LLM Mart Basic

Executes joiner, mover and leaver processes — provisioning, group membership, access changes on role change, and complete deprovisioning. Use this to set up or fix joiner-mover-leaver, deprovision someone completely, clean up accumulated access, audit group membership, or find ac

Tracks hardware and software assets through their life — procurement, ownership, licensing, refresh, and disposal. Use this to build an asset register, prepare for a software audit, plan a refresh cycle, control license spend, or dispose of equipment safely.

Designs and operates the corporate network — segmentation, remote access, wireless, DNS and addressing, and diagnosing network problems. Use this to segment a network, set up or fix remote access, diagnose intermittent connectivity, plan addressing or DNS, or assess whether the n

Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or w

Runs servers and corporate systems — patching, configuration baselines, change control, capacity, and the routine that prevents incidents. Use this to establish a patching cadence, standardize server configuration, plan a maintenance window, decide change control for infrastructu

Defines and applies visual brand — logo usage, palette, typography, imagery direction, and the guidelines that keep expression consistent across product and marketing surfaces. Use this to establish a brand from scratch, audit whether an existing brand is being applied consistent

Owns what gets built and why: product strategy, roadmap, discovery, user experience, and the definition of success for each release. Use this to decide what to build next, to cut scope, to turn a business goal into a product bet, to judge whether a feature is worth its cost, or w

Applies a deliberate visual direction to an interface — minimalist editorial, industrial utilitarian, or high-polish commercial — each with its own type scale, palette behavior, surface treatment, and motion. Use this when a product needs a point of view rather than defaults, whe

Builds and maintains the design system a product is assembled from — tokens for color, type, spacing and elevation, component contracts, and the rules that keep them coherent as the product grows. Use this when starting a new interface, when screens have drifted apart visually, w

Raises the visual and interaction quality of an interface — layout, hierarchy, type, spacing, density, and the details that separate a considered product from a generic one. Use this when a screen works but looks unfinished or default, when a layout feels crowded or arbitrary, wh

Upgrades an existing interface to a higher standard without rebuilding it — auditing what is there, identifying what reads as generic or unfinished, and sequencing changes by impact. Use this when a product works but looks dated or default, when a redesign is being considered, wh

Designs slide decks, one-pagers, and marketing graphics that carry an argument rather than decorate one. Use this to build or fix a pitch deck, board deck, or conference talk; to design a banner, social graphic, or one-pager; or when a deck is dense, unfocused, or being read alou

Audits a website, app, onboarding flow, or design for usability, conversion, and product problems, tying every finding to a business outcome and a severity. Use this to review an interface, diagnose low conversion or activation, find where users drop off, get structured product f

Produces design reference imagery before implementation — screen concepts, layout directions, and flows for web or mobile that make a verbal brief concrete enough to argue with. Use this when a brief needs visualizing before anyone builds, when comparing layout directions, when h

Applies decision science and cognitive bias research to marketing and product decisions — how people actually choose under uncertainty, and how framing, defaults, sequencing, and social context change behavior. Use this to diagnose why a well-argued offer is not converting, to st

Captures how a person or brand actually writes and turns it into reusable voice instructions every other content skill draws from. Use this before drafting any content for a new brand or client, when output keeps coming back sounding generic, when several writers need to sound li

Runs content as an operation — the production pipeline, editorial calendar, repurposing engine, competitive content intelligence, and audits of what already exists. Use this to build or fix a content production system, plan a calendar, decide how one piece becomes many, rank cont

Owns brand, demand generation, content, communications, and how the market understands what the business does. Use this to set marketing strategy, allocate budget across channels, decide positioning and messaging, judge whether a campaign is worth running, diagnose why demand has

Decides what content to make and why — topic territory, format mix, cadence, and how content connects to a business outcome rather than to traffic. Use this to plan a content program, choose topics, build an editorial calendar, decide which formats and platforms to commit to, or

Plans, runs, and synthesizes customer research — interviews, surveys, win-loss analysis, and message testing — into findings that change decisions. Use this when the customer is being guessed at, before positioning or a major launch, when churn or conversion has an unexplained ca

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 shard` forks a [checkpoint](checkpoint.md) into `--count` leases

`crabbox share` grants other people access to an existing lease through the

`crabbox ssh` resolves a lease and prints a ready-to-run `ssh` command for it.

`crabbox status` prints the current state of a lease: its slug, provider,

`crabbox stop` ends a single lease. For coordinator-backed and direct cloud

`crabbox sync-plan` prints the local sync manifest and its size hotspots

`crabbox tunnel` opens one foreground SSH local port-forward to a resolved

`crabbox unshare` removes sharing rules from a coordinator-backed lease. It is

`crabbox usage` reports lease cost and usage estimates from the broker, broken down by user, organization, or the whole fleet.

`crabbox verify` checks a signed run receipt produced by `crabbox run --attest`.

`crabbox vnc` prints (or opens) the connection details for a desktop-capable

`crabbox warmup` leases a box and waits until it is ready: it provisions (or

`crabbox watch` runs a command on a warm lease, then watches the local

Linux portal viewers default to **Match window**: only the connected controller

`crabbox whoami` calls the broker's `/v1/whoami` endpoint and prints the

Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.

Inspect ADR health read-only; optionally select one ADR with --adr N.

{{SKILL_ENTRY:decision-lifecycle}}

Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.

Lightweight Q&A about the project — answer from context and return, no routing, no state change.

Atom Agent, Open-Source Governed AI Agent Platform for Self-Hosted Automation

The agent engineering intelligence harness, optimized tools, memory system, subagents and mixture of models packages ⚚

Sesori iOS/Android app and the Sesori Bridge CLI — drive Claude, Codex, OpenCode, Cursor, Pi, OMP, Hermes coding sessions from your phone

🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.

Use ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers — OAuth login in the web UI, no API keys

Latitude is the open-source AI monitoring platform.

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

Official Model Studio CLI（阿里云百炼 CLI）built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.

Curated DeepSeek Harness (DSH) plugins, extensions, tools, skills, clients, runtimes, integrations, and verified references — English and Chinese.

Turn papers, code, and docs into presentation-ready, natively editable PPTX in Codex / Claude Code. Native charts and equations, speaker notes, click-build anim…

Grix : Work with agents like talking to people.

Local First Ai Agent. Optimized for Local Ai models. Long context window. Proper tools callings. Runs privately on your device.

Model Context Protocol server that integrates AgentQL's data extraction capabilities.

AI that ships your tickets.

Metadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.

An open-source, extensible, self-hosted agent workspace with multi-runtime support for Codex, Claude Code, and more, plus reusable local apps for custom interfa…

Open-source Windows desktop client and GUI for DeepSeek Harness — zero-setup installer with Codex, plugins, skills, SSH, mobile remote access, and 11 skins.

The open-source AI workbench for scientific research

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

A Fully free agentic browser driver for AI , few tools, full control, real stealth, top-tier token efficiency.