LLM Mart Basic

Multi-jurisdiction reference framework for corporate capital allocation, investment appraisal (NPV, IRR, MIRR, payback, profitability index), cost of capital (WACC, CAPM, hurdle rates), M&A valuation methods (DCF, trading comparables, precedent transactions, accretion/dilution),

Multi-jurisdiction reference framework for debt and capital structure advisory — optimal capital structure theory (M&M, trade-off, pecking order), leverage and credit metrics, debt instruments, covenant analysis, refinancing, WACC optimization, Basel III/IV capital requirements,

Route corporate finance questions to the narrowest specialist in the catalog. Use when you do not already know the specialist needed. Not for direct finance answers; Maestro classifies, dispatches, and synthesizes only. Dispatches single agent for focused tasks, parallel team (ma

Reference framework for financial planning and analysis (FP&A) covering driver-based budgeting, rolling forecasts, zero-based budgeting (ZBB), scenario and sensitivity analysis, budget-versus-actual variance analysis, long-range planning (LRP), integrated P&L/balance sheet/cash f

Multi-jurisdiction reference framework for OECD transfer pricing (arm's length principle, five TP methods, BEPS Action 13 documentation, CbCR) and OECD Pillar Two GloBE rules (IIR, UTPR, QDMTT, ETR computation, SBIE carve-outs, safe harbors, deferred tax divergence under IAS 12 v

Multi-jurisdiction reference framework for corporate treasury operations, cash and liquidity management, FX and currency risk, hedge accounting qualification (ASC 815 / IFRS 9), FX translation (ASC 830 / IAS 21), Basel III LCR/NSFR, Dodd-Frank and EMIR derivatives reporting, and

Variance decomposition framework and SEC Regulation S-K Item 303 MD&A commentary guidance for FP&A and corporate finance teams. Provides driver decomposition methodology (Volume/Price/Rate/Mix/One-Time), MD&A structural requirements with regulatory citations, restatement-risk tri

Multi-jurisdiction reference framework for working capital management — cash conversion cycle (CCC) optimization, accounts receivable management (collections, credit policy, aging analysis, factoring, invoice discounting, AR securitization, ASC 860 / IFRS 9 SPPI derecognition), a

Pair every cloud spend value with a kgCO2e estimate by region and service category for CSRD and SEC climate disclosure. Input is region, service category, and dollar value; output is paired kgCO2e with confidence label (vendor-published, third-party, or estimated) and source cita

Fetch live per-token, per-image, and per-GPU-hour prices for foundation models across Anthropic, OpenAI, Google, AWS Bedrock, Azure OpenAI, OCI Generative AI, and Vertex AI. Supports single-model lookup and comparative multi-provider tables. Every price is labeled with source URL

Fetch live public prices and build cost estimates for AWS, Azure, OCI, Scaleway, Gandi, Alibaba Cloud, and Tencent Cloud using each provider's public pricing API or official documentation. Supports live-environment cost analysis and prototype cost planning. Currency defaults to U

Normalize vendor-specific billing rows (AWS CUR, Azure Cost Management, GCP Billing Export, OCI) into FOCUS v1.2 columns from user-pasted CSV or JSON input. Refuses to invent column values not derivable from the input. No credentials accepted; operates on user-supplied data only.

Emit pod CPU and memory request/limit recommendations from user-pasted p50, p95, and p99 utilization metrics over a 7-14 day window. Outputs recommended requests at p95 plus 20% headroom, limits at p99 plus 30%, estimated monthly savings, and Karpenter consolidation eligibility f

Use this skill when reviewing FluxCD Kustomization, HelmRelease, GitRepository, HelmRepository, or OCIRepository resources. Trigger when the user asks whether a Flux configuration is safe for production, whether SOPS encryption is required, whether prune is safe on a given worklo

Apply an elevated review pass to AI or LLM-generated frontend code changes, checking specifically for hallucinated framework APIs, slopsquatted or non-existent dependency names, unsanitized dynamic-HTML sinks, and missing accessibility semantics before the diff is merged.

Statically review Angular component and service architecture for correct Signals usage (signal/computed/effect boundaries and purity), appropriate change-detection strategy (OnPush vs default), and service/DI boundary design, grounded in Angular's own Signals, change-detection, a

Statically review Angular SSR bootstrap configuration and component templates for hydration-mismatch risk (NG0500-class errors), unjustified ngSkipHydration usage, and direct-DOM-manipulation patterns that bypass Angular's template-owned DOM model, grounded in Angular's own hydra

Statically review Angular templates and components for injection via DomSanitizer bypass calls (bypassSecurityTrustHtml, bypassSecurityTrustUrl, bypassSecurityTrustResourceUrl), unsanitized [innerHTML] bindings, and dynamically bound iframe security attributes such as [attr.sandb

Reviews frontend-to-backend API contracts — BFF route handlers and direct backend calls — for data-minimization, server-side object-level authorization enforcement, error-shape leakage, CORS misconfiguration, and backward-compatible versioning before they ship.

Audit JS/CSS/HTML feature usage against the project's declared Browserslist/supported-browser matrix using Baseline and caniuse status data, flag unguarded non-Baseline usage, and verify feature-detection or polyfill fallback coverage, with per-feature caniuse/Baseline lookups lo

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.

`crabbox attach` follows the recorded events of an active coordinator run and

`crabbox azure` groups Azure provider setup commands. It currently has a single

`crabbox bench` records and reports local benchmark timing observations. It is a

`crabbox cache` inspects, purges, or warms package and build caches on a

`crabbox capsule` captures, replays, and tracks lightweight failure capsules.

Save the state of a lease, then restore it onto another box or fork it into a

`crabbox claims list` prints the lease claims stored on the current machine. It

`crabbox cleanup` sweeps direct-provider machines and local provider state that

`crabbox code` bridges a Linux lease's `code-server` workspace into the

`crabbox config` inspects and updates user configuration. It has three

`crabbox connect` resolves a lease and opens an interactive SSH session to it.

`crabbox cp` copies files or directories between the host and a Crabbox-owned

`crabbox desktop` drives a visible desktop session on a lease that was warmed

`crabbox doctor` runs a preflight before you commit to a long workflow. It is

`crabbox egress` gives a lease mediated outbound network: a lease-local browser

`crabbox events` prints the broker's event log for a recorded run.

`crabbox heartbeat` refreshes the idle deadline for one owned lease and prints

`crabbox history` lists recorded remote command runs from the broker. Each run is

`crabbox image` holds the trusted-operator controls for provider base images:

`crabbox init` onboards the current repository: it writes the minimal config

Atom Agent, Open-Source Governed AI Agent Platform for Self-Hosted Automation

The agent engineering intelligence harness, optimized tools, memory system, subagents and mixture of models packages ⚚

Sesori iOS/Android app and the Sesori Bridge CLI — drive Claude, Codex, OpenCode, Cursor, Pi, OMP, Hermes coding sessions from your phone

🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.

Use ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers — OAuth login in the web UI, no API keys

Latitude is the open-source AI monitoring platform.

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

Official Model Studio CLI（阿里云百炼 CLI）built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.

Curated DeepSeek Harness (DSH) plugins, extensions, tools, skills, clients, runtimes, integrations, and verified references — English and Chinese.

Turn papers, code, and docs into presentation-ready, natively editable PPTX in Codex / Claude Code. Native charts and equations, speaker notes, click-build anim…

Grix : Work with agents like talking to people.

Local First Ai Agent. Optimized for Local Ai models. Long context window. Proper tools callings. Runs privately on your device.

Model Context Protocol server that integrates AgentQL's data extraction capabilities.

AI that ships your tickets.

Metadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.

An open-source, extensible, self-hosted agent workspace with multi-runtime support for Codex, Claude Code, and more, plus reusable local apps for custom interfa…

Open-source Windows desktop client and GUI for DeepSeek Harness — zero-setup installer with Codex, plugins, skills, SSH, mobile remote access, and 11 skins.

The open-source AI workbench for scientific research

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

A Fully free agentic browser driver for AI , few tools, full control, real stealth, top-tier token efficiency.