LLM Mart Basic

Audit JS/CSS/HTML feature usage against the project's declared Browserslist/supported-browser matrix using Baseline and caniuse status data, flag unguarded non-Baseline usage, and verify feature-detection or polyfill fallback coverage, with per-feature caniuse/Baseline lookups lo

Reviews Vite and Webpack build/chunking configuration and bundle-size composition for duplicate dependencies, unsplit vendor chunks, and tree-shaking failures, always version-labeling config since Vite 8 replaced Rollup-era manualChunks with Rolldown-based codeSplitting.

Reviews JavaScript/CSS bundle composition against explicit numeric budgets, evaluates route- and component-level code-splitting boundaries, and requires a CI-enforced budget before endorsing any size fix as resolved.

Review page-load resource sequencing, render-blocking CSS/JS, layout-shift sources, and Core Web Vitals (LCP/CLS/INP) budget adherence against the critical rendering path model, explicitly separating lab/synthetic measurement (Lighthouse) from field/real-user measurement (CrUX/RU

Review CSS for specificity and cascade-layer discipline, design-token (custom-property) conformance, and responsive strategy correctness (container queries vs. media queries), catching specificity wars, hardcoded-value token drift, and non-reflowing layouts that fail WCAG 1.4.10/

Reviews design-token source of truth and build pipelines for hardcoded-value drift and resolved WCAG 1.4.3/1.4.11 contrast compliance across theme variants (light, dark, high-contrast), grounded in the W3C Design Tokens format and current WCAG success criteria.

Reviews Playwright end-to-end test configuration -- fixtures, storageState/auth setup, CI sharding and parallelism, and toHaveScreenshot visual-assertion options -- for reliability and correct gating, grounded in current, version-specific Playwright API docs.

Statically review Next.js App Router caching surfaces -- route-level revalidate exports, cache-boundary directives on server functions reading cookies(), generateStaticParams on personalized routes, and Cache-Control/Vary response headers -- for defects that let one user's authen

Assess breaking-change and regression risk for a same-framework major-version upgrade (React, Next.js, Angular, Vue, or core build tooling), grounding every claimed breaking change in the framework's official release notes/migration guide, and separate upgrade-blocking issues fro

Review client-side authentication and session-management code for token-storage location, cookie-flag correctness, CSRF/open-redirect exposure, and OAuth/OIDC flow choice for browser-based apps against OWASP ASVS and Session Management Cheat Sheet guidance, with the OAuth-for-bro

Determines and reviews whether aggregation/shaping logic belongs in a Backend-for-Frontend layer versus client-side composition, and audits existing BFF boundaries for scope creep, duplicated aggregation logic, and leaked backend topology or pass-through authorization.

Sequence frontend specialist and red-team reviews for the 10 governed workflows (new feature, perf regression, a11y audit, security review, SSR/hydration bug, design-system change, framework migration, AI-generated code review, production incident, CWV failure) and issue a bindin

Review frontend source for DOM XSS sinks (innerHTML, dangerouslySetInnerHTML, v-html, document.write, eval-class APIs), verify actual attacker-reachable taint flow, and audit Content-Security-Policy and Trusted Types enforcement for real bypasses rather than header-presence check

Build a cost-to-serve model covering CDN egress, SSR/edge compute, image transformation, and CI build-minute spend for a frontend surface, and rank remediation options by dollar savings weighed against Core Web Vitals and security impact, without treating cost-cutting and securit

Route frontend governance tasks to the narrowest specialist or parallel team (max 4) from the frontend agent catalog. Use when you do not already know which frontend specialist handles the task. Not for direct frontend answers; Maestro classifies, dispatches, and hands off to fro

Build a phased, reversible plan to migrate or modernize a legacy frontend surface (jQuery/Backbone/AngularJS to a modern framework, CRA/Webpack to Vite, or a same-framework major-version bump) using strangler-fig sequencing with measurable exit criteria per phase, without default

Design or review browser-side Real User Monitoring instrumentation for Core Web Vitals (LCP, INP, CLS) using the web-vitals attribution build and distributed tracing via OpenTelemetry Web, enforcing lab-vs-field evidence labeling, sampling/cardinality sizing, and PII-in-telemetry

Reviews cross-cutting frontend architecture decisions (module boundaries, rendering topology, technology adoption) against a rewrite-averse, evidence-grounded standard before they are approved, producing an ADR-quality verdict rather than a stylistic opinion.

Reviews frontend test-pyramid shape, critical-path coverage, and flaky-test governance across unit, component, integration, and E2E layers (Vitest/Jest, Testing Library, Playwright/Cypress), loading framework references only when the task needs them.

Statically review GraphQL client configuration (Apollo Client, and urql/similar clients by analogy) for production-enabled devtools/introspection exposure, a normalized cache left uncleared across user sessions, missing persisted-query allowlisting against client-driven query abu

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

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…