市场、查看/删除你的技能，也支持给一个 web 链接从中下载并安装技能或插件。装上后智能体即可原生地创建、编辑、管理、删除、申请上架技能。 | ZJU-REAL/HugAgentOS |
| [minimax-code-trajectory](https://agentpluginsdirectory.com/plugins/minimax-code-trajectory--minimax-ai) | Inspect and visualize local MiniMax Code session ledgers as privacy-aware trajectories through a dependency-free MCP server. | MiniMax-AI/MiniMax-Code-Plugins |
| [agent-toolkit-core](https://agentpluginsdirectory.com/plugins/agent-toolkit-core) | Core orchestration skills, dev companion, output handshake, PR fallback, and code-reviewer agent. The baseline install for any project. | ulises-jeremias/agent-toolkit |
| [context-hygiene](https://agentpluginsdirectory.com/plugins/context-hygiene) | trigger: context bloat, stale observations, resolved content inlined, noisy exploration. avoid: context rot and lost-in-the-middle failures. | open-coder-ai/chock-catalog |
| [spec-plugin](https://agentpluginsdirectory.com/plugins/spec-plugin) | Spec-driven project execution pipeline, from ideation to verified deliverables, orchestrated by AI agents. Works with any project type. Built on a team of subagents plus a tool-use hook, so it needs an agent that can run plugin-provided subagents and hooks. | nexaedge/nexaedge-marketplace |
| [pick-subagent](https://agentpluginsdirectory.com/plugins/pick-subagent) | 서브에이전트 모델을 골라 실행하는 슬래시 커맨드 + 서브에이전트 루프 스킬 | wonjiko/claude-toymarket |
| [model-invocable-skills](https://agentpluginsdirectory.com/plugins/model-invocable-skills) | Show which Pi skills are available to the model and which require explicit user invocation. | emo-eth/skills |
| [caveman](https://agentpluginsdirectory.com/plugins/caveman) | Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman. | RDCrystalLab/agentic-plugins |
| [automation-governance](https://agentpluginsdirectory.com/plugins/automation-governance) | Framework and tooling for evaluating workflow, skill, and process automation readiness based on the Google DeepMind Intelligent AI Delegation framework. | ghchinoy/agent-skills |
| [eval-writer](https://agentpluginsdirectory.com/plugins/eval-writer) | Defines measurable success criteria and designs evaluations for any LLM-based task, product, feature, or piece of logic. | tiennguyentt/agent-plugins |
| [swarm-forge-squad](https://agentpluginsdirectory.com/plugins/swarm-forge-squad) | The SwarmForge squad workflow: a persistent squad leader that spawns short-lived specialist workers on demand, each bound by a capability contract. | pproenca/dot-plugins |
| [wom.womr-skill-reachability](https://agentpluginsdirectory.com/plugins/wom.womr-skill-reachability) | Session-start warning for bare-name skill routes the Skill tool cannot load. | wommy/agents-wom-plugins |
| [skill-creator](https://agentpluginsdirectory.com/plugins/skill-creator--agentplugin-net) | Portable Agent Plugin packaging of the skill-creator Agent Skill. | agentplugin-net/portable-agent-plugins |
| [moe-memory](https://agentpluginsdirectory.com/plugins/moe-memory) | Semantic recall over past sessions and journal entries. | zak-keown/moe |
| [skill-bridge](https://agentpluginsdirectory.com/plugins/skill-bridge) | Convert an openclaw (or similar) skill into a portable mavis/mcode-compatible skill, exposed as a stdio MCP server. Detects encoding, parameterizes hardcoded paths, enriches frontmatter, and runs the official skill-creator lint. | MiniMax-AI/MiniMax-Code-Plugins |
| [memory-discipline](https://agentpluginsdirectory.com/plugins/memory-discipline) | trigger: repeated mistakes, rediscovered patterns, preferences, non-derivable facts. avoid: persisting file contents, git history, or task intermediates as memory. | open-coder-ai/chock-catalog |
| [vendored-skills](https://agentpluginsdirectory.com/plugins/vendored-skills) | Vendored skills from external repositories, copied into this marketplace and pinned to the upstream commit they came from, so they keep working when upstream moves. | nexaedge/nexaedge-marketplace |
| [pi-bots](https://agentpluginsdirectory.com/plugins/pi-bots) | Run persistent domain-owning bots through Pi and pi-subagents. | emo-eth/skills |
| [cli-creator](https://agentpluginsdirectory.com/plugins/cli-creator) | 從 API 文件、OpenAPI spec、curl 範例或現有腳本建立可組合的 CLI 工具。支援 Python (uv single-file)、Rust、TypeScript，含 companion skill 自動生成。 | RDCrystalLab/agentic-plugins |
| [unknown-remover](https://agentpluginsdirectory.com/plugins/unknown-remover) | Classifies the unknown, picks the artifact form, and writes one planning document at a time from the five-document chain. | tiennguyentt/agent-plugins |
| [verification-loop](https://agentpluginsdirectory.com/plugins/verification-loop--minimax-ai) | Enforce a claim-to-proof workflow: define the evidence, run the right verification, and distinguish verified results from assumptions before declaring work complete. | MiniMax-AI/MiniMax-Code-Plugins |
| [token-efficiency](https://agentpluginsdirectory.com/plugins/token-efficiency) | trigger: large command output, broad searches, re-reading unchanged files, front-loading references. avoid: wasting context window on low-signal content. | open-coder-ai/chock-catalog |
| [wall-clock](https://agentpluginsdirectory.com/plugins/wall-clock) | Keep agent work inside a deadline with time-aware planning, bounded assignments, and explicit wrap-up reports. | emo-eth/skills |
| [skill-scout](https://agentpluginsdirectory.com/plugins/skill-scout) | 從外部 repo 發現、評估、移植 skills 到插件市集。支援瀏覽、討論篩選、合併相關 skills、雙格式 plugin.json 產出。觸發詞：讀這個 repo、看一下 ~/workspaces、瀏覽 skills、移植這個 skill、把這個 porting 過來、評估這個 repo、從 GitHub 匯入 skill；read this repo, browse skills, port this skill, add this skill. | RDCrystalLab/agentic-plugins |
| [tmux-fork](https://agentpluginsdirectory.com/plugins/tmux-fork) | Fork new tmux windows to spawn parallel AI agents or run CLI commands | RDCrystalLab/agentic-plugins |