LLM Mart Basic

Design AWS non-destructive task automation using EventBridge, Step Functions, Lambda, Systems Manager Automation, SNS, SQS, approvals, notifications, reporting, and evidence gathering. Use only for read-only or coordination-safe automation; do not use for destructive remediation

Investigate broad AWS incidents and observability gaps using CloudWatch metrics, logs, alarms, traces, EventBridge events, service health, runbooks, timelines, blast radius, root-cause discipline, and post-incident actions. Prefer RDS/Aurora investigator for database-specific per

Repair AWS pipeline configuration, buildspecs, workflow files, deployment steps, artifact wiring, release guardrails, and CodeDeploy integration in-repo. Use for non-destructive CI/CD corrections; do not trigger live pipeline runs or mutate cloud state.

Use this skill when reviewing AWS ACM Private CA (Private Certificate Authority) issuer configurations for cert-manager. Trigger on any request to audit AWSPCAIssuer, AWSPCAClusterIssuer, IRSA policy for cert-manager, certificate template ARNs, CRL configuration, or cross-account

Investigate Amazon RDS and Aurora-specific incidents involving latency, connection exhaustion, slow queries, lock waits, storage pressure, CPU/I/O saturation, replica lag, failover behavior, Performance Insights, and database capacity. Prefer this for database performance; prefer

Review AWS resilience and business continuity strategy across RTO/RPO, dependency maps, multi-AZ, multi-Region, failover/failback, game days, runbooks, drift, and recovery validation. Prefer data protection backup steward for backup-plan/vault/restore implementation details.

Review Amazon S3 data perimeter and exposure posture across Block Public Access, Object Ownership, ACL removal, bucket/access point policies, TLS-only access, encryption, replication, lifecycle, logging, cross-account access, and prefix boundaries. Prefer this for S3 data exposur

Review broad AWS security posture across Security Hub CSPM, GuardDuty, Inspector, Macie, Config, CloudTrail, IAM, public exposure, vulnerability findings, and remediation governance. Prefer compliance evidence mapper for audit evidence packs, IAM skill for policy surgery, S3 peri

Review AWS Lambda-centered serverless workloads for production readiness across execution roles, event sources, retries, DLQs/destinations, concurrency, idempotency, observability, deployment safety, performance, cost, and rollback. Prefer event-driven architecture for EventBridg

Patch AWS serverless rollout definitions across Lambda, API Gateway, EventBridge, SQS, SNS, event source wiring, aliases, versions, and deployment config. Prefer this for repo-side rollout corrections; do not perform live rollout actions or destructive operations.

Design and stress-test AWS cross-domain solution architectures when the request spans multiple AWS domains or needs an architecture decision record. Prefer narrower AWS skills for single-domain IAM, network, EKS, ECS, serverless, RDS, DynamoDB, S3, Bedrock, IaC, cost, security, m

Triage AWS tickets and alerts using priority, owner, evidence, incident context, escalation path, OpsCenter, health signals, and safe next steps. Prefer this for non-destructive request coordination and escalation; prefer deep domain skills for implementation or root-cause invest

Review AWS workload cost posture against the Well-Architected Framework Cost Optimization Pillar. Covers cost visibility, tagging compliance, commitment coverage, rightsizing, Spot and managed service adoption, and idle resource identification. Use when auditing cloud spend, plan

Review AWS workload reliability posture against the Well-Architected Framework Reliability Pillar. Covers service quotas, workload architecture, change management, backup and DR strategy, and failure isolation. Use when auditing availability design, planning disaster recovery, or

Review AWS workloads against the Well-Architected Framework Security Pillar: identity foundations, detective controls, infrastructure protection, data protection, and incident response readiness.

Use this skill for Microsoft Foundry and Azure AI Foundry operations governance: resource-versus-project boundary design, RBAC review, quota planning, network isolation, logging, and safe MCP-backed read or write execution. Trigger when the user asks how to run Foundry safely acr

Operate Azure Kubernetes Service with an adversarial production posture. Use for AKS architecture sanity checks, upgrade safety, node-pool strategy, workload identity, network policy, scaling, observability, and operator-readiness reviews.

Review Azure App Service and Web Apps for production readiness across plan tier fit, slots, networking, private ingress, identities, secrets, scaling, diagnostics, resilience, backup, rollback, and operator readiness. Use when a team wants a real go/no-go decision instead of shal

Use this skill for Azure Cosmos DB application development work, especially NoSQL data modeling, document structure, partition-aware access patterns, point reads, query design, SDK usage, transactional batch scope, consistency-aware reads, change feed integration, and Cosmos DB d

Use this skill for Azure Cosmos DB performance investigation, especially RU spikes, query latency, throttling, hot partitions, indexing inefficiency, partition-skew analysis, request-charge profiling, diagnostic-log review, and evidence-driven remediation planning.

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

Open-source MCP servers for Latin American commerce — Pix, NF-e, banking, fiscal, logistics, and messaging across Brazil, Mexico, Argentina, Colombia, Chile, an…

pi coding agent in a technicolor web trenchcoat

Open-source AI Search Intelligence Platform — track, analyze, and improve AI visibility, citations, prompts, competitors, and content opportunities across ChatG…

Open-source toolkit for the QVeris capability routing network: CLI, MCP server, Python SDK, skills, and REST API docs for agents to discover, inspect, call, and…

⚡ The Complete X/Twitter Automation Toolkit — Scrapers, MCP server for AI agents (Claude/GPT), CLI, browser scripts. No API fees. Open source. Unfollow people w…

The AI agent that interacts with you in the real world.

Offline Codex Desktop migration for Windows and macOS.

LLM 驱动的多市场股票智能分析系统：多源行情、实时新闻、决策看板与自动推送，支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashbo…

Your smart, reliable, and friendly personal AI assistant.

The LLM Anti-Framework

A general-purpose AIGC video engine: script to finished film in one pipeline — dramas, ads, product videos, otome games, and more. | 通用 AIGC 视频引擎 —— 从剧本到成片一条流水线…

GTM agent for technical founders. Pay-per-result. Signed receipts. Two surfaces: terminal CLI + local web dashboard.

Desktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protocol (stdio)

DeepSeek Harness (dsh) Windows desktop client - bundled Node.js + dsh CLI, one-click launch

Open-source, real-time collaborative AI canvas - notes, mini-apps, and agents on one infinite board.

MCPSafari: Native Safari MCP Server for AI Agents

197 bioinformatics & life science skills for Claude Code and AI agents — BixBench 92.0% accuracy. RNA-seq, single-cell, drug discovery, proteomics, and more. Po…

The AI agent with a wallet — spends USDC autonomously to get real work done. Apache-2.0, TypeScript.

The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, with…

Ouroboros — self-creating AI agent. Born Feb 16, 2026.