LLM Mart Basic

Implements and reviews React/TypeScript frontend work covering component architecture, state management, rendering strategy, and web performance. Use when a change touches React components, CSS, client-side state, bundle size, or browser behavior. Full-access writer; pairs with U

Designs and reviews Google Cloud architecture, IAM, networking, and cloud cost. Use when the task involves GCP services, Terraform targeting GCP, gcloud operations, or GCP cost optimization. Not for AWS work (use AWS Expert); cross-provider IaC and pipeline concerns belong to Dev

Assesses data-handling changes for EU data subjects, judging lawful basis, DPIA triggers, PII flows, consent quality, retention, and data subject rights implementability, and returning severity-ranked findings that bridge legal obligations to engineering fixes. Use when a change

Designs and audits Google Tag Manager setups, covering server-side tagging on Cloud Run, Consent Mode v2, GA4, data layer schemas, and conversion APIs. Use for tag migrations, data layer design, consent-aware measurement, or tracking data quality issues. Pairs with GDPR Expert, w

Diagnoses and designs DNS, TLS, load balancing, CDN caching, and protocol-level behavior (TCP, HTTP, gRPC, WebSocket). Use when the task involves DNS records, certificates, LB or proxy configuration, CORS, timeouts, or intermittent connectivity issues. Cloud-provider resource pro

Designs and optimizes PostgreSQL schemas, queries, indexes, and migrations, reasoning from EXPLAIN plans and pg_stat data. Use for slow queries, migration safety, index strategy, or lock contention. Pairs with Backend Staff Engineer, who owns the application layer.

Reviews a pull request or working diff for correctness, security, and maintainability, returning severity-ranked findings with file:line references and a verdict. Use when asked to review a PR, code-review a diff, or given a PR number/URL. Read-only; pairs with Cybersecurity Expe

Reviews feature plans, specs, and user stories for problem framing, scope boundaries, and measurable success criteria. Use when planning a feature, writing user stories, prioritizing work, or defining how success will be measured. Advisory and read-only; pairs with the technical

Designs test strategy and writes tests at the right level, from unit to E2E, including diagnosing flaky suites. Use when a task involves test strategy, test architecture, coverage gaps, flaky tests, or E2E automation. Full-access writer; pairs with the implementing engineer whose

Shapes system architecture, reasoning about module boundaries, dependency direction, domain modeling, and long-term maintainability trade-offs. Use for system design, DDD, cross-module refactors, or architecture review. Pairs with Backend and Frontend Staff Engineers, who own imp

Reviews usability, accessibility, and interaction design of UI changes, returning severity-ranked findings. Use when a change touches user-facing UI, WCAG compliance, or interaction flows. Advisory and read-only; pairs with Frontend Staff Engineer, who implements.

Audits views for compliance with Apple's Sufficient Contrast accessibility nutrition label (WCAG 2.1 contrast ratios). Use when the user asks to check color contrast, audit contrast ratios, verify the Sufficient Contrast nutrition label, or review a view for accessibility.

Audits views for compliance with Apple's VoiceOver accessibility nutrition label. Checks that interactive elements have accessibility labels, labels are human-readable, accessibility traits are correct, images are properly configured, and custom controls are exposed to assistive

Guide for the C -fbounds-safety language extension. Covers the language model, pointer annotations, adopting bounds-safety in existing C code, compiler build settings and modes, and runtime debugging of bounds violations.

Authoritative App Intents best practices from Apple. Consult for any App Intents best-practices or correctness review, and when writing, reviewing, refactoring, or extending App Intents code. Supersedes prior training on these topics. For code generation, consult the relevant ref

New App Intents APIs, behaviors, and deprecations introduced in the iOS 26 (2025) and iOS 27 (2026) releases (and their macOS/watchOS/tvOS/visionOS siblings). Use when adopting, migrating to, or asked about: declaring where an intent runs with supportedModes / IntentModes (.backg

Use when an app's layout must adapt to a window that changes size while the app runs, or when an app must support more than one window. That includes being asked to make an app resizable or support a resizable window, a layout that breaks or does not adapt as the window resizes,

Audit and enable security-oriented Xcode build settings. Progressively enables compiler warnings, static analyzer checkers, and Enhanced Security features. Use when: user wants to secure their Xcode project, audit security settings, enable hardening, review security posture of bu

Authoritative guide for building and migrating document-based apps in SwiftUI using the Document protocol (iOS 27 and aligned releases, including macOS Golden Gate). Consult when building a new document-based app; implementing open, edit, save, or export document flows; working w

Verify app behavior on device or simulator via screenshots, UI hierarchy, and touch interactions.

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.

Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot target.com [--paranoid|--normal|--yolo]

Build an exploit chain — given bug A, finds B and C to combine for higher severity and payout. Knows common chain patterns: IDOR→ATO, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth. Usage: /chain

Active vulnerability hunting. Two-track dispatcher — asks Red Team vs WAPT, hands off to hunt-dispatch skill and sibling commands. Usage: /hunt target.com | /hunt *.target.com | /hunt targets.txt [--vuln-class X] [--source-code P] [--chrome]

On-demand intelligence fetch for a target — CVEs, disclosed reports, new features. Pulls NVD/GitHub-Advisory CVEs + bundled disclosed reports + hunt memory context. Usage: /intel target.com

Inspect or rotate the autopilot ledger JSONL files (findings.jsonl, negatives.jsonl). Caps file size and keeps N rotated backups so memory does not grow unbounded.

Pick up a previous hunt on a target — shows hunt history and untested surface from the autopilot ledger. Usage: /pickup target.com

Run full recon pipeline on a target — subdomain enum (Chaos API + subfinder), live host discovery (dnsx + httpx), URL crawl (katana + waybackurls + gau), gf pattern classification, nuclei scan. Outputs to recon/<target>/ directory. Usage: /recon target.com

Optional manual note on a target or the last confirmed finding. Capture is automatic during autopilot; this is for extra context. Usage: /remember

Write a submission-ready bug bounty report. Generates H1/Bugcrowd/Intigriti/Immunefi format with CVSS 3.1 score, proof of concept, impact statement, and remediation. Run /validate first. Usage: /report

Mandatory pre-flight scope check — verify an asset is in scope BEFORE any HTTP touch. Deterministic (deny-wins, default-deny) via engine/scope.py against the engagement's scope.md. Blocks out-of-scope testing. Usage: /scope <asset> [<asset> ...]

Show ranked attack surface for a target from its recon manifest + hunt memory. Deterministic backing is `cbh surface <target>` (reads recon/<target>/manifest.json); LLM layer adds ledger signal. Usage: /surface target.com

Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP lock bypass, authority retention, bonding curve exploits, fake renounce, sandwich amplification). Manual 8-class grep audit (with an optional automated scanner if present). Usage: /token-scan <contract_path_or_dir> [--chain solana]

Quick 7-Question Gate triage on a finding before writing a report. Kills N/A submissions before they happen. Faster than /validate — for quick go/no-go decisions. Usage: /triage

Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate

Smart contract security audit — runs through 10 bug class checklist (accounting desync, access control, incomplete path, off-by-one, oracle errors, ERC4626, reentrancy, flash loan, signature replay, proxy/upgrade). Applies pre-dive kill signals first. Generates Foundry PoC template for confirmed findings. Usage: /web3-audit <contract.sol>

Crabbox is a single CLI (`crabbox`). Commands are top-level, not nested under a

`crabbox actions` prepares a leased box from your repository's own GitHub

See [Runtime adapter stack](../features/runtime-adapter-stack.md) for the

`crabbox admin` groups trusted operator controls for coordinator-backed leases and the cloud resources behind them. Use it to inspect every lease the broker tracks, reconcile expired leases against live cloud state, force-release or delete a backing server, print provider IAM pol

`crabbox artifacts` turns a desktop lease into durable QA evidence: it collects

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…