LLM Mart Basic

Use when the user wants adversarial stress-testing of a proposed architecture, structure, or shape. Not for tasks that require source or remote-system changes.

Use when the user asks for a council, second opinions, or parallel investigation. Not for cross-examination of existing proposals: use cross-critique.

Use when independent proposals on a contested decision need cross-critique before choosing, reusing the original authors. Not for parallel multi-stance investigation: use council.

Use when one reviewer is not enough because failure modes are heterogeneous, or a claim needs cross-lens pressure before it ships. Not for collapsing a decision field: use converge.

Use when a current decision needs pressure-testing until the rationale is clear to a skeptic. Not for tasks requiring source or remote-system changes.

Use when a non-trivial decision sits under uncertainty and correctness matters more than speed. Not for patch review: use review. Not for plan attacks: use load-bearing-assumption-test.

Use when the user asks why a plan is wrong or says "poke holes in this". Not for tasks that require source or remote-system changes.

Use when one reviewer angle is insufficient or the user suspects a direction is tunnel-visioned or inherited its framing. Modes: artifact, direction. Not for source or remote-system changes.

Use when a workflow, plan, diff, or completed work cycle must be checked for practices that punish the project later. Not for source, remote, credential, publish, deploy, or irreversible changes.

Use when asking "overkill?", "elegant?", "audit", or "taste-test this", or setting a taste register. Not for tasks that require source or remote-system changes.

Use when product copy needs buyer-objection evidence collected through approved, consented outreach. Not for unsolicited outreach or survey design.

Use when the user wants the current jargon weather of a domain described without advocacy. Not for choosing a positioning move: use buzzword-hijack.

Use when a user wants to choose and execute a bounded positioning move that rides a jargon wave. Not for describing the jargon weather of a domain: use buzzword-analysis.

Use when asked to research a feature across competitor products or to analyze competitor release changelogs (mode: changelog), and publish a cited report.

Use when customer feedback, NPS, churn, email feedback, call transcripts, or voice-of-the-customer analysis needs a report over a time window.

Use when dogfooding a developer-facing product or workflow to produce an evidence-backed DX scorecard. Not for visual UI audit: use web-design-review.

Use when projecting cost, estimating BYO cost or spend, or sizing a deal. Not for remote, credential, publish, deploy, or irreversible changes.

Use when invoking /product-signal-pulse with an optional lookback window to query configured product signals. Not for credential, publish, deploy, or irreversible changes.

Use when asked to analyze a screen recording, voice capture, or meeting notes artifact for product feedback. Not for credential, publish, deploy, or irreversible changes.

Use when asked to draft launch or promotion copy for a shipped feature across channels via /release-promotion. Not for posting, publishing, scheduling, or committing, drafts only.

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.

`crabbox attach` follows the recorded events of an active coordinator run and

`crabbox azure` groups Azure provider setup commands. It currently has a single

`crabbox bench` records and reports local benchmark timing observations. It is a

`crabbox cache` inspects, purges, or warms package and build caches on a

`crabbox capsule` captures, replays, and tracks lightweight failure capsules.

Save the state of a lease, then restore it onto another box or fork it into a

`crabbox claims list` prints the lease claims stored on the current machine. It

`crabbox cleanup` sweeps direct-provider machines and local provider state that

`crabbox code` bridges a Linux lease's `code-server` workspace into the

`crabbox config` inspects and updates user configuration. It has three

`crabbox connect` resolves a lease and opens an interactive SSH session to it.

`crabbox cp` copies files or directories between the host and a Crabbox-owned

`crabbox desktop` drives a visible desktop session on a lease that was warmed

`crabbox doctor` runs a preflight before you commit to a long workflow. It is

`crabbox egress` gives a lease mediated outbound network: a lease-local browser

`crabbox events` prints the broker's event log for a recorded run.

`crabbox heartbeat` refreshes the idle deadline for one owned lease and prints

`crabbox history` lists recorded remote command runs from the broker. Each run is

`crabbox image` holds the trusted-operator controls for provider base images:

`crabbox init` onboards the current repository: it writes the minimal config

Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, multi-channel. Lightwei…

Open-source AI browser agent for web automation: a web browsing agent and computer-use agent in plain English. Browser MCP for Claude Code and Gemini CLI.

Agent-native trading terminal built on DeepSeek Harness. Crypto, US, CN and HK in one three-column GUI, 19+ hot-swappable connectors, dry-run by default with hu…

Open-source desktop and web coding agent with a first-party host and harness, durable sessions, model connections, streaming chat, and workspace tools.

OrcaReplay — Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.

A complete toolkit for connecting R and LLMs

OpenSRE — the memory-first AI SRE. Self-hosted incident investigation with episodic memory, knowledge graph, web console, Slack & Teams. opensre.in

A desktop AI coding assistant that works with your local projects. Ally helps you understand code, edit files, search a workspace, manage tasks, and complete de…

【在线免费使用】 简单快速将SQL或DBML转换为美观的ER图（支持 Agent Skill）/ The best SQL to ER Diagram converter (Support Agent Skill).

Operation-bound protection for autonomous AI agents: contain and verify operations before committing changes, understand intent and risk across long-running wor…

Local-first AI coding agent desktop: Electron + Rust host core + pi Agent Harness + user-installable plugins

Local-only Go static analysis engine with a built-in MCP server. Gives AI coding agents deterministic structural awareness: call graphs, impact analysis, symbol…

Self-hosted AI agent workspace with tool calling, MCP, multi-model routing, sandboxed execution, multi-agent workflows, and LLM-authored 3D character animation…

Automated TDD enforcement for Claude Code

High-performance platform for building websites, e-commerce, and web applications—with Native AI, JavaScript development, and a marketplace for portable sites a…

Autonomous AI-agent orchestration engine for job discovery with decision traces, tool adapters, and production-grade run control.

Token efficient Claude Code full Python rebuild. AI Coding Agent in 310K LoC Python.

OPC — One Person Company. A full team in a single Claude Code skill. Adaptive agent orchestrator with 21 built-in roles, 6 flow templates, and adversarial quali…

Open-source, secure environment with real-world tools for enterprise-grade agents.

MCP server for AI-powered GitHub project management — agent orchestration, PRD-to-issues pipeline, sprint planning, and multi-agent swarm coordination