LLM Mart Basic

Wire up WordPress postboxes on custom plugin admin pages with

Build plugin admin settings pages with the WordPress Settings API instead of custom form handlers. Covers `register_setting()`, `add_settings_section()`, `add_settings_field()`, `settings_fields()`, `do_settings_sections()`, `add_settings_error()`, `settings_errors()`, `admin_ini

Add, remove, or audit WordPress Admin Toolbar nodes with `admin_bar_menu` and `WP_Admin_Bar`, including capability-aware links, parent/child ordering, accessible markup, frontend/admin/network/editor contexts, and WordPress 7.1's persistent toolbar in the Post and Site Editors. U

Build and review WordPress 7.1 WP AI Client integrations for

Audits destructive or long-running WordPress batch writes for retry

Create or audit WordPress Block Bindings sources that connect block attributes to post meta, post/term data, pattern overrides, custom tables, or remote data. Covers PHP source registration, editor registration, metadata.bindings markup, supported-attribute filters, context, edit

Implement or audit WordPress block editor extensions for the always-iframed post editor in WordPress 7.1. Covers parent UI versus editor-canvas documents, ownerDocument/defaultView, @wordpress/compose useRefEffect, DOM events and observers, block and editor asset placement, block

Create or audit WordPress blocks registered through block.json, metadata collections, or PHP-only autoRegister. Covers register_block_type, register_block_type_from_metadata, API version 3, attributes and roles, dynamic rendering, wrapper attributes, editor/frontend asset fields,

Add custom WP-CLI commands to a WordPress plugin via `WP_CLI::add_command( $name, $callable, $args )`. Covers the class-based command pattern with PHPDoc-driven synopsis, positional vs `--flag` args, I/O helpers (`success` / `log` / `warning` / `error` / `confirm` / `debug`), for

Implement or audit compatibility with the WordPress 7.1 browser-side media pipeline. Covers wp_is_client_side_media_processing_enabled, wp_client_side_media_processing_enabled, REST media create/sideload/finalize, generate_sub_sizes, convert_format, client-side image resizing and

Extend or audit WordPress comments and editor Notes, including WP_Comment queries, REST note permissions, note status/mentions, notification hooks, comment counts, pingbacks/trackbacks, and WordPress 7.1 behavior changes. Use when a plugin creates or queries comments/notes, alter

Register and review WordPress 7.1 Connectors API integrations

Build or audit data-driven WordPress plugin interfaces with the public `@wordpress/dataviews` DataViews, DataViewsPicker, and DataForm components. Use for sortable/filterable/paginated admin datasets, item pickers, quick edit forms, field and action contracts, server-driven REST

Audit third-party PHP and JavaScript dependencies bundled with a

Build or migrate WordPress editor and plugin React interfaces using public @wordpress/components APIs. Covers dependency handles, accessible controlled controls, WordPress 7.1 40px form-control defaults, removed Navigation and __experimentalApplyValueToSides APIs, Navigator migra

Implement or audit secure WordPress file uploads and sideloads

Read, write, copy, delete, chmod files from a WordPress

Use WordPress' HTML API for structured server-side HTML inspection

Audits WordPress plugin or theme PHP code for

Build or audit interactive WordPress blocks with the Interactivity API: block.json interactivity support, viewScriptModule, PHP state/config/context helpers, data-wp-* directives, @wordpress/interactivity stores, hydration, async actions, and WordPress 7.1 binding rules. Use for

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.

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.

Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report.

Sanctioned lane for non-behavioral work — docs-only edits, dependency bumps, reverts. Type-scaled gates; no TDD demanded of prose.

Clean up an already-merged local branch after proving containment. Confirm each discard and preserve unique work.

Show the codeArbiter command catalog — the public command list and what each routes to.

Create a verified local Git commit when committing changes is requested. Not for explaining commit history, drafting a message only, or postponing a commit. Applies every commit gate and never implies a push or PR.

Stop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation.

Audit stale provenance-tracked docs on request. Report first; re-scout or re-baseline only for selected docs.

Build project context from an existing codebase through isolated scouts, resolve gaps, and preserve initialization gates.

Investigate an unexplained defect or unexpected behavior without changing application code. Use for root-cause diagnosis and an evidence-backed handoff. A no-action close records a board note. Not for implementing a known fix, new features, or explanation-only questions.

Develop greenfield project context through a layered interview, preserve decisions, and initialize only after the required gates.

Verify the active host install, package, command ownership, enforcement, and harmless live-fire probe. Read-only.

Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation.

Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.

Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store.

Read-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs. the prior 20-commit window.

Sanctioned, logged bypass of a gate or hard rule — one audit line, then proceed.

Open a PR or finish branch disposition; route CI watching and post-merge cleanup to their owners. Merge and discard need explicit authority.

Zero-onboarding, read-only dry-run of the reviewer fleet against the current uncommitted diff. Predicts reviewers, runs the state-free secret scan, writes nothing.

Your efficient agentic AI coding CLI assistant

AI coding with Aegis governance built into execution: baseline-aware changes, evidence-backed delivery. Free desktop client, your choice of model. 将哲科思维融入 AI 开发…

Android in docker solution with noVNC supported, video recording, mcp server and AI-agent

Your AI assistant, built for the agentic era. Open source and local: talk to it, and it runs your agents, your coding CLIs, your browser and your apps. Windows,…

Verifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.

Let Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw CDP as short commands, no screenshots and no MCP ne…

Unofficial, agent-friendly Mercadona shopping CLI (Go) — search products, read prices, build a cart and prepare checkout from the terminal. BYO credentials.

Local-first AI canvas for visual workflows, AI short drama, image/video generation, storyboarding and asset management. ComfyUI, AI agents, MCP & Blender. 本地优先…

Let any AI coding tool — Claude Code, Cursor, Codex — drive your real Chrome. One-prompt setup, muscle memory, local-first.

runs anywhere. uses anything

Open-source dots for the web: an AI agent with its own browser, one that does not get blocked.

Free MIT AI coding agent — no API key needed. Built-in free model, or bring Claude, GPT, Gemini, DeepSeek, Ollama +50 more. Swarm mode, 40+ tools, browser & des…

Open-source AI customer support system. AI-first support, human-ready operations.

A durable, multiplayer, mobile-first web app for Pi agents, built on Pi Durable

Embedded Cypher knowledge graph for Python and Rust. Bundled MCP server, describe() schema, and code-graph parser for LLM agents.

Turn PDFs, books and papers into interactive learning webpages｜将复杂材料转化为可追溯、可测验、可做笔记的学习网页

PhysicsOS 是一个面向初高中物理学习的公益可视化智能体，通过 AI 理解题目并结合物理引擎，将抽象物理过程转化为可交互、可观察、可计算、可验证的真实物理场景。