LLM Mart Basic

Use when the user wants adversarial stress-testing of a proposed architecture, structure, or shape. Not for tasks that require source or remote-system changes.

Use when the user asks for a council, second opinions, or parallel investigation. Not for cross-examination of existing proposals: use cross-critique.

Use when independent proposals on a contested decision need cross-critique before choosing, reusing the original authors. Not for parallel multi-stance investigation: use council.

Use when one reviewer is not enough because failure modes are heterogeneous, or a claim needs cross-lens pressure before it ships. Not for collapsing a decision field: use converge.

Use when a current decision needs pressure-testing until the rationale is clear to a skeptic. Not for tasks requiring source or remote-system changes.

Use when a non-trivial decision sits under uncertainty and correctness matters more than speed. Not for patch review: use review. Not for plan attacks: use load-bearing-assumption-test.

Use when the user asks why a plan is wrong or says "poke holes in this". Not for tasks that require source or remote-system changes.

Use when one reviewer angle is insufficient or the user suspects a direction is tunnel-visioned or inherited its framing. Modes: artifact, direction. Not for source or remote-system changes.

Use when a workflow, plan, diff, or completed work cycle must be checked for practices that punish the project later. Not for source, remote, credential, publish, deploy, or irreversible changes.

Use when asking "overkill?", "elegant?", "audit", or "taste-test this", or setting a taste register. Not for tasks that require source or remote-system changes.

Use when product copy needs buyer-objection evidence collected through approved, consented outreach. Not for unsolicited outreach or survey design.

Use when the user wants the current jargon weather of a domain described without advocacy. Not for choosing a positioning move: use buzzword-hijack.

Use when a user wants to choose and execute a bounded positioning move that rides a jargon wave. Not for describing the jargon weather of a domain: use buzzword-analysis.

Use when asked to research a feature across competitor products or to analyze competitor release changelogs (mode: changelog), and publish a cited report.

Use when customer feedback, NPS, churn, email feedback, call transcripts, or voice-of-the-customer analysis needs a report over a time window.

Use when dogfooding a developer-facing product or workflow to produce an evidence-backed DX scorecard. Not for visual UI audit: use web-design-review.

Use when projecting cost, estimating BYO cost or spend, or sizing a deal. Not for remote, credential, publish, deploy, or irreversible changes.

Use when invoking /product-signal-pulse with an optional lookback window to query configured product signals. Not for credential, publish, deploy, or irreversible changes.

Use when asked to analyze a screen recording, voice capture, or meeting notes artifact for product feedback. Not for credential, publish, deploy, or irreversible changes.

Use when asked to draft launch or promotion copy for a shipped feature across channels via /release-promotion. Not for posting, publishing, scheduling, or committing, drafts only.

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‑WebUI Tools is a modular toolkit designed to extend and enrich your Open WebUI instance, turning it into a powerful AI workstation. With a suite of over 15…

The token-efficient agentic coding workbench. Built for a future where every token counts — it optimizes token usage at the agent-loop level, saving 70%+ on lon…

MCP server for controlling a real iPhone via macOS iPhone Mirroring...and any MacOs app. Screenshot, tap, swipe, type — from any MCP client.

One desktop for all your AI coding Agent — Claude Code, Codex CLI & Gemini CLI. Auto-detect, one-click install, unified chat, file explorer, terminal & editor.…

Pi — A cross-platform AI coding agent, bringing the Claude Code experience to your desktop. No environment setup, no terminal commands. Download and start codin…

DeepSeek Harness Desktop (dsh-desktop). EAC: Embracing All Creation (揽尽万象). Bundled Node.js runtime with full dsh-CLI kernel, one-click startup, 10 built-in UI…

A telegram bot for searching and auto-saving.

金蝶云星空 K3Cloud MCP Server，让 AI 助手（Claude Desktop、Claude Code、Cursor、Cline、Cherry Studio、Openclaw 等任意支持 MCP 协议的客户端）通过自然语言查询和操作金蝶 ERP 系统。

Rewrite frontier research using allegorical structural mapping.

Free4Chat is a temporary collaboration fabric for Humans and Agents.

Give any AI agent a full desktop — it sees the screen, clicks, types, and runs apps like a human. Automate anything with a UI: browsers, legacy software, intern…

A personal AI agent that can work safely on your machine, remember useful context, and keep its data under your control.

A framework for AI-driven economic activity. Declarative, composable, observable, deterministic.

Open-source, self-hosted customer support desk in a single binary. A lightweight alternative to Intercom, Zendesk, Chatwoot.

54 rigorous skills for Codex, OpenCode, and Pi: code review, security audit, feature development, frontend design, MCP tools, Hugging Face ML/training, and more…

A wonderful list of Game Development resources.

Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux. Open-source Claude Science desktop alternative built on Tau…

Lexora — Personal AI workspace built around Desktop / 以 Desktop 为核心的个人 AI 工作台

Open-source, AI-native Evernote alternative with native MCP. Zero-cost on Cloudflare or self-hosted with Docker.

Full job-hunt Claude skill bundle — Job Description decoder + Resume builder (11 templates) + Behavioral Interview / story bank. Three self-contained sub-skills…