LLM Mart Basic

Covers Highloadblock module — HighloadBlockTable manage API (add/update/delete, lang names), compileEntity() and dynamic DataManager CRUD, user fields (HLBLOCK_{id}), hlblock UF relations and _REF, directory iblock property (UF_XML_ID), ORM events, rights operations (hl_element_*

Covers Bitrix\Main\Web\HttpClient HTTP client — legacy mode and PSR-18 (sendRequest), async Promise, proxies/timeouts, http_client_options, main.HttpClient logger, SSRF, redirects, and GeoIp\Manager lookups. Applied in external API integrations, webhooks, async calls and geolocat

Iblock types/elements/sections, ORM compileEntity, properties, SEO templates. Use for content iblock work.

Covers Landing module — sites/landings, blocks repository, publish/unpublish flow, hooks (Metrika/GA/pixels), customization limits vs classic CMS. Applied for Sites24/landing pages, storefronts, knowledge bases on landing. Key terms — Landing, Site, Block, BlockRepo, publication,

Covers Bitrix localization — Bitrix\Main\Localization\Loc, lang/<code/>/ language files, loadMessages, placeholders in getMessage, Context::getCulture() and culture formats, JS localization via BX.message and $Bitrix.Loc, translate:index for phrase indexing. Applied when adding a

Covers PSR-3 logging in Bitrix — Bitrix\Main\Diag\Logger, FileLogger, SysLogger, NullLogger, LogFormatter, loggers section in .settings.php, named kernel loggers (main.Default, main.HttpClient, main.GeoIpManager, main.EventLog.*), integration with Monolog and third-party PSR-3 lo

Covers creation and maintenance of a custom Bitrix module in /local/modules/<vendor>.<module>/ — CModule class, install/index.php, DoInstall and DoUninstall, install/version.php with $arModuleVersion, registration of events and agents during installation, module options (options.

D7 ORM tablets, ConditionTree queries, Objectify, batch/merge/deleteByFilter writes. Use for entity design, reads, and persistence.

Covers Bitrix performance — composite site, query optimization, replication/clustering, sharding, hot/cold sessions. Applied for high-load optimization beyond basic caching. Key terms — composite, NGINX, replication, sharding, query optimization.

Covers PostgreSQL support in Bitrix — PgsqlConnection, migration from MySQL, compatible code, module support matrix. Applied when configuring or migrating to PostgreSQL Enterprise editions. Key terms — PostgreSQL, PgsqlConnection, migration, compatible-code.

Covers Bitrix project structure — /local vs /bitrix, PSR-4 autoloading, .settings.php, Loader includeModule vs requireModule, placement of components, templates, modules, routes and php_interface, namespaces like Vendor\Module. Applied for "where to put code" questions, module lo

Covers Pull module — sending realtime events to users/channels from PHP, JS subscription overview, watch tags, when to use Pull vs Messenger vs agents, link to BitrixVue. Applied for live UI updates, notifications, collaborative screens. Key terms — pull, Bitrix\Pull\Event, CPull

HttpRequest/HttpResponse, Json/AjaxJson/Redirect, Uri, UuidGenerator. Use instead of $_GET/$_POST and raw headers.

Covers REST module — registering methods from a custom module, scopes, webhook and OAuth overview, rest / restIntegration settings, link to Engine controllers and ActionFilter\Scope::REST. Applied when exposing module APIs to apps, webhooks, or marketplace integrations. Key terms

Covers Bitrix unified operation results — Bitrix\Main\Result, Error, ErrorCollection, typed descendants (AddResult, UpdateResult, DeleteResult, EventResult), difference between Result and exceptions, returning errors from controllers via addError and combining service errors. App

RoutingConfigurator, /local/routes, PublicPageController, site-guard, urlrewrite migration. Use for public/API URLs.

Covers Sale module — API choice (D7 object model vs ORM vs CSale*), FUSER, Basket, Order create/update, properties, statuses and events, payments, delivery/shipments, discounts and coupons, reservation/deduction, permissions, buyer accounts. Applied for cart/checkout, order lifec

CSRF, XSS, SQLi, SSRF, JWT/JWK, access rights, encryption. Use when handling input or auditing security.

Covers SEO module — sitemap generation, robots.txt, webmaster/search-engine engines, keywords/tools orientation; links to iblock IPROPERTY / InheritedProperty for page meta. Applied for crawl maps, Webmaster/Search Console wiring, SEO tooling. Key terms — Sitemap, Generator, Job,

Covers DI container Bitrix\Main\DI\ServiceLocator (PSR-11) — registration of services in the services section of a module's .settings.php file, autowire, retrieving dependencies via has()/get(), constructor injection in application services, action-parameter injection in controll

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.

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.

{{SKILL_ENTRY:post-merge-cleanup}}

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

{{SKILL_ENTRY:commit-gate}}

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.

{{SKILL_ENTRY:context-check}}

{{SKILL_ENTRY:context-creation}}

{{SKILL_ENTRY:debug}}

{{SKILL_ENTRY:decompose}}

Verify the active host install, package, command ownership, enforcement{{IF:pi}}, wrapper self-test, and active-dispatch coverage gap{{ELSE}}, and harmless live-fire probe{{END}}. 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.

{{SKILL_ENTRY:finishing-a-development-branch}}

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.

Trim transcript clutter to extend session lifetime — analyze, prune a copy, or toggle the after-each-turn service. Dry-run by default; gains land at resume/compaction, not the current turn.

{{SKILL_ENTRY:decision-variance}}

Claude Code skills for Chinese-narration recaps from supported video files, with optional editable JianYing/CapCut draft export. | 用 Claude Code skills 为支持的视频文件…

Drive the Unity Editor from an AI agent or the terminal. The Editor serves MCP itself over HTTP, so there is no second process to run, and the isuzu-unity-cli c…

面向企业的数字员工构建与运行平台：把专业员工的经验、流程与判断标准，固化为可随时上岗、可配置、可审批、可观测的 AI 数字员工。

A local-first, Pi-powered AI agent workspace for Desktop, WebUI, and CLI

660+ muapi-hosted generative-media models plus community-submitted third-party API tools (SEO, enrichment, social, scraping) — one YAML file per entry, browsabl…

A compounding agent OS for recursive agents. Also an open source alternative to Grok Bot and Meta's Muse.

Independent desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes on Linux and macOS.

Production agent skills for Claude Code, Cursor, and any SKILL.md harness — Codex fleets, video pipeline, monorepo review bundles, multi-chain explorer.

See and manage what your coding assistants load — skills, commands, subagents, plugins and MCP servers, with real usage.

An Enterprise-Grade Full-Stack RBAC Permission Management System Built with Go + React

Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistants and multi-agent AI workflows.

基于 DeepSeek Harness（DSH）的稳定桌面端，集成Git、内置浏览器与记忆功能 | DeepSeek Harness desktop GUI with local workspaces, Git, browser and memory.

⚡ Control Apache Airflow with natural language via MCP. Chat with your workflows using Claude, GPT, or any LLM — no REST API calls needed. Supports Airflow 2.x…

Open-source CLI, schemas, resolver, and DSH agent tools for DSH Plugin Hub

Pi Coding Agent 中文学习蓝皮书：从安装与第一个可验收任务开始，逐步掌握 Session、Context、Skill、Extension、Subagent 与长期 Agent 工作流。

Self-hosted framework for orchestrating fleets of specialist AI agents — ensemble reasoning and a full agentic coding pipeline, model-agnostic and local-friendl…

Self-hosted, vendor-neutral control plane for your local coding agents (Claude Code & Codex). Run your agents, on any plane.

A practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent memory, evaluation, observability, and…

Vibe Coding 从入门到精通教程｜AI 结对编程工作流｜Prompt、Skill、Workflow、上下文管理、codex实战指南

Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 51 rules mapped to OWASP Agentic Top 10 (2026). Works with LangC…