LLM Mart Basic

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

Review HTML markup and rendered DOM structure for correct native-element usage, valid heading/landmark hierarchy, and WAI-ARIA APG-conformant custom-widget patterns; produce a WCAG 2.2-grounded verdict with APG pattern citations for every custom interactive control, flagging anyt

Audit frontend code for internationalization readiness — externalized ICU MessageFormat strings, Intl-based date/number/currency/plural formatting, correct lang/dir attribute propagation, and RTL-safe CSS logical properties — before translation vendor engagement, with CLDR plural

Review JavaScript/TypeScript for event-loop and microtask/macrotask ordering correctness, unhandled Promise rejection paths, DOM event-listener and timer cleanup, and race-condition risk in rapid-repeated-async UI patterns, tracing actual browser scheduling semantics rather than

Inventory the hidden behaviors in a legacy jQuery/Backbone-era codebase — implicit global event delegation, direct DOM mutation outside any render cycle, plugin side effects, ad-hoc accessibility shims, and unsanitized HTML string building — that a mechanical framework port would

Reviews micro-frontend/module-federation boundary contracts for shared-dependency versioning safety, runtime isolation, and ownership clarity before adoption or extension of a distributed frontend architecture.

Reviews monorepo task-graph configuration (Turborepo tasks/caching, Nx task pipelines) alongside dependency and lockfile governance (pnpm catalogs, npm overrides, lifecycle-script risk) to prevent false-green CI from stale cache reuse and unpinned supply-chain exposure.

Statically review Next.js App Router Server/Client Component boundaries and Server Action data mutations for correct data-fetching placement, bundle-leak risk, and authorization-trust integrity, escalating client-trusted authorization to a security finding rather than a style not

Statically review Next.js App Router route segments and fetch() calls for rendering-mode (static/ISR/dynamic) and Data-Cache misconfiguration, escalating cross-user data leakage to a security finding rather than a performance nit.

Statically review Next.js middleware, Server Actions, next.config.js, and environment-variable files for four documented server-side defect classes -- middleware matcher exclusions that silently skip auth on Server Functions, Server Actions missing allowedOrigins CSRF protection,

Statically review Nuxt 3/4 full-stack code for private secrets exposed via runtimeConfig.public/NUXT_PUBLIC_* env vars, useState/module-scope cross-request state pollution in Nitro, server-route SSRF via $fetch/ofetch with blind useRequestHeaders/credential forwarding, NuxtPayloa

Statically review payment-page frontend code for PCI-DSS-relevant defects in the browser/DOM slice only — raw PAN collection in self-controlled inputs instead of Stripe hosted fields, card data persisted client-side or to analytics, raw card data POSTed to a first-party endpoint,

Review frontend analytics instrumentation and A/B or multivariate experiment configurations for event-schema correctness, sample-ratio-mismatch risk, statistically valid stopping rules, and consent-gated privacy compliance before shipping a tracking or experiment change.

Validates installability against W3C manifest criteria and tests real offline navigation behavior end to end, rejecting a manifest-schema-valid but practically non-installable or non-functional-offline PWA.

Statically review React component trees for composition, prop-interface, and state-placement defects (God-components, prop drilling, overbroad context, hook-rule violations) against React's own composition guidance, producing ranked file:line findings.

Statically review React Server Components code for data leaks across the server-to-client serialization boundary — secrets passed as props to Client Components, server-only modules missing the `server-only` guard, `use server` actions with no authorization check, non-public envir

Statically review useState/useEffect/useReducer call sites against React's documented "You Might Not Need an Effect" anti-pattern catalog, plus race-condition and stale-closure detection via dependency-array and cleanup-function analysis, producing ranked file:line findings.

Reviews route-tree structure, loader/action placement, code-splitting boundaries, and navigation-blocking/focus-management behavior in React Router and Next.js applications for correctness, server-side security enforcement, and accessibility conformance on route transitions.

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.

This is the lane for changes with no behavior to test-drive — prose edits, a version bump on an

Use this after a pull request has merged but your local checkout is still on the topic branch.

Prints the public command catalog straight from `COMMANDS.md` — the plugin's own single source

This is the single entry point for turning staged work into a commit — nothing in codeArbiter

The protocol for a rule conflict — not a skill route, an orchestrator-level halt. When two sources

An optional, on-demand drift audit for the bypass case: a merge, a direct push, or a manual edit

This is the populator for a project that already has code to read. Instead of interviewing you about

This is where an unexplained defect goes before anyone touches code. The investigation is

This is the populator for a project that has no code yet to read. Rather than guessing at

Proves the install is actually enforcing, rather than just present. codeArbiter's worst failure

This is the standard entry point for new work with a human in the loop at every step. A short

This is the entry point for a defect that already has a known cause, or one you can describe

This is how a repository opts into codeArbiter for the first time. It writes the root-level state

A bare-numbers governance glance — three metrics, each with a trend arrow against the prior

The sanctioned, logged escape hatch. A routine gate — a lint rule, a style check, a non-security

Explicit PR entry and a direct request to open a PR use the same branch-finishing owner.

A zero-onboarding, read-only dry-run of the reviewer fleet against whatever is currently

This is a Feature Forge preview command — the after-each-turn service ships **off** by default and

Compares architectural records with the scaffold and prior decisions using SMARTS.

This is the lane for moving or reshaping code without changing what it does — a rename, an extract,

AI coding platform for teams

AI Multi-Agent Framework in .NET

Production-ready code examples for Telnyx AI Communications Infrastructure — Voice AI, SMS, SIP, and IoT APIs

UltraGameStudio - AI coding agent for game development: engine workflows, gameplay code, and asset generation.

🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

The context-aware model router that learns & adapts to your long-horizon coding agent workflows. Lightweight & extensible, works with any harnesses, any models,…

Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.

Native desktop UI for Claude Code with orchestration, streaming, background agents, and multi-provider support. Built with Tauri + React.

OpenCode mobile client via Telegram: run and monitor AI coding tasks from your phone while everything runs locally on your machine. Scheduled tasks support.

Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

Exposes internet search tools for use by LLM-backed Assist in Home Assistant

Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs

Versus Incident is the self-hosted AI SRE agent. It learns what your system normally look like and escalates only what is new or unexpected issues — routing to…

Browser-native side panel for Hermes Agent — connect web context to your local Hermes runtime.

Agentic-friendly CLI generator for APIs: turn Swagger, OpenAPI, and google.api.http protos into single-binary CLIs with catalogs and generated Skills.

Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

Official python implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.

An agent small enough to run anywhere. A minimal agentic runtime in C — ~380 lines, 54KB binary, ~2MB RAM. A skill file + an LLM + a shell loop, no framework.

AgentiLoop Agent! An Autonomous Agentic Agent for Mac, and exclusive Apple only harnesss. Suppprtd automation, scripting, coding, build anything and more. Power…

微信公众号 AI 运营助手 | 选题、写稿、审稿、排版、配图、发布全流程 Skill，支持 OpenClaw / Claude Code / Cursor / Codex