LLM Mart Basic
@llm-mart · Joined Jun 2026
Imported from notque/vexjoy-agent/agents/base-instructions.md.
Zero-dependency combat visual upgrades: CSS particle replacement, Framer Motion combat juice, CSS 3D card transforms.
Data pipelines, ETL/ELT, warehouse frontend, dimensional modeling, stream processing.
Database frontend, optimization, query performance, migrations, indexing strategies.
Extract coding conventions and style rules from GitHub user profiles via API.
Python hook development for the Claude Code event-driven system and its telemetry store.
Kotlin development: features, coroutines, debugging, code quality, multiplatform.
Kubernetes and Helm: deployments, troubleshooting, cloud-native infrastructure.
MCP server development for local documentation access in TypeScript/Node.js and Go.
Use this agent when building a NextJS e-commerce site: shopping cart, Stripe payments, product catalogs, order management, and checkout flows
Use this agent when you need expert assistance with NodeJS backend API development: REST endpoints, authentication, file uploads, webhooks, middleware, and database integration
OpenSearch/Elasticsearch: cluster management, performance tuning, index optimization.
Web performance optimization: Core Web Vitals, rendering, bundle analysis, monitoring.
Perses observability platform: dashboards, plugins, operator, core development.
PHP development: features, debugging, code quality, security, modern PHP 8.x patterns.
Pipeline orchestration: scaffold multi-component workflows, fan-out/fan-in patterns.
Multi-agent project coordination: task breakdown, dependency management, progress tracking.
Prometheus and Grafana: monitoring, alerting, dashboard frontend, PromQL optimization.
Python development: features, debugging, code review, performance. Modern Python 3.12+ patterns.
OpenStack Python development: Nova, Neutron, Cinder, Oslo libraries, WSGI middleware.
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.
Use MCP Inspector to connect to local or remote servers, inspect capabilities, call tools, read resources, test prompts, and diagnose failures before release.
/lookup-contact
Lookup contact
Search for Autotask contacts by name, email, phone, or company
/my-tickets
My tickets
List tickets currently assigned to you with optional filtering
/reassign-ticket
Reassign ticket
Reassign a ticket to a different resource or queue
/search-products
Search products
Search the Autotask product catalog for products, services, or inventory items
/search-tickets
Search tickets
Search for tickets in Autotask PSA by various criteria
/time-entry
Time entry
Log time against tickets or projects in Autotask PSA
/update-ticket
Update ticket
Update fields on an existing Autotask ticket (status, priority, queue, due date)
/device-lookup
Device lookup
Find a device in Datto RMM by hostname, IP address, or MAC address
/resolve-alert
Resolve alert
Resolve an open alert in Datto RMM
/run-job
Run job
Run a quick job on a device in Datto RMM
/site-devices
Site devices
List all devices at a site in Datto RMM
/edit-doc-sections
Edit doc sections
Read, edit, and restructure sections of an IT Glue document
/find-organization
Find organization
Find an organization in IT Glue by name
/get-password
Get password
Retrieve a password from IT Glue (with security logging)
/lookup-asset
Lookup asset
Find a configuration item (asset) in IT Glue by name, hostname, serial number, or IP address
/search-docs
Search docs
Search IT Glue documentation by keyword or phrase
/account-summary
Account summary
Get a security posture summary for a RocketCyber customer account
/search-incidents
Search incidents
Search RocketCyber security incidents by account, status, severity, verdict, and date range
/find-secret
Find secret
Locate a Keeper record by description and return its UID and metadata without revealing any credential
/scope-audit
Scope audit
Report exactly what the connected Keeper KSM application can reach - folders, record counts, and record types - reading no credential values
Make any song you can imagine
39 views 0 likesLeading AI-powered video generation platform that specializes in creating hyper-realistic talking avatars
37 views 0 likesHermes Agent is an open-source, self-improving autonomous AI agent developed by Nous Research
36 views 0 likesKilo Code is a popular, open-source AI coding agent and "agentic engineering" platform designed to help developers build, refactor, and debug software faster
34 views 0 likesGeneral-purpose agent in one static Go binary. ReAct loop, ACP server for IDEs, OpenAI-compatible REST API with embedded web UI, Telegram gateway, cron schedule…
20 views 0 likesAutonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it.
20 views 0 likesTSP自托管、零运维的 A 股「选股 + 监控 + 回测」量化工作台 | 基于 TickFlow 数据源 | LLM能力驱使策略定制+个股分析+复盘 | 自由接入第三方数据源与个性化扩展数据 | 个人开源 ,非TickFlow官方项目
15 views 0 likesCurated, verified Agent Skills powered by ModelStudio.
18 views 0 likesRun Claude Code, Codex, Antigravity, Cursor Agent and OpenCode as one runtime — persistent sessions, multi-agent councils, an OpenAI-compatible endpoint, an MCP…
17 views 0 likespi had nothing (nothing), so I made something (something) — sorry mariozechner-senpai, I went ahead and lovingly soiled your pure pi for you. opinionated fork o…
14 views 0 likesA persistent workspace for development work that self-improves and continues beyond one session.
33 views 0 likesOpen-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.
20 views 0 likes📚 A zero-dependency, git-backed micro-lesson library for AI Agents to asynchronously share and search verified debugging experience. Python stdlib only. | http…
28 views 0 likesDeterministic, local-first memory and guardrails for AI coding agents with no LLM in the hot path.
31 views 0 likesDeterministic spec-orchestration for local LLMs in the pi coding agent — drives prompts through refine→research→grill→compose→critique, with bundled web/docs/fe…
20 views 0 likesNative Safari browser automation for AI agents. 97 tools via AppleScript — zero overhead, keeps logins, runs silently in background. Drop-in alternative to Chro…
32 views 0 likesAgent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.
15 views 0 likesGit for agent memory. Branches, diffs, PRs, and rollback for what your agents know.
32 views 0 likesMulti-Provider AI Gateway - No personal logs by design. Model autodiscovery, Failover groups, High availability, Android companion app, and more - "Because we h…
16 views 0 likesProduction-grade MCP server for MikroTik RouterOS with secure AI-native network automation.
28 views 0 likes