LLM Mart Basic

Audit how visible your brand is inside AI answers (ChatGPT, Claude, Gemini, Perplexity, AI Overviews). Claude builds a prompt panel for your category, scores where you show up vs competitors, and turns the gaps into a prioritized fix list. Platform: AI visibility.

Catches unusual performance changes across your accounts — CPC spikes, CVR drops, spend surges, impression collapses, CTR shifts — and flags them with context about what likely changed. The goal is to catch problems in hours instead of discovering them days later during a routine

Runs your conversion data through different attribution models side by side — last click, first click, linear, time decay, position based, and data-driven. Shows you how credit shifts between campaigns depending on the model so you can make better budget decisions instead of over

Compares your Meta ad sets and identifies where audiences overlap significantly, causing your ads to compete against each other in the same auctions. Tells you exactly which ad sets are cannibalizing each other and how much it's costing you in inflated CPMs. Platform: Meta.

Analyzes your campaign history, conversion volume, CPA targets, and auction dynamics, then recommends the right bid strategy for each campaign — manual CPC, target CPA, target ROAS, maximize conversions, or maximize conversion value. Not a blanket recommendation, but campaign-by-

Track how AI assistants describe your brand over time and catch wrong, outdated, or damaging claims. Claude builds your monitoring prompt set, compares runs week over week, and drafts the correction plan when answers drift. Platform: AI visibility.

Models what happens to your CPA, ROAS, conversion volume, and impression share when you increase or decrease budget by any amount. Uses your actual account data and historical diminishing returns patterns, not generic industry assumptions. Platform: Google and Meta.

Builds a consistent, filterable naming convention across your Google and Meta accounts based on your campaign types, objectives, targeting, and reporting needs. Makes filtering, reporting, and cross-platform analysis actually work instead of guessing what "Campaign_v3_Final_NEW"

Given your total budget, recommends the optimal split across Google Search, PMax, Meta prospecting, Meta retargeting, and any other active channels based on your last 60-90 days of marginal ROAS and CPA by channel. Tells you where each additional dollar produces the best return.

Find the exact pages AI assistants cite when answering questions in your category, and identify which ones you can get into. Claude clusters the cited sources, scores each by attainability, and outputs an outreach/content plan. Platform: AI visibility.

Takes your raw campaign performance data and writes the executive summary paragraph that goes at the top of the report. The plain English explanation of what happened, why it happened, and what's being done about it. The part every client actually reads. Platform: Google and Meta

Pulls competitor ads from Meta Ad Library and Google Ads Transparency Center, categorizes their messaging angles, formats, CTAs, and creative types, then identifies gaps in their approach you can exploit and patterns worth testing in your own campaigns. Platform: Meta.

Systematic competitive analysis covering positioning, messaging hierarchy, objection handling, and CTA strategy from landing page URLs or screenshots. Use when pasting a competitor URL, uploading competitor screenshots, requesting positioning analysis, or needing to understand co

Rewrite existing pages so AI assistants can extract, quote, and cite them. Claude restructures your content into answer-ready blocks — direct answers, comparison tables, stats with sources, schema — without wrecking the human reading experience. Platform: AI visibility.

Transform one long-form piece into multiple platform-specific content derivatives including LinkedIn posts, tweet threads, email snippets, ad hooks, and video scripts while maintaining voice consistency. Use when given a blog post, article, or pillar content to atomize across cha

Maps out how users move through your funnel from first ad click to conversion. Identifies where the biggest drop-offs happen, which campaigns contribute most at each stage, and how long the typical conversion path takes across different audience segments. Platform: Google and Met

When your CPA spikes, Claude breaks down exactly what caused it. It looks across your campaign data and isolates the contributing factors — audience fatigue, bid landscape shifts, creative decay, landing page conversion drops, budget distribution changes, or new competitor activi

Monitors your ads for early signs of fatigue before performance fully collapses. Tracks frequency buildup, CTR decay, CPM increases, and engagement drops across all active creatives and tells you which ones need rotation now vs next week. Platform: Meta.

Analyzes performance by day of week and hour of day across your campaigns. Identifies when your ads perform best and worst, recommends ad schedule adjustments with estimated savings, and tells you exactly what you'd give up by restricting hours. Platform: Google and Meta.

Analyzes how your campaigns perform across mobile, desktop, and tablet. Identifies where device performance diverges significantly and recommends bid adjustments, campaign splits, or creative/landing page changes to capture the gap. Platform: Google and Meta.

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 Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it.…

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

:memo: Vimlike Modal Text Editor in Rust

CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Hermes Agent memory plugin/provider for scope-aware recall, SQLite truth, LanceDB semantic search, and hybrid retrieval.

For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式，带到每一个 AI 工具里。

A coding agent: give it a prompt and it reads, writes, runs commands, and searches code in a loop until the work is done, using native tool-calling across OpenA…

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and…

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

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…

See your agent think. Zero-config observability & governance for 26 AI agent runtimes: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, Ope…

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP…

Yet another coding agent harness, lightweight and written in go.

a coding Agent from pi. ∞ providers, sub-agents, hashline edits, and a permission gate

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting…

🧠 Leon is your open-source personal assistant.

The Station, an open-world multi-agent environment that models a miniature scientific ecosystem.

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

VelaTerm = iTerm2 + Codex, The Best Terminal for AI Coding