LLM Mart Basic

Runs 14 numbered engineering protocols in one pack — brainstorm, spec, plan, scaffold, TDD red-green-refactor, systematic debugging, refactoring, code review, performance, security, docs, git hygiene, release checklist, postmortem. Use when the user says "build this feature prope

Delivers a ruthless, structured critique of any screen, mockup or site — scores hierarchy, spacing rhythm, contrast, typography pairing and color discipline /10 with evidence, detects clichés (purple gradients, glassmorphism-by-default, emoji soup, cookie-cutter heroes), and rank

Organizes tax season — an organizer, not tax advice: a document checklist by category (income, expenses, assets, payroll, prior filings), an expense-category sweep that flags plausibly missed deductions in generic jurisdiction-agnostic categories, a quarterly-estimate calendar te

The company audits its own payroll — tracks AI token spend per department and mission, estimates costs from session data or telemetry, sets budget alerts and writes the monthly cost memo. Use when the user says "how much is this costing me", "token spend", "AI budget", "cost per

Builds a complete CSS motion system — duration and easing tokens (fast 120ms micro-feedback, base 200ms, slow 320ms entrances; standard, decelerate and spring curves), enter/exit/emphasis patterns, stagger rules, and prefers-reduced-motion fallbacks — delivered as a copy-paste CS

Ten-minute NDA triage — classifies an incoming NDA as GREEN (sign under standard delegation), YELLOW (targeted fixes, listed), or RED (full review). Screens mutuality, term and survival, definition breadth, embedded non-solicits or non-competes, missing standard carve-outs, resid

Builds an end-to-end UI system for a product — design tokens (color scale, type scale, spacing, radii, shadows), a component inventory covering every interaction state, a layout grid, and WCAG contrast checks — emitted as CSS variables plus a component spec doc. Use when the user

Explains budget-vs-actual or period-over-period variances: sets a materiality threshold first, builds the variance table in dollars and percent, decomposes drivers (price, volume, mix, timing, one-offs), draws a bridge waterfall, and writes the so-what per material line with fore

Vendor agreement status check — inventories what exists versus what is needed (MSA, DPA, SOW, SLA, insurance certs, security review), builds a gap analysis table, runs an expiration and renewal radar with dates and notice windows, notes surviving obligations, and delivers an onbo

Ingests 5–20 of the user's writing samples and distils a reusable voice-profile.md — signature phrases, sentence-length distribution, opener/closer habits, punctuation quirks, vocabulary do/don't lists, tone sliders, and three calibration paragraphs with self-checks. Other skills

Turns any idea into a live single-file HTML prototype in minutes — inline CSS/JS, CDN-only dependencies (cdnjs), mobile-first, seeded with believable fake data, interactive states wired — ready to open in a browser or paste as a Claude artifact. Use when the user says "prototype

Browser-tests a local webapp end to end — starts the app, installs Playwright if missing, writes a spec for the critical path plus edge cases, runs headless, captures screenshots, console and network logs on failure, and reports a pass/fail table with repro steps. Degrades to cur

Designs and tests YouTube thumbnails — 3–5 concept briefs covering composition, face or object, a 3-word-max overlay, and colour contrast against YouTube's UI, each run through a curiosity check, a mobile legibility test at 168×94 px, and a /10 scoring rubric, ending in a verdict

Pre-implementation exploration: deep interview, approach comparison, design doc. Use when exploring a vague feature idea, clarifying ambiguous requirements, or comparing approaches before coding. For the full workflow, use the ia-brainstorm command (Claude Code).

C patterns for systems code, libraries, and native extensions: module layout, function decomposition, status-enum errors, memory safety, undefined behavior, and performance measurement. Use when writing, reviewing, refactoring, or debugging C, working with malloc lifetimes, buffe

Structured code reviews with severity-ranked findings and deep multi-agent mode. Use when performing a code review, auditing code quality, or critiquing PRs, MRs, or diffs. For the full multi-agent workflow, use the ia-review command (/ia-review in Claude Code).

Modern C++ patterns: RAII and ownership, rule of zero/five, exceptions and error handling, API and ABI boundaries, templates, and CMake tooling. Use when writing, reviewing, refactoring, or debugging C++, working with smart pointers, move semantics, memory leaks, template errors,

Systematic root-cause debugging with verification. Use for errors, stack traces, broken tests, flaky tests, regressions, or anything not working as expected. For validating bug reports before fixing, use bug-reproduction-validator agent.

Visual design and aesthetic direction for frontend interfaces. Use when building web pages, landing pages, dashboards, Next.js server components, or applications where visual identity matters. For React patterns and testing, use react-frontend.

Manage Git worktrees for isolated parallel development. Use when creating, listing, switching, or cleaning up git worktrees, or when needing isolated branches for concurrent reviews or feature work.

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

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.