LLM Mart Basic

Gate live financial authority actions — budget threshold changes, Savings Plan purchases, and Reserved Instance commitments. These are committed spend or can trigger immediate service suspension.

Gate KMS key deletion and disable operations. All data encrypted with a deleted CMK (OSS SSE-KMS, ECS encrypted disks, RDS/PolarDB TDE) becomes permanently and irrecoverably inaccessible. This guard enforces complete CMK dependency audits, deletion window confirmation, and explic

Gate OSS bucket ACL and policy mutations — public-read/write ACL exposes data to internet crawlers within seconds; CN-* cross-border replication requires DSL Article 31 assessment.

Gate RAM policy/role mutations against the Alibaba Cloud account hierarchy. RAM AdministratorAccess assignment, policy deletion with active STS tokens, and Resource Directory Control Policy changes carry account-wide or org-wide blast radius. This guard enforces blast-radius asse

Gate RDS/PolarDB instance deletion, spec downgrade, and backup policy removal — database deletion without verified backup is permanently destructive.

Traffic engineering for Alibaba Cloud load balancers — CLB (Classic, legacy), ALB (Application Load Balancer, Layer 7 advanced routing), NLB (Network Load Balancer, Layer 4 high throughput), and GA (Global Accelerator) — type selection, health check design, WAF integration, and t

Alibaba Cloud Maestro routing skill. Classify the user's Alibaba Cloud task, select the narrowest specialist agent or the right team of specialists from the catalog, and dispatch them — single specialist for focused tasks, parallel team (max 4) for multi-domain tasks. Never auto-

Manage MaxCompute CU package governance, DataWorks scheduling, Quick BI reporting, and PAI ML platform. Optimize query cost and job scheduling efficiency for big data workloads.

Plan Alibaba Cloud migrations using SMC (Server Migration Center), DTS (Data Transmission Service) for data sync, OSSImport for object storage migration, and design cutover sequencing with rollback paths.

Configure and operate Alibaba MSE (Microservice Engine) — Nacos service discovery and configuration management, Sentinel rate limiting and circuit breaking, Seata distributed transactions, and ARMS APM for microservices observability.

Design Alibaba Cloud network topology — VPC peering, CEN for multi-VPC/multi-region connectivity, Express Connect for private circuits, SLB/ALB/NLB/CLB load balancer selection, and Smart Access Gateway for branch offices.

Respond to Alibaba Cloud incidents using CloudMonitor alarms, SLS log analytics, ARMS APM distributed tracing, and alert governance for ECS, RDS, ACK, and network services.

Govern Alibaba Cloud OSS data perimeters — bucket ACL and policy conflict resolution, Block Public Access configuration, cross-account access via RAM role, VPC endpoint binding for private access, WORM (Object Lock), and MLPS 2.0 data residency compliance.

Manage OSS lifecycle policies, bucket policy and ACL governance, NAS/CPFS shared file storage, cross-region replication, and access control hardening for Alibaba Cloud object and file storage.

Operate PolarDB (MySQL/PG/Oracle) clusters and RDS instances — DAS diagnostics, database proxy, Global Database Network, backup strategy, and performance tuning.

Audit Alibaba Cloud RAM users, groups, roles, and policies; review STS token lifecycle and scope; assess Resource Directory permission boundaries; review Control Policy statements for org-wide gaps or over-privilege.

Govern Alibaba Cloud Container Registry (ACR) — Enterprise Edition vs Personal Edition selection, image vulnerability scanning, namespace IAM least privilege, image retention policies, cross-region replication, and supply chain security posture.

Review Alibaba Cloud workload HA and BCDR designs — RDS High-Availability Edition failover, PolarDB Global Database Network, ACK multi-zone, ECS disaster recovery cross-region, RTO/RPO target analysis, and HBR (Hybrid Backup Recovery) coverage.

Harden Alibaba Cloud security posture via Security Center (threat detection, vulnerability scanning, baseline checks), WAF, Anti-DDoS Pro, Cloud Firewall, and Network Traffic Analysis (NTA).

Review Function Compute 3.0 (FC3), SAE (Serverless App Engine), and EDAS for production readiness — cold start optimization, VPC binding, RAM role injection, ARMS distributed tracing, security group rules, concurrency limits, and SLA-readiness.

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.

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

Build AI Agents like playing LEGOs. Everything is a Plugin.

The coding agent that answers to you, your model, your machine, your rules.

CI-native agent CLI tool for deterministic pipeline gating.

Local-first cross-platform desktop workspace for Claude Code / agents: multi-agent, Git worktrees, code diffs, skill marketplace, multi-model, Computer Use, tas…

Local-first visual generation runtime and studio for people and coding agents, with reproducible image and video workflows across multiple providers.

A token-efficient MCP server for safe, line-oriented text file editing with partial reads, hash-based conflict detection, and atomic multi-file operations.

Open-source, evidence-driven MCP server for RTL simulation debugging: correlate VCS/Xcelium logs, VCD/FSDB waveforms, SystemVerilog/UVM source, hierarchy, and c…

runs anywhere. uses anything

One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher, per-run git worktrees, one review board.

Soul-driven AI agent with permission-hardened tools, token budgets, and multi-channel access. Runs 24/7 from CLI or Telegram.

Email, SMS & phone-call infrastructure for AI agents — send and receive real email and text messages, and place agent-driven outbound voice calls, all programma…

55 MCP tools to drive the Unity Editor from any MCP-compatible AI agent — scenes, GameObjects, prefabs, assets, tests, and builds. OpenClaw gateway included for…

Google Ads MCP + Meta Ads MCP + GA4 in one server for Claude, ChatGPT, Cursor & n8n — 250+ tools, hosted remote MCP, OAuth login, no API keys. By Ryze AI.

Claude Code & Codex 本地 token 追踪 — 状态栏（Codex 业界首创伪 statusline）、GitHub 风格热力图、多模型成本分析。 | Local token tracker for Claude Code & Codex — status line (industry-first…

Empower the Shell to think. Evolve Operations.

🤖 A full-stack Agent Chat Runtime for pre-production validation, built with act, TypeScript, and LangGraph JS combining streaming, multimodal, HITL, and tools…

Cerul — video memory infrastructure for AI products. SDKs, CLI, MCP, and developer integrations.

Stealth headless browser for AI agents — bypass Cloudflare, bot detection, and anti-scraping. Drop-in Puppeteer/Playwright replacement.

Web research for your agents with smart and safe tooling + knowledge store

FuXi is a fast, self-contained AI coding agent that lives in your terminal — edit code, run commands, and drive tools, with cost-aware routing across LLM provid…