---
title: "Agent Tooling Agent Plugins, page 3 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/3
last-updated: 2026-10-08
---

# Agent Tooling Agent Plugins, page 3 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 |
| --- | --- | --- |
| [sergeant](https://agentpluginsdirectory.com/plugins/sergeant) | An AI agent orchestration system for working across multi-repo projects, with specialized capabilities for cross-repo dispatch, wiki management, code review, and project-aware context loading. | callmeradical/sergeant |
| [ai-skills-plugin](https://agentpluginsdirectory.com/plugins/ai-skills-plugin) | Portable Agent Skills for AI-harness diagnosis, AGENTS.md guidance, prompt design, IDE-native agents, hooks, slash commands, workflow creation, skill authoring and upkeep, and Agent Plugin creation. | Starraider/ai-skills-plugin |
| [automated-assessment](https://agentpluginsdirectory.com/plugins/automated-assessment) | Systematic project assessment against checkpoint-enabled skills with scripted verification + LLM review | netresearch/automated-assessment-skill |
| [chock-mise](https://agentpluginsdirectory.com/plugins/chock-mise--open-coder-ai-2) | trigger: personalize the coding agent to its owner, adopt the owner's dialect, taste, habits and demeanor so it works like a trained twin of that developer. apply: the owner's chock-mise profile where present; defer to committed project standards where it is silent or conflicts. avoid: inferring personal identity or employer-confidential data, and overriding the project's own committed rules. | open-coder-ai/chock-copilot-plugins |
| [codex-workflow](https://agentpluginsdirectory.com/plugins/codex-workflow) | 사용자 의도를 먼저 판별하고, 제품·기능·연구 실험·버그에 맞는 서로 다른 승인 흐름을 적용하는 한국어 워크플로우입니다. | j-token/j-token-codex-workflow-kit |
| [ink-and-agency](https://agentpluginsdirectory.com/plugins/ink-and-agency) | Skills for writing, sprint work, codebase workflows, and neurodivergent-friendly executive-function support (ink), plus a multi-lens decision council (agency). | risadams/ink-and-agency |
| [memhub](https://agentpluginsdirectory.com/plugins/memhub) | XTrace MemHub team memory: search_memory / save_artifact / import_conversation MCP tools plus skills for setup, login, onboarding, artifact upload, session import, team-memory recall, session handoff, spec-driven development, Rulebook rule authoring (create-rule) and a team's first Rulebook, tested starter rules fitted to the repo, and rules proposed from CLAUDE.md + past sessions (start-rulebook), and PR babysitting. A rule lives in a RULEBOOK: a container with its own membership, so it reaches exactly the people that book binds; the authoring skills resolve which book it lands in and offer to create one when there is none. Session auto-capture ships through the host-native plugin layer (hooks are outside the Agent Plugins spec). Session ↔ PR linking: after a call that addresses GitHub (`gh pr …`, a `curl`/`gh api` REST request, or a GitHub MCP tool) whose output names exactly one pull request, a PostToolUse hook asks the backend one question and injects one instruction, a session that ran `gh pr create`, or the GitHub MCP create tool, links itself unconditionally (opening it is work the session did, and a PR has many sessions), while every other GitHub call, a hand-rolled `curl` POST included, leaves the authorship judgment to the agent, and an org with no GitHub integration is told once that connecting it is what links sessions to shipped code. The hook is stateless apart from one short-lived negative answer (an enabled org with GitHub disconnected, cached 30 minutes per credential, and never inferred from a reply that merely says the feature is off) and degrades to silence on every failure. Two skills complete it: link-pr (link this or a named session by hand, also the answer for a PR opened by a script or CI helper, which is deliberately not detected) and find-contributing-sessions (map your own unlinked PRs, or the ones you name, to the sessions on this machine that wrote their code: scan local session history once, rank the candidates per PR by the evidence that matched, and link the ones you approve). The agent records ONE work type for a pull request it links (feat, fix, chore, docs, perf, refactor, other), and only when the PR has none yet, the first label is permanent, and asking again would cost the link, not just the type. Spec workflows: spec-work guides implementation, spec-check freshly reviews changes, and spec-maintain offers local/cloud bootstrap and reviewable Git or Brain proposals through the shared spec entry point. A companion animal draws what the plugin is doing in the band above the prompt, one per session picked from its session id (/goose, /hippo, /penguin and /shiba switch it for the session; `always` pins one for every session): asleep while the session is idle, awake and watching while Claude answers or the person types, and up announcing each Rulebook rule that fires, crossly when one blocked the call, or presenting a rule the harness just proposed with Activate / Reject / Later buttons (activating takes a rulebook admin; the animal says so to anyone else). Clicking the ♥ beside it pets it, and a proposal's rule↗ opens that rule in MemHub Studio. It needs Claude Code's function-hook runtime, which /memhub:companion turns on and persists. | XTraceAI/agent-plugins |
| [plugkit](https://agentpluginsdirectory.com/plugins/plugkit) | Official agent-plugkit maintenance plugin | agent-plugkit/plugkit-marketplace |
| [precise-terms](https://agentpluginsdirectory.com/plugins/precise-terms) | Transform verbose instructions into concise prompts and canonical technical terms while preserving every stated requirement. | andydrewie/precise-terms |
| [quantitative-grounding](https://agentpluginsdirectory.com/plugins/quantitative-grounding) | Add decision-useful quantitative structure for scale, comparison, likelihood, economics, uncertainty, and consequential empirical claims without numerical theater or false precision. | andydrewie/quantitative-grounding |
| [rementum](https://agentpluginsdirectory.com/plugins/rementum) | Load and save durable project knowledge through seven Rementum MCP tools. | rementum/rementum |
| [savestate-memory](https://agentpluginsdirectory.com/plugins/savestate-memory) | Encrypted portable agent memory via SaveState MCP | savestatedev/savestate |
| [srinitude-skills](https://agentpluginsdirectory.com/plugins/srinitude-skills) | Portable Agent Skills and read-only local tools. | srinitude/skills |
| [swarm-pi-code-plugin](https://agentpluginsdirectory.com/plugins/swarm-pi-code-plugin) | Portable Pi workflows with durable Host Assistance, discovery, review, and isolated implementation. | JiaWeiXie/swarm-pi-code-plugin |
| [wc-view](https://agentpluginsdirectory.com/plugins/wc-view) | Interactive local workspace for reviewing and iterating on Markdown and agent-generated HTML artifacts | astrojose/wc-view |
| [agent-kit](https://agentpluginsdirectory.com/plugins/agent-kit) | Portable agent skills for software development workflows | rakaadi/agent-kit |
| [ai-employee-builder](https://agentpluginsdirectory.com/plugins/ai-employee-builder) | Connect AI Employee Builder across supported hosts and optionally keep a private, local cross-runtime improvement ledger. | the2hourclo/aieb-thin-plugin |
| [ai-toolkit](https://agentpluginsdirectory.com/plugins/ai-toolkit) | Optional post-install Agent plugin manager for Copilot customizations from teggr/ai-toolkit, focused on inventory, updates, and reconciliation. | teggr/ai-toolkit |
| [buddy-agent-harness](https://agentpluginsdirectory.com/plugins/buddy-agent-harness) | Initialize standards-based agent configuration across agent harnesses | repobuddy/buddy-agent-harness |
| [building-with-zep](https://agentpluginsdirectory.com/plugins/building-with-zep) | Build and configure applications that use Zep, agent memory built on temporal Context Graphs. Bundles the building-with-zep skill and the Zep documentation MCP server. | getzep/building-with-zep-plugin |
| [codex-reset-credit](https://agentpluginsdirectory.com/plugins/codex-reset-credit) | Check Codex reset credits and local rate-limit reset windows without exposing authentication secrets. | heyNag/charms |
| [corrobore](https://agentpluginsdirectory.com/plugins/corrobore) | Portable skills and MCP tools for using Corrobore as evidence-backed structured working memory and CTI validation substrate. | Estance-Labs/corrobore |
| [cuemap](https://agentpluginsdirectory.com/plugins/cuemap) | Repository-aware code memory and context for AI coding agents. | cuemap-dev/agent-plugin |
| [deep-state-of-mind](https://agentpluginsdirectory.com/plugins/deep-state-of-mind) | Deep State of Mind (DSOM) Sovereign AI Agent Cognitive Architecture, Open Knowledge Format (OKF), and Model Context Protocol (MCP) toolset. | linuxmalaysia/deep-state-of-mind-for-my-ai |
| [esment](https://agentpluginsdirectory.com/plugins/esment) | Esment memory for your AI assistant: recall before you answer, save what matters. | xm1000z/esment-plugins |
| [field-notes-mcp](https://agentpluginsdirectory.com/plugins/field-notes-mcp) | Anonymous message board for AI agents: read, search and leave short notes over HTTP or, when HTTPS is blocked, over DNS. No account needed. | mq1n/field-notes-mcp |
| [grok-bot-rooms](https://agentpluginsdirectory.com/plugins/grok-bot-rooms) | Hosted Grok Bot assistant registry with rooms: first-load welcome prompt for lobby, register approved assistants, check into general/game rooms, room slash commands (/join /leave /whos-here /who), and host-and-invite so colleagues share one host's lobby. Also includes publisher marketplace skills (submit path, scaffold, compatibility). Skills + remote MCP; no IDE-only components. | mrlynn/grok-bot-plugin-example |
| [hu-<team>](https://agentpluginsdirectory.com/plugins/hu-team) | Team-specific HU agent skills. | uashogeschoolutrecht/hu-agent-framework |
| [kyberion-agent-plugin](https://agentpluginsdirectory.com/plugins/kyberion-agent-plugin) | Portable Agent Plugins package for Kyberion governed operations, knowledge access, mission control, approvals, and audit workflows. | famaoai-creator/kyberion |
| [linear-spec-plugin](https://agentpluginsdirectory.com/plugins/linear-spec-plugin) | Spec-driven project execution pipeline backed by Linear. Same skills and agents as spec-plugin, but writes specs, stories and validation to Linear via GraphQL while keeping reasoning artifacts on disk. | nexaedge/nexaedge-marketplace |
| [matryoshka-plugin](https://agentpluginsdirectory.com/plugins/matryoshka-plugin) | 플러그인 컴포넌트를 만드는 플러그인: skill, agent 생성기 | wonjiko/claude-toymarket |
| [okf-agent-graph](https://agentpluginsdirectory.com/plugins/okf-agent-graph) | OKF Agent Graph Engineering Runtime (AGER): author multi-agent loop graphs as OKF and reverse-engineer existing agent stacks. Multi-host bindings and write isolation. | SpillwaveSolutions/okf-agent-graph |
| [okf-graph-eng](https://agentpluginsdirectory.com/plugins/okf-graph-eng) | OKF graph engine: validate, walk, pack, and impact-analyze Git-native knowledge graphs. Owns Catalog and ContextPack. Domain nouns live in PKC, SAC, DEKC, and AGER. | SpillwaveSolutions/okf-plugin |
| [ollama](https://agentpluginsdirectory.com/plugins/ollama) | agent-tools-runtime plugin for Ollama's REST API: list/pull models, single-shot generate/chat completions, and async jobs (start_generate/start_chat + job_status) for calls that take a while, against a local server or Ollama Cloud. | MauricioPerera/agent-tools-runtime |
| [pstack](https://agentpluginsdirectory.com/plugins/pstack--0x7067) | Agent Skills for rigorous, parallelizable engineering work. | 0x7067/pstack |
| [qi](https://agentpluginsdirectory.com/plugins/qi) | Work on qi: a local-first text river running Granite 4.1, with research that verifies its own citations and a standalone Mac app. Covers setup, editing the codebase, the model cards, adapter conversion, the research process, and shipping. | qubie-org/qi |
| [second-brain-core](https://agentpluginsdirectory.com/plugins/second-brain-core) | Shared foundation for Spillwave ContentPack plugins: OKF schemas, typed edges, deterministic write helpers, progressive-disclosure packing, and write isolation. | SpillwaveSolutions/second-brain-core |
| [skill-creator](https://agentpluginsdirectory.com/plugins/skill-creator--torumakabe) | Create, validate, package, and locally verify Agent Skills for GitHub Copilot. | torumakabe/copilot-agent-plugins |
| [skilla](https://agentpluginsdirectory.com/plugins/skilla) | Install, update and remove Agent Skills and Agent Plugins from git repositories with the skilla CLI, instead of vendor-specific plugin commands. | junior/skilla |
| [skizl](https://agentpluginsdirectory.com/plugins/skizl) | Full lifecycle manager and optimizer for agentic skills, author, densify into micro-kernels, pack, unpack, pin, sym, diff, snapshot, bump, archive, fork, publish, and git-guard. | alexsmedile/skizl |
| [trace](https://agentpluginsdirectory.com/plugins/trace) | Viewer for Iva's Trace: the turn journal as a live schema, a turn feed and a replay. | smixs/iva-plugins |
| [unabyss](https://agentpluginsdirectory.com/plugins/unabyss) | Personal and company context from Unabyss, available to your agent through the Unabyss MCP server. | Unabyss/unabyss-vellum |
| [adaptive-sdd](https://agentpluginsdirectory.com/plugins/adaptive-sdd) | Guide adaptive specifications, resumable evidence-backed delivery, and portable Project Memory. | JonC613/adaptive-sdd |
| [advisor-profiles](https://agentpluginsdirectory.com/plugins/advisor-profiles) | Named advisor profiles from WATCHDOG.yml, reviewed by a secondary model after each completed agent turn. | emo-eth/skills |
| [agency-agents](https://agentpluginsdirectory.com/plugins/agency-agents) | 數位行銷代理商專用 Agent 集合，涵蓋工程、設計、行銷、銷售、測試等 14 個專業類別，共超過 140 個專業 Agent。 | RDCrystalLab/agentic-plugins |
| [agent-aware-cli](https://agentpluginsdirectory.com/plugins/agent-aware-cli) | Best practices and architectural guidelines for CLI tools optimized for both human users and AI coding agents. | ghchinoy/agent-skills |
| [agent-builder](https://agentpluginsdirectory.com/plugins/agent-builder) | Creates, evaluates, and packages confirmed capabilities as one-agent-with-licensed-skills plugins. | tiennguyentt/agent-plugins |
| [agent-computer-use](https://agentpluginsdirectory.com/plugins/agent-computer-use) | Native macOS computer use and GPT Realtime voice control through CUAService. | ingpoc/agent-plugins |