---
title: "Agent Tooling Agent Plugins, page 2 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/2
last-updated: 2026-10-08
---

# Agent Tooling Agent Plugins, page 2 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 |
| --- | --- | --- |
| [copilot-atelier](https://agentpluginsdirectory.com/plugins/copilot-atelier) | Portable GitHub Copilot customization library: role-specific custom agents with handoffs and subagent allow-lists, deterministic lifecycle hooks, and on-demand Agent Skills for PowerShell/DSC engineering (Sampler, Pester, Datum, AutomatedLab, WinRM, MECM), document conversion (PDF, DOCX, XLSX, Marp, pandoc), Outlook and Microsoft To Do automation, research and citation integrity, agentic-security review, and skill/prompt/agent evaluation. Skills are portable; agents, rules, slash commands, and hooks load in GitHub Copilot clients. Keybindings are not a plugin component type; install the CopilotAtelier module from the PowerShell Gallery to get those too. | raandree/CopilotAtelier |
| [meta](https://agentpluginsdirectory.com/plugins/meta) | Opinionated guidance for governing marketplaces, organizing plugins, and writing agent skills. | BastiDood/skills |
| [prism](https://agentpluginsdirectory.com/plugins/prism) | Route Prism work across full Story and Epic lifecycles directly in the host. | baldaworks/prism |
| [vigiles](https://agentpluginsdirectory.com/plugins/vigiles) | Verify CLAUDE.md/AGENTS.md references, compile typed specs, and test the agent harness | zernie/vigiles |
| [retro](https://agentpluginsdirectory.com/plugins/retro) | LLM-driven session retrospection. Detects friction in agent sessions and materializes learnings into correct destinations (personal rules, project rules, skill PRs, checkpoints, harness artefacts). | netresearch/retro-skill |
| [ledger-memory](https://agentpluginsdirectory.com/plugins/ledger-memory) | Ledger-backed persistent memory for coding agents: append-only facts with retraction vaccines, scars, and a generated MEMORY.md projection | prime-radiant-inc/ledger-memory |
| [graphban](https://agentpluginsdirectory.com/plugins/graphban) | Graphban fleet roles for Cursor. Mint a wave in the Fleet view for the MCP config; this ships the agents that use it. | asc-me/graphban |
| [mcp](https://agentpluginsdirectory.com/plugins/mcp) | LingTai's read-only MCP registry signpost and its owned mcp-manual Agent Skill. | Lingtai-AI/lingtai-kernel |
| [mcp-server-patterns](https://agentpluginsdirectory.com/plugins/mcp-server-patterns) | Reference patterns for designing, evaluating, integrating, and debugging MCP servers without changing the active MCP configuration. | hetaoBackend/MiniMax-Code-Plugins |
| [starlight-foundry](https://agentpluginsdirectory.com/plugins/starlight-foundry) | Design portable skills and bounded agent systems, with an optional compile-and-proof handoff to a Starlight Foundry runtime. | frankxai/Starlight-Intelligence-System |
| [cowork-onboard](https://agentpluginsdirectory.com/plugins/cowork-onboard) | Guided setup for Claude Cowork: confirms your workspace folder, connects your tools, builds your context files (about you, your voice, how you work), and creates working folders that match your job. | aiwithremy/cowork-onboard |
| [orrery](https://agentpluginsdirectory.com/plugins/orrery) | Configurable cross-client architect orchestration with lazy setup, exact user-selected native roles, risk-routed Astra and Terra implementation lanes, content-addressed tool-surface consent, transactional adapter installation, and a separate explicit Codex Luna app-task lane. | DivyamTalwar/ORRERY |
| [jonhill90-skills](https://agentpluginsdirectory.com/plugins/jonhill90-skills) | Jon Hill's public collection of portable Agent Skills: self-contained, model- and harness-agnostic instructions an AI coding agent loads on demand. | jonhill90/skills |
| [kibi](https://agentpluginsdirectory.com/plugins/kibi) | Repo-local, per-branch, queryable knowledge base. Portable Agent Plugin packaging Kibi's Agent Skills and MCP server. | Looted/kibi |
| [mora](https://agentpluginsdirectory.com/plugins/mora) | Local-first memory skills and MCP tools for grounded recall, briefs, and governed capture. | pyranthus-hq/mora |
| [maestria](https://agentpluginsdirectory.com/plugins/maestria) | Portable maestria engineering methodology delivered as Agent Skills for compatible clients. | agustinusnathaniel/maestria |
| [roca](https://agentpluginsdirectory.com/plugins/roca) | Local semantic memory for AI agents. | thellmwhisperer/la-roca |
| [skills-board](https://agentpluginsdirectory.com/plugins/skills-board) | Search your team's Skills Board library over MCP and get the install command for a saved skill or a published collection. | TommyBez/skillsboard |
| [toughtongue](https://agentpluginsdirectory.com/plugins/toughtongue) | Build, refine, and analyze Tough Tongue AI voice agents for tough conversations, agents that automate them (sales calls, lead qualification, demos, screening, booking) and agents that train you for the ones you handle yourself (negotiations, interviews, coaching). Create scenarios, place phone calls, schedule meeting bots, and analyze sessions. | tough-tongue/toughtongue-skills |
| [agy](https://agentpluginsdirectory.com/plugins/agy) | Antigravity CLI (agy) plugin for review, rescue, and autonomous agent workflows. | iicmaster/antigravity-plugins |
| [godmode](https://agentpluginsdirectory.com/plugins/godmode) | Your coding agent says "done." Godmode is how you know: a local, tamper-evident evidence ledger of what it did, claimed, and verified, with gates and a completion bar enforced in hooks at runtime on hosts where the hook is live-proven (see the host table). Zero deps, zero network. | AIimagined/Godmode |
| [orq](https://agentpluginsdirectory.com/plugins/orq) | Agent skills for building, deploying, evaluating, and monitoring LLM pipelines on the orq.ai platform. | orq-ai/assistant-plugins |
| [portable-agent-skills](https://agentpluginsdirectory.com/plugins/portable-agent-skills) | Agent workflow skills that behave the same in Claude Code and Codex CLI, with a portability contract enforced in CI. | rosslevinsky/portable-agent-skills |
| [prompt-optimizer](https://agentpluginsdirectory.com/plugins/prompt-optimizer) | Clarify and optimize prompts for GPT-6 Astra, GPT-5.6, Claude Sonnet/Opus/Fable, Gemini, Kimi, GLM, and DeepSeek-V4, plus Claude model selection and Astra Skills/AGENTS.md audits. | IchenDEV/prompt-optimizer-plugins |
| [agent-harness](https://agentpluginsdirectory.com/plugins/agent-harness) | Use when making a repo agent-ready, verifying harness consistency, checking for documentation drift, bootstrapping harness infrastructure (AGENTS.md as index, docs/ structure, CI verification, enforcement mechanisms), or auditing repo agent-readiness maturity level. | netresearch/agent-harness-skill |
| [correctionguy](https://agentpluginsdirectory.com/plugins/correctionguy) | Agents often drift and waste time on the wrong work. Correction Guy watches from the sidelines and steers them back on track. | correctionguy/correctionguy |
| [mental](https://agentpluginsdirectory.com/plugins/mental) | Never reconstruct where you left off. Local-first continuity for you and your coding agents, resume, decisions, and what's still in the air. CLI, MCP, and Agent Skills for Cursor, Claude Code, Copilot, and Codex. | afaraha8403/mental |
| [ngautopilot-core](https://agentpluginsdirectory.com/plugins/ngautopilot-core) | Core NgAutoPilot workflows for project intake, stack detection, routing, compatibility gates, and risk assessment. | janpereira-dev/ngAutoPilot |
| [steering](https://agentpluginsdirectory.com/plugins/steering) | Compact conversation-steering skills for changing direction, explaining decisions, asking for clarity, answering questions without implied action, finishing punted work, delegating research to a subagent, tightening prose, executing decisively, rethinking code architecture, and raising frontend quality. | stbenjam/skills |
| [a2acli](https://agentpluginsdirectory.com/plugins/a2acli) | CLI and agent skills for the A2A protocol: drive a2acli to discover/invoke/monitor A2A agents, and build/audit A2A-compliant services. | ghchinoy/a2acli |
| [admit-bench](https://agentpluginsdirectory.com/plugins/admit-bench) | Admissibility gates for agents that act on physical plants. Check a proposed action against evidence, authority, procedure, and projected physics before it executes. | Refiant-Inc/admit-bench |
| [agent-plugins](https://agentpluginsdirectory.com/plugins/agent-plugins--peter-gy) | Ship Agent Plugins with Python packages and inspect their installed files. | peter-gy/agent-plugins |
| [dialectic](https://agentpluginsdirectory.com/plugins/dialectic) | Configuration-first multi-agent design debate. Agents with different roles (architect, security, performance, simplicity,...) run structured debate rounds and a judge decides when convergence is reached. | slior/dialectic-agentic |
| [gepa-omni](https://agentpluginsdirectory.com/plugins/gepa-omni) | Optimize scorable prompts, code, configs, schemas, SQL, regexes, and agent instructions with GEPA's Omni portfolio and fresh continuation workflow. | Qredence/gepa-omni |
| [pigeonhole](https://agentpluginsdirectory.com/plugins/pigeonhole) | A wall of mail slots for parallel coding agents. Each worktree gets a pigeonhole; agents leave each other notes and post what they are working on. No server, no daemon, no MCP. | Baukebrenninkmeijer/pigeonhole |
| [skill-authoring](https://agentpluginsdirectory.com/plugins/skill-authoring) | Write documents for agents, analyze a skill, prune the prose that changes no behavior, and split broad references into focused files | staticaland/skills |
| [skill-lifecycle](https://agentpluginsdirectory.com/plugins/skill-lifecycle) | Create, convert, and generate agent skills from prompts and pull requests. | PlagueHO/plagueho.copilot |
| [summon](https://agentpluginsdirectory.com/plugins/summon) | Cross-vendor sub-agent broker with structured envelopes, council, governed deliberation, and authenticated local browser surfaces; optional MCP facade and provider drivers (CLI + openai-compat + arkcli). | Nafjan/summon |
| [a2ahub](https://agentpluginsdirectory.com/plugins/a2ahub) | Reliable handoffs between autonomous agents, using a Git repository both sides can inspect. | ydnikolaev/a2ahub |
| [agent-discipline](https://agentpluginsdirectory.com/plugins/agent-discipline) | trigger: edits without reading, unverified completion claims, weakened tests, dead code. avoid: skipping verification, deleting assertions, leaving unused code. | open-coder-ai/chock-catalog |
| [agent-looper](https://agentpluginsdirectory.com/plugins/agent-looper) | Portable Agent Plugins skills for designing and running Agent Looper fix-until-green cycles. | dancingteeth/agent-looper |
| [agent-skillopt](https://agentpluginsdirectory.com/plugins/agent-skillopt) | Create review-gated portable Skill packages for coding agents. | naipi11/Agent-SkillOpt |
| [all-my-friends-are-agents](https://agentpluginsdirectory.com/plugins/all-my-friends-are-agents) | Discover authenticated rooms and run durable, bounded consultations over MCP. | virusimmortal00/AllMyFriendsAreAgents |
| [maccing](https://agentpluginsdirectory.com/plugins/maccing) | Maxxing skills for coding agents: an engineering doctrine (dx for design priorities, writing-code for naming/modeling/organizing/UI/research), the reasoning operating manual, a database group (database-mapping binds a schema to generic roles, database-ops governs production data), growth (Google/Meta/TikTok Ads + WhatsApp via YCloud), aside (site skills driven through the Aside browser: Magnific, Shopee Seller Centre), a Notion API engineering reference with a bundled self-hosted notion MCP server, and a self-hosted Google Workspace MCP server (Calendar, Gmail, Drive, Docs, Sheets, Slides, Forms, Tasks, Chat, Contacts). | andredezzy/maccing |
| [maintainerd-core](https://agentpluginsdirectory.com/plugins/maintainerd-core) | Foundation for the maintainerd maintainer toolkit. Ships bootstrap (generates a repo's.claude/maintainerd.json config contract and starter guidelines), doctor (validates that setup, config, paths, commands, labels, guidelines, rosters, the coverage ratchet, and, with --profile, reports a repo's drift from a fleet's repo standard), and new-repo (creates or adopts a repo against that standard), plus the canonical config and profile schema references that every other maintainerd plugin reads. | Vycari/maintainerd |
| [ncp](https://agentpluginsdirectory.com/plugins/ncp) | NCP: an agent-to-agent memory bus over MCP. Bounded, trust-weighted context assembly, durable cross-session memory, and directed whispers for multi-agent systems. | kulkarni2u/neural-context-protocol |
| [nelos](https://agentpluginsdirectory.com/plugins/nelos) | Plan complex Codex work into safe, dependency-aware parallel slices. | virusimmortal00/nelos |
| [reelier](https://agentpluginsdirectory.com/plugins/reelier) | Ships two Agent Skills and nothing else: reelier-replay freezes a repeatable tool-call job into a deterministic replay with a receipt per run, and reelier-write-safety covers bounding an agent's writes before you grant them. Skill-only package: it includes no MCP servers. | seldonframe/reelier |