LLM Mart Basic

Runs 14 numbered engineering protocols in one pack — brainstorm, spec, plan, scaffold, TDD red-green-refactor, systematic debugging, refactoring, code review, performance, security, docs, git hygiene, release checklist, postmortem. Use when the user says "build this feature prope

Delivers a ruthless, structured critique of any screen, mockup or site — scores hierarchy, spacing rhythm, contrast, typography pairing and color discipline /10 with evidence, detects clichés (purple gradients, glassmorphism-by-default, emoji soup, cookie-cutter heroes), and rank

Organizes tax season — an organizer, not tax advice: a document checklist by category (income, expenses, assets, payroll, prior filings), an expense-category sweep that flags plausibly missed deductions in generic jurisdiction-agnostic categories, a quarterly-estimate calendar te

The company audits its own payroll — tracks AI token spend per department and mission, estimates costs from session data or telemetry, sets budget alerts and writes the monthly cost memo. Use when the user says "how much is this costing me", "token spend", "AI budget", "cost per

Builds a complete CSS motion system — duration and easing tokens (fast 120ms micro-feedback, base 200ms, slow 320ms entrances; standard, decelerate and spring curves), enter/exit/emphasis patterns, stagger rules, and prefers-reduced-motion fallbacks — delivered as a copy-paste CS

Ten-minute NDA triage — classifies an incoming NDA as GREEN (sign under standard delegation), YELLOW (targeted fixes, listed), or RED (full review). Screens mutuality, term and survival, definition breadth, embedded non-solicits or non-competes, missing standard carve-outs, resid

Builds an end-to-end UI system for a product — design tokens (color scale, type scale, spacing, radii, shadows), a component inventory covering every interaction state, a layout grid, and WCAG contrast checks — emitted as CSS variables plus a component spec doc. Use when the user

Explains budget-vs-actual or period-over-period variances: sets a materiality threshold first, builds the variance table in dollars and percent, decomposes drivers (price, volume, mix, timing, one-offs), draws a bridge waterfall, and writes the so-what per material line with fore

Vendor agreement status check — inventories what exists versus what is needed (MSA, DPA, SOW, SLA, insurance certs, security review), builds a gap analysis table, runs an expiration and renewal radar with dates and notice windows, notes surviving obligations, and delivers an onbo

Ingests 5–20 of the user's writing samples and distils a reusable voice-profile.md — signature phrases, sentence-length distribution, opener/closer habits, punctuation quirks, vocabulary do/don't lists, tone sliders, and three calibration paragraphs with self-checks. Other skills

Turns any idea into a live single-file HTML prototype in minutes — inline CSS/JS, CDN-only dependencies (cdnjs), mobile-first, seeded with believable fake data, interactive states wired — ready to open in a browser or paste as a Claude artifact. Use when the user says "prototype

Browser-tests a local webapp end to end — starts the app, installs Playwright if missing, writes a spec for the critical path plus edge cases, runs headless, captures screenshots, console and network logs on failure, and reports a pass/fail table with repro steps. Degrades to cur

Designs and tests YouTube thumbnails — 3–5 concept briefs covering composition, face or object, a 3-word-max overlay, and colour contrast against YouTube's UI, each run through a curiosity check, a mobile legibility test at 168×94 px, and a /10 scoring rubric, ending in a verdict

Pre-implementation exploration: deep interview, approach comparison, design doc. Use when exploring a vague feature idea, clarifying ambiguous requirements, or comparing approaches before coding. For the full workflow, use the ia-brainstorm command (Claude Code).

C patterns for systems code, libraries, and native extensions: module layout, function decomposition, status-enum errors, memory safety, undefined behavior, and performance measurement. Use when writing, reviewing, refactoring, or debugging C, working with malloc lifetimes, buffe

Structured code reviews with severity-ranked findings and deep multi-agent mode. Use when performing a code review, auditing code quality, or critiquing PRs, MRs, or diffs. For the full multi-agent workflow, use the ia-review command (/ia-review in Claude Code).

Modern C++ patterns: RAII and ownership, rule of zero/five, exceptions and error handling, API and ABI boundaries, templates, and CMake tooling. Use when writing, reviewing, refactoring, or debugging C++, working with smart pointers, move semantics, memory leaks, template errors,

Systematic root-cause debugging with verification. Use for errors, stack traces, broken tests, flaky tests, regressions, or anything not working as expected. For validating bug reports before fixing, use bug-reproduction-validator agent.

Visual design and aesthetic direction for frontend interfaces. Use when building web pages, landing pages, dashboards, Next.js server components, or applications where visual identity matters. For React patterns and testing, use react-frontend.

Manage Git worktrees for isolated parallel development. Use when creating, listing, switching, or cleaning up git worktrees, or when needing isolated branches for concurrent reviews or feature work.

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

Paper trading simulator for Polymarket — built for AI agents. MCP server, live order books, strategy backtesting. Install: npx clawhub install polymarket-paper-…

An SSH tool dedicated to addressing all pain points · (macOS/Windows/Linux/Android/iOS)

The first AI agent harness native to the browser. A browser extension that runs a full agent loop where you already work: it drives your tabs, spins up sandboxe…

SmartLabel AI 2026: Auto-Annotate Any Object via LLM-Powered Prompt Parsing

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

Scholar All-In-One: A research infrastructure for AI agents

Give your AI agent a real browser — with a human in the loop. Open-source MCP-native browser agent.

同花顺免费开源AI插件FQGate-agent（原插件名 tonghuasun-agent）：为 Codex、Claude Code、DeepSeek 等 AI 工具提供本机 A 股实时行情、K 线、Level-2、资讯、账户查询与可选交易能力。

A non-linear AI agent workbench — session is a tree: branch anytime, and context follows the branch

Production-grade AutoCAD MCP server for AI agents — 122 tools, dual COM (live AutoCAD) + headless ezdxf engines, ISO GD&T and dimension-tolerance validation for…

A DeepSeek coding agent harness: persistent shell, Ultra subagents, auto approval, Chrome MCP and session telemetry

Waku Waku! Waku Agent is a local-first AI agent harness you actually own, including loop, memory, eval, all in code built to stay legible as it grows.

Remote control for Claude Code, Codex, Grok, and Cursor on Mac or PC. View sessions, send tasks, and drive them remotely from your phone, PIN, or Ring. OpenClaw…

Next-gen AI-native server ops panel with an in-workspace SRE agent. Crash self-healing, safe rollbacks, Docker/game servers, and local Ollama support.

Professional cloud architecture diagrams with official AWS, Azure and GCP icons, from Terraform code or a plain JSON graph. MCP server + agent skill.

A ready-to-use self-growing desktop AI assistant for long-running tasks, memory, agents, tool reviews, MCP, and high-concurrency workspace automation. / 开箱即用的自我…

Collection of templates using the Alchemyst AI Platform for your next big AI app.

Fast, exact LLM decoding on Apple Silicon (MLX) behind an OpenAI-compatible endpoint

The open source AI research agent.

Open-source agent-native visual production workspace where humans and coding agents edit the same live canvas — local-first, BYOK image/video models.