LLM Mart Basic

Build with MPP (Machine Payments Protocol) - the open protocol for machine-to-machine payments over HTTP 402. Use when building paid APIs, payment-gated content or endpoints, AI agent payment flows, MCP tool payments, pay-per-token streaming, or metered pay-as-you-go billing. Cov

Prepare the session for context compaction - write a handoff file a fresh session can continue from, propose updates to the project's durable docs, apply them on approval or with `auto`. Use before compacting or clearing context, or on "pre-compact".

Opinionated Python development setup with uv, ty, ruff, pytest, and just. Use when creating a new Python project, writing or fixing pyproject.toml, or configuring linting, formatting, type checking, testing, pre-commit hooks, or build and CI tooling.

Discards the accumulated drafts and framings from this thread and re-derives the task from a clean problem statement. Use when the user says the thread is contaminated, that the conversation is going in circles, or that they want a fresh take, or when they invoke /reset-context-c

Practical day-1 guide to building applications in Rust well. Covers the mental model (ownership, errors as values, traits-not-interfaces), day-1 decisions (String vs &str, Box vs Rc vs Arc, dyn vs impl Trait, anyhow vs thiserror), idioms, anti-patterns, and a tight crate shortlis

Build high-quality Agent Skills for any agent - opinionated best practices distilled from the Agent Skills spec, official Anthropic guidance, and production experience. Covers SKILL.md structure, frontmatter, description writing, single-file vs references/ layout, progressive dis

Build, test, deploy, and audit Solana programs with Anchor or native Rust, and build with ZK Compression (Light Protocol). Use when developing Solana smart contracts, implementing token operations, optimizing compute, deploying to networks, auditing programs for vulnerabilities,

Writes or audits README files following the Standard Readme specification (github.com/RichardLitt/standard-readme). Use whenever the user asks to create, write, rewrite, improve, audit, or fix a README, or asks about README quality or structure - even if they never mention "stand

Covers macOS app development with Swift 6.3, SwiftUI, SwiftData, Swift Concurrency, Foundation Models, Swift Testing, ScreenCaptureKit, and app distribution. Use when building native Mac apps - windows, scenes, navigation, menus and toolbars, SwiftData models and queries, modern

Builds type-safe React apps with TanStack Query (data fetching, caching, mutations), Router (file-based routing, search params, loaders), and Start (SSR, server functions, middleware). Use when working with react-query, server state, file-based routing, typed search params, route

Builds full-stack TypeScript apps with Vite 8, React 19, Tailwind CSS v4, shadcn/ui, Biome, Vitest, and Hono. Covers the frontend (Vite/Rolldown build and dev server, type-safe React 19, strict TypeScript 6.0, Tailwind/shadcn styling, Biome lint/format, Vitest) and the Hono 4 bac

Thorough on-demand refresh of one skill in a skills repository: researches usage/upstream/docs in parallel, gates twice for approval, bumps version, updates CHANGELOG, runs the repo's validation, then commits and watches CI. Install the pond MCP (https://pond.cascade.fyi/) for th

Build internet-native payments with the x402 open protocol - HTTP 402 Payment Required for on-chain micropayments with no accounts or API keys. Use when developing paid APIs, paywalled content, AI agent payment flows, or MCP tools that charge per call. Covers the TypeScript, Pyth

Generate a CVE 5.x JSON document from an <tracker> tracking issue, ready to paste into the Vulnogram `#source` tab of the ASF CVE tool at https://cveprocess.apache.org/cve5/<CVE-ID>#source. The conversion is deterministic: same issue in, same JSON bytes out. Handles multiple cred

Produces executive-level research — market sizing, competitor mapping, trend analysis, and strategic intelligence — grounded in cited sources with the confidence in each claim made explicit. Use this to analyze a market or industry, map competitors, evaluate a market-entry or bui

Finds the single constraint currently limiting a business's growth and the highest-leverage moves against it, rather than producing a list of everything that could be improved. Use this when growth has stalled or slowed, when deciding where to spend limited time or budget, when r

Pressure-tests a decision, plan, or idea before it is committed to — surfacing the assumption it rests on, the case against it, and what would have to be true for it to work. Use this when weighing options, when a plan needs challenging before commitment, when you have already de

Sets direction, allocates capital and attention, and makes the calls no one else can make. Use this when a decision spans more than one function, when priorities conflict and something must be cut, when a plan needs pressure-testing before commitment, or when the question is what

Evaluates a software or startup idea against problem, market, competition, monetization, defensibility, and execution, and returns a verdict rather than encouragement. Use this when an idea needs pressure-testing before anyone builds, when deciding whether something is worth purs

Designs AI systems, automations, and agent workflows for a business — identifying which manual work is worth automating, how to structure the system, which tools fit, and what could go wrong. Use this to automate part of an operation, design an agent or MCP workflow, reduce repet

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

Your efficient agentic AI coding CLI assistant

AI coding with Aegis governance built into execution: baseline-aware changes, evidence-backed delivery. Free desktop client, your choice of model. 将哲科思维融入 AI 开发…

Android in docker solution with noVNC supported, video recording, mcp server and AI-agent

Your AI assistant, built for the agentic era. Open source and local: talk to it, and it runs your agents, your coding CLIs, your browser and your apps. Windows,…

Verifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.

Let Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw CDP as short commands, no screenshots and no MCP ne…

Unofficial, agent-friendly Mercadona shopping CLI (Go) — search products, read prices, build a cart and prepare checkout from the terminal. BYO credentials.

Local-first AI canvas for visual workflows, AI short drama, image/video generation, storyboarding and asset management. ComfyUI, AI agents, MCP & Blender. 本地优先…

Let any AI coding tool — Claude Code, Cursor, Codex — drive your real Chrome. One-prompt setup, muscle memory, local-first.

runs anywhere. uses anything