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.

Author a numbered, dated, user-attributed Architecture Decision Record under .codearbiter/decisions/.

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.

Finish an already-merged branch — classify the leftover artifacts, return to a fast-forwarded default checkout, and delete the merged local branch. Every discard confirmed per item; containment proven, never assumed.

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

Run the full commit gate — the only sanctioned path to a git commit.

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.

Optional manual drift audit — report stale provenance-tracked docs, then per stale doc offer re-scout, re-baseline, or defer. Not the daily loop; commit-gate auto-heal owns routine maintenance.

Brownfield back-fill — scout an existing codebase and populate .codearbiter/, then lock it initialized.

Investigate-then-decide root-cause analysis for a defect whose cause is unknown. No code changes — exits to /ca:fix, /ca:adr, or a no-action close.

Greenfield decomposition interview — a layered interview that populates .codearbiter/ and locks it initialized.

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.

Author a new codeArbiter skill: prove the gap is real, get the spec approved, then write it.

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

AI assistant in Telegram that remembers everything and helps you run your life. Self-hosted in one command.

知更 — 本地 AI 的上下文与记忆层。Mac 上用语音输入、情境代回并调度 Codex / Claude Code；iOS 正在成为随身记忆终端和本地 Agent 遥控器。Local-first · BYOK.

Agent skill that turns Claude Code / Codex into a motion-design studio for voiceover-driven explainer videos — word-level voiceover sync, 78 motion recipe cards…

CoCo Super Intelligence is the orchestration layer that turns Claude Code, Cursor, or Codex into an engineering department: a routed advisory board, 185 skills,…

Deploy AI agent teams at scale without compromise

大师.skill — 输入行业，自动调研 6 轨[行业大佬 / 工具地图 / 工作流 / 知识正典 / 信息源 / 术语标准] → 提炼为可运行的行业 Master OS skill；装到任意 Claude Code / OpenClaw / Codex / Hermes agent 即让其进入「这一行的资深人」模式。…

Notion MCP server for Claude, Cursor, ChatGPT & Claude Desktop. Connect AI agents to Notion via Model Context Protocol — pages, databases, blocks, comments, fil…

Hook-based token compressor for 5 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI). Up to 95% bash compression, signature-mode for code…

Model-neutral agent desktop/runtime for private, enterprise, and OpenAI-compatible / Anthropic-compatible model API. Tested on DeepSeek, Qwen, Kimi, GLM models.…

AI agent skill for end-to-end hotel search and booking—compare live rates across leading OTAs and hotel suppliers, verify availability, book stays, and manage r…

More than just Karpathy’s LLM Wiki, 100% local with Ollama. Drop Markdown notes → AI extracts concepts → your Obsidian wiki auto-links and grows. Zero sharing.…

Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks from beginner to power user!

A magical tool that changes how you use Agents. Install once — every Agent automatically discovers and uses all your MCP tools, and saves your tokens along the…

Open-source 24/7 Cowork app for OpenClaw, Hermes, Claude Code, Codex, OpenCode and 20+ more CLI Agent | Customize your assistants | Team them up｜Star if you lik…

AgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15…

Query, provision and operate Cloud, SaaS, API and Model Context Protocol (MCP) resources through a unified SQL-based framework for humans and AI agents.

Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs l…

A self-healing scraper for hostile sites: broken selectors repair themselves, browser rendering kicks in when needed, and a coherent identity layer (Chrome TLS…

Lightweight AI-native workflow builder for individuals and small teams — describe your idea in natural language, get a runnable workflow on a visual canvas, pub…

Minimal AI coding agent (~1,000 lines of Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder.