LLM Mart Basic

Audit game narrative systems for technical quality -- branching dialogue trees, state/flag tracking, quest systems, choice-consequence mapping, localization pipelines, voice-over integration, and cinematic scripting..

Feature discovery agent — mines project docs, memory, user feedback, and competitor gaps to surface the highest-leverage features to build next. Outputs a prioritized feature backlog.

Map a cloud system against NIST SP 800-53 Rev. 5 + FedRAMP baselines to produce the documentation an authorization needs — System Security Plan (SSP), Control Implementation Summary (CIS), Plan of Action and Milestones (POA&M), Continuous Monitoring (ConMon) Plan..

Audit patient-facing healthcare software for portal feature completeness, secure messaging, health literacy, telehealth readiness, consent management, and HIPAA compliance. Triggers: evaluating a patient portal, checking PHI exposure in notifications, auditing telehealth flows.

Generate a production-grade Product Detail Page (PDP) optimized for the 2026 conversion benchmarks — 4-8% target vs 1.5-3% average. Triggers: "product page", "PDP", "product detail page", "Shopify product page", "ecommerce conversion".

Audit academic peer review operations -- reviewer matching algorithms, conflict of interest detection, turnaround time optimization, review quality scoring, and editorial workflow management..

Audit game analytics and telemetry implementation -- event tracking completeness, FTUE and monetization funnel coverage, retention metric infrastructure, A/B testing framework, heatmap data collection, churn prediction signals, and LTV modeling support..

Audit a codebase for product-market fit readiness -- evaluate startup PMF signals, core value loop tightness, feature scatter vs focus ratio, user activation funnel friction, retention hook infrastructure, pricing flexibility, analytics event coverage, CI/CD iteration speed, and

Audio file → full publishing kit pipeline. From a single .mp3 or .wav per episode, generates Whisper-large-v3 transcript with word-level timestamps, automatic chapter detection (audio scene change + topic shift), two show-notes lengths (scannable summary + long-form SEO).

Audit investment portfolio management software for mean-variance optimization, Black-Litterman model, risk parity allocation, VaR/CVaR risk metrics, Brinson performance attribution, tax-loss harvesting rebalancing logic, Sharpe ratio calculations, efficient frontier accuracy.

Audit manufacturing predictive maintenance systems for OPC-UA/MQTT sensor data pipelines, time-series storage retention, ML model lifecycle (training-serving skew, drift detection, retraining triggers), MTBF/MTTF/MTTR reliability calculations, Weibull survival analysis.

Audit pricing research and sensitivity analysis systems for Van Westendorp price sensitivity meter (OPP/IDP/PMC/PME intersections), Gabor-Granger demand curves, Newton-Miller-Smith revenue extension, price elasticity econometric modeling, willingness-to-pay estimation.

Audit procurement and procure-to-pay systems for spend analytics (Pareto analysis, tail spend visibility), supplier consolidation opportunities, Kraljic matrix category management, maverick spending detection, contract compliance and utilization tracking, three-way PO matching.

Audit film, television, and digital content production budgets for above-the-line (ATL) and below-the-line (BTL) cost accuracy, SAG-AFTRA/DGA/WGA/IATSE union rate compliance, fringe and payroll tax calculations, VFX bid variance analysis, post-production cost validation.

Audit manufacturing production optimization systems for OEE (Overall Equipment Effectiveness) calculation accuracy, Six Big Losses categorization, job shop and flow shop scheduling algorithms (LP, MIP, constraint programming, genetic algorithm), Theory of Constraints bottleneck d

Audit factory production scheduling systems for finite capacity planning, Drum-Buffer-Rope (DBR) Theory of Constraints implementation, dispatching rules (EDD, SPT, critical ratio), sequence-dependent changeover optimization, MRP integration.

Audit real estate investment software for IRR/NPV/cap rate/cash-on-cash return calculations, pro forma income modeling (GPR, vacancy, rent growth, NNN pass-throughs), equity waterfall and promote structures, debt modeling (fixed/ARM/IO/construction loans).

Audit public sector and government resource allocation systems for budget optimization algorithms (zero-based, incremental, performance-based), service demand forecasting (ARIMA, Prophet, regression), equity-based distribution scoring (CDC SVI, environmental justice indices.

Audit a quoting or estimation system -- analyze labor hour estimation accuracy, material take-off completeness, pricing rule engines, markup and margin optimization, good-better-best tiered pricing, and quote-to-close win rates.

Audit a real estate analytics platform -- evaluate comparable sales and rental engines, automated valuation models (AVM), demographic and economic indicator pipelines, submarket scoring, gentrification detection, price forecasting accuracy, market cycle analysis, and risk modelin

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.