LLM Mart Basic

Benchmark clean and incremental Xcode builds, surface compile and configuration hotspots, and produce an approval-first optimization plan before changing project files.

Compare browser-agent reliability on a repeatable task and anti-bot suite before choosing a stack or claiming progress.

Run a repeatable evaluation suite for browser agents against static web task snapshots instead of judging them from demos or one-off tests.

Run Claude Code, Codex CLI, Gemini CLI, or OpenCode through bounded H100 post-training tasks and compare how well each agent improves a base LLM.

Score deep research agents on benchmark tasks using factual verification, report-quality scoring, and process evaluation before model or workflow changes ship.

Use EnterpriseRAG-Bench to evaluate an enterprise RAG or knowledge-agent system against a realistic synthetic company corpus with answer, recall, and comparative scoring.

Run realistic enterprise-style IT scenarios before trusting an automation agent in production operations.

Run CIS benchmark checks against cluster nodes and control planes when an agent needs a narrow Kubernetes hardening audit, not a general platform listing.

Run a real-task benchmark suite against OpenClaw agents so model or harness changes can be compared before they hit production workflows.

Run structured prompt-injection attack and defense experiments against an LLM-integrated app before production by measuring attack success and testing detection or recovery pipelines.

Run concurrent scripted conversations against a target agent to measure whether it stays on task, responds correctly, and holds up in repeatable test cases.

Better Auth is an open source authentication framework for TypeScript apps. It gives agents a concrete way to wire sign-in, sessions, passkeys, OAuth providers, and plugins into modern web stacks with real package and docs support.

A fast, configurable secrets scanner built by the creator of Gitleaks and backed by Aikido Security. Betterleaks detects leaked passwords, API keys, and tokens in git repositories, directories, and stdin with CEL-based validation and parallelized scanning.

Automates migration from ESLint and Prettier to Biome (formerly Rome) by parsing .eslintrc and .prettierrc configs, mapping rules to biome.json equivalents, and running biome check --apply for bulk reformatting.

Generates Blender Python (bpy) scripts that programmatically create Geometry Nodes modifier trees, using the node_groups API and GeometryNodeTree interface for parametric 3D asset generation.

Put an inline firewall and containment layer in front of agent network traffic, tool calls, and MCP traffic before you trust an agent with local secrets.

Add hard pre-execution guardrails to Claude Code so destructive shell commands are blocked before an agent can run them.

Use CC Safety Net when coding-agent CLIs need pre-execution hooks that block destructive commands, secret access, and unsafe file operations before tools run.

Scan staged changes, commits, or repositories for secrets before they leave the workstation or CI job, instead of relying on a later platform-side catch.

Add a runtime guard that evaluates agent actions, blocks dangerous commands or secret exposure, and audits new skills before they run.

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.

Use MCP Inspector to connect to local or remote servers, inspect capabilities, call tools, read resources, test prompts, and diagnose failures before release.

Build an MCP server in TypeScript with focused tools, validated schemas, local and remote transports, Inspector tests, and production security controls.

An MCP server exposes tools, resources, or prompts through a standard protocol so an AI application can discover and use external capabilities.

Treat an AI agent skill as both an instruction package and a software dependency: inspect what it says, what it runs, what it can access, and how it updates.

Open a pull request the only sanctioned way — clear every BLOCK-level review finding, then stage the PR. Never a direct write to the default 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.

SMARTS arbitration — reconcile architectural artifacts against the scaffold and prior decisions; every variance resolved by an explicit, user-attributed choice.

Restructure code with behavioral parity proven through unmodified pre-existing tests, then refactor. No behavior change.

Cut a release the only sanctioned way — derive the target's declared version policy from the commit log, roll its changelog, compose an annotated tag, and optionally publish its exact declared assets. Takes the declared target's name as its only argument, or --dry-run to preview one with no write. The only path to a version tag.

Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR.

Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or /ca:feature.

Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard gates remain true stops.

Daily repo hygiene — review the day's repo state, then perform the cleanups under per-action confirmation. Fast-forward only, never destructive without a yes.

Show the project's current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current branch. Read-only.

Wire codeArbiter's statusline into ~/.claude/settings.json, or remove it.

The sanctioned task-board mutator — add a queued task, start one (flips to in-progress and stamps the date, minting a dotted ID on pick-up), or mark an in-progress task done. The only blessed write to open-tasks.md.

Opt-in lightweight STRIDE pass for a sensitive feature before implementation. Not a routine gate — invoke it when a change warrants security thought.

Deep, rarely-convened whole-codebase audit — eleven specialist lenses, a resumable on-disk audit log, findings filed as GitHub issues on approval. Expensive; estimates cost and STOPs before running. Never a required gate.

Watch a PR's CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges.

Gates a new or changed third-party dependency through review before anything installs. Naming the

A read-only health scan of every recorded ADR under `.codearbiter/decisions/`. For each one it

Records an architectural decision as a numbered, dated ADR under `.codearbiter/decisions/`. This is

Assembles everything codeArbiter logs — `overrides.log`, `triage.log`, `decisions/`,

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…