LLM Mart Basic

Create, edit, and debug vanilla Minecraft 26.x and 1.21.x datapacks, including functions, advancements, recipes, loot tables, predicates, tags, and pack metadata. Use when the deliverable is a datapack file tree without Java or loader APIs.

Operate EssentialsX on Minecraft 26.x and 1.21.x servers, including configuration, permissions, economy, kits, warps, homes, and moderation. Use for EssentialsX administration, not plugin development or general server deployment.

Generate or edit Minecraft raster assets such as pack icons, promo art, concept textures, thumbnails, banners, and UI mockups. Use when the deliverable is a bitmap image rather than JSON, SVG, or code-native assets.

Create, modify, debug, or migrate Minecraft mods for current NeoForge or Fabric 26.x, legacy 1.21.x, and Forge 1.20.1. Use for loader-based gameplay code and assets; use minecraft-multiloader when one codebase must target both modern loaders.

Build and maintain Architectury-based Minecraft 26.x or 1.21.x mods that share one codebase across NeoForge and Fabric. Use only when both loaders are required; use minecraft-modding for a single-loader project.

Create, modify, and debug server plugins for current Paper 26.x on Java 25 or legacy Bukkit-derived 1.21.x servers on Java 21. Use for JavaPlugin APIs, events, commands, schedulers, configuration, PDC, and Adventure, not client mods or vanilla datapacks.

Create and debug Minecraft 26.x and 1.21.x resource packs, including pack metadata, textures, models, blockstates, item definitions, sounds, fonts, animations, and shaders. Use for client-side visual or audio assets without gameplay code.

Set up, operate, tune, and troubleshoot Minecraft Java 26.x and legacy 1.21.x servers across Paper, Purpur, Folia, Velocity, Fabric, and NeoForge. Use for infrastructure, backups, proxies, and live operations, not plugin or mod development.

Design and implement automated tests for current Minecraft 26.x or legacy 1.21.x mods and plugins using JUnit, MockBukkit, NeoForge Game Tests, or Fabric Game Tests. Use for test code and test execution, not release publishing or gameplay implementation.

Create and debug Minecraft 26.x and legacy 1.21.x world generation for datapacks, NeoForge, or Fabric, including biomes, dimensions, features, structures, and biome modifiers. Use for worldgen data or registration, not general gameplay systems.

Operate WorldEdit safely for Minecraft 26.x and 1.21.x selections, region edits, masks, schematics, brushes, terrain shaping, and rollback. Use for command-driven world editing, not plugin development or general server administration.

Analyze prompt-cache effectiveness for Claude Code usage from the Agent Monitor dashboard — cache hit rate (total_cache_read / (total_cache_read + total_input)), cache_write vs cache_read reuse, cache-read vs cache-write spend, and the sessions with the poorest reuse. Pulls token

Break down Claude Code costs using the Agent Monitor pricing engine. Shows per-model costs (input, output, cache_read, cache_write at $/Mtok rates), per-session costs, daily trends, and compaction baseline token recovery. Use when analyzing spending, comparing model costs, or pla

Break down Claude Code usage by model family (Opus / Sonnet / Haiku) from the Agent Monitor dashboard — each family's share of tokens, share of cost, and the spots where an expensive model is doing cheap work. Pulls per-model token and cost splits from /api/pricing/cost, current

Calculate a productivity score using actual Agent Monitor metrics — session completion rates, cache efficiency (cache_read vs input), compaction pressure (baseline tokens), turn velocity (turn_count / total_turn_duration_ms), tool success ratio (PreToolUse vs PostToolUse), and th

Generate a comprehensive session report with per-model token usage (input, output, cache_read, cache_write including compaction baselines), cost breakdown via the pricing engine, tool invocations, agent hierarchy, compaction events, API errors, turn durations, and thinking block

Analyze Claude Code usage trends over time using the Agent Monitor's analytics API — daily session counts, daily event counts, token volumes by type, model distribution, tool usage rankings, and agent/event type distributions across 365-day retention windows.

Run a full audit of the user's Claude Code configuration via the Agent Monitor Config Explorer API: counts per surface (user vs project), duplicate or overlapping skills and subagents, hooks that run shell commands, and which surfaces are read-only vs mutable. Reads /api/cc-confi

Inventory hooks across the user, project, and project-local settings plus the ~/.claude/hooks scripts directory — read through the Agent Monitor Config Explorer API — and flag hooks that POST to the network or run arbitrary commands. Reads /api/cc-config/hooks and /api/cc-config/

Audit the configured MCP servers (user + project scope) via the Agent Monitor Config Explorer API: transport (stdio vs http), command/args and env variable names, headers, and the source file each definition came from. Reads /api/cc-config/mcp. Use when reviewing MCP integrations

Fourteen posts of being wrong in production, compressed to checkboxes

Healthy nodes, a quiet network, 300 restarts in three days, and a latency budget measured in milliseconds

Discovery worked. Ping worked. Every TCP connection timed out, and later the tunnel only worked when someone had a terminal open.

Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.

A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.

A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.

None of the safety came from the model. It came from six boring habits.

Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.

Six hours in, one step left, everything green, and the incident that didn't happen

CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.

Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it

An API request routing a model's tool call through an approval gate to a remote MCP server

31 config keys, two audits, and why the first one was wrong in both directions

The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.

Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.

Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.

"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks

stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.

The most important rule wasn't about what I could change. It was about what I was allowed to display.

Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.

Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report.

Sanctioned lane for non-behavioral work — docs-only edits, dependency bumps, reverts. Type-scaled gates; no TDD demanded of prose.

{{SKILL_ENTRY:post-merge-cleanup}}

Show the codeArbiter command catalog — the public command list and what each routes to.

{{SKILL_ENTRY:commit-gate}}

Stop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation.

{{SKILL_ENTRY:context-check}}

{{SKILL_ENTRY:context-creation}}

{{SKILL_ENTRY:debug}}

{{SKILL_ENTRY:decompose}}

Verify the active host install, package, command ownership, enforcement{{IF:pi}}, wrapper self-test, and active-dispatch coverage gap{{ELSE}}, and harmless live-fire probe{{END}}. Read-only.

Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation.

Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.

Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store.

Read-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs. the prior 20-commit window.

Sanctioned, logged bypass of a gate or hard rule — one audit line, then proceed.

{{SKILL_ENTRY:finishing-a-development-branch}}

Zero-onboarding, read-only dry-run of the reviewer fleet against the current uncommitted diff. Predicts reviewers, runs the state-free secret scan, writes nothing.

Trim transcript clutter to extend session lifetime — analyze, prune a copy, or toggle the after-each-turn service. Dry-run by default; gains land at resume/compaction, not the current turn.

{{SKILL_ENTRY:decision-variance}}

Your car as a chat-room agent: Raspberry Pi 5 + dashcam + local AI. CodeWatch's sibling for the garage.

The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit log.

AI agent for Home Assistant — talk to your home, create automations in plain language, analyze cameras with face recognition, and get proactive anomaly alerts.…

A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first, cloud-ready for ma…

Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

Web & desktop (Electron) client for the OCTO open workplace — one React + TypeScript codebase shipping browser and PC surfaces, with first-class AI agent UX.

同花顺官方 A股金融数据服务，提供股票实时行情、历史行情、财务报表、指数、板块、涨停等数据，适用于 AI Agent、量化研究和应用开发，支持 API、MCP、CLI 和 Python。Official Tonghuashun (HiThink) A-share financial data service provi…

Open-source desktop SQL workspace for PostgreSQL, MySQL/MariaDB, SQLite and 15+ more databases like DuckDB, ClickHouse, Redis and Firestore. Built-in MCP server…

🤖 Local-assist BOSS Zhipin CLI for AI agents — search, welfare filtering, shortlist, JSON-envelope output; low-risk & compliant by default.

The local-first sidebar AI agent for ComfyUI — runs on your own Claude OR ChatGPT subscription (no API keys, no extra LLM costs). Drives your live graph: edits,…

Persistent memory for Claude Code — identity, context, and continuity across sessions

🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI…

A curated list of plugins, skills, MCP servers, patch/profile layers, orchestrators & UIs for DeepSeek Harness (DSH). Visualization · PPT · Coding · Agents · Lo…

World Memory Protocol.

Run your own organization of agents.

The most RAM efficient harness

AI-native, free, open-source alternative to Jira, Trello, ClickUp & Monday. Built for Scrum teams where humans and AI agents collaborate as equals — on the same…

Free open-source desktop app that scrapes JAV metadata and generates NFO + cover art for Jellyfin, Emby & Kodi. No Docker, no CLI — one-click install on Windows…

A cross-platform desktop app to manage Agent Skills in one place and sync them to multiple AI coding tools’ global skills directories — “Install once, sync ever…

天枢 (Tianshu) 是一个基于harness工程的终端编程智能体运行时（Tui X Gui），针对DeepSeek V4 做了前缀缓存工程优化（长会话实测稳态命中率 97–99%）和深度适配。它跳出了传统 AI 编程助手把大模型仅当成“工具”的局限，基于认知虚拟机 (CVM)、自感知层和信息素（Stigmergy…