LLM Mart Basic

Generate and run unit, API, and E2E tests (including Playwright) that match project conventions. Use when adding coverage or reproducing a bug with a failing test first.

Map the attack surface and build a STRIDE threat model - trust boundaries, data flows, entry points, assets, and prioritized threats with mitigations. Use for /threatmap, architecture security reviews, or "what could go wrong?" planning.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Verify and install missing CLI tools on demand - scanners, linters, runtimes - without root, using uvx, npx, or static binaries in ~/.local/bin. Use at the start of any audit, scan, or build when a needed tool may be absent.

Run the Navin Trading Agent OS. Use when the user wants a programmable investment agent, paper portfolio, market scan, debate, risk limits, backtest, or /trading.

Translate and localize between French, English, and Arabic - adapting idioms, register, formats, and cultural context, not just words. Use for any cross-language content.

Default web UI/UX design intelligence for Navin. Design-system generator (84 styles, 192 palettes, typography, landing patterns, UX rules) plus mandatory framer-motion for all web sites. Use when building, designing, scaffolding, or reviewing any website, landing page, dashboard,

One-time setup wizard for the navin upgrade skill. Triggers: setup update, configure update, 切设置更新, 初始化更新.

Value / quality screen for the Trading Agent OS. Prefer cash-generative names with reasonable debt and a margin of safety.

Generate short videos with the generate_video tool (Veo, Sora, Hailuo) - scripts, storyboards, scene-by-scene AI generation, and ffmpeg assembly. Use for social clips, product demos, and ads.

Hunt for concrete, exploitable vulnerabilities - OWASP Top 10 patterns, hardcoded secrets, vulnerable dependencies and CVEs, SSRF, path traversal. Use for /probe, dependency audits, or "find the flaws" requests.

Get current weather and forecasts (no API key required).

Turn websites into clean Markdown or structured JSON for RAG, migrations, or analysis. Use when the user needs scraped content, tables, or documentation corpora - not full browser testing.

Detect changes in price, content, tenders, or availability and alert only on meaningful deltas. Use with cron or .navin/HEARTBEAT.md for recurring checks.

Run a project's engineering decisions as a living log — MADR-lite ADRs (supersede, never delete) for decisions expensive to reverse, issues for the work (and its cheap-to-reverse choices), research artifacts, an optional PRD, a project constitution, and living Mermaid architectur

Author and validate knowledge as OKF (Open Knowledge Format) bundles — a directory of markdown files with YAML frontmatter, where every concept is one .md file with a REQUIRED `type` field, reserved index.md/log.md files, bundle-relative cross-links, and a permissive conformance

Organize, format, and index research as OKF-conformant knowledge bundles — dated, sourced, append-only snapshots of the external evidence behind a decision (technology evaluations, library comparisons, industry-practice surveys). Use when recording research output, structuring a

Add a new declarative attribute to the better-data library (e.g. #[ArrayOf], #[Default], domain hint). Attributes live in src/Attribute/ as final readonly classes with constructor-promoted public properties — pure data carriers, never business logic. The failure mode that catches

Compose better-data DTOs with the better-route library — use BetterRouteBridge::{get, post, put, patch, delete} to register a REST route that hydrates the request into a DTO, validates, calls the handler with (DataObject, mixed $request), and presents returned DataObject values t

Work on better-data-plugin-test — the companion plugin

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.

Implement GraphQL API endpoints

Initialize new project with essential structure

Build reference documentation by creating markdown files and updating CLAUDE.md

Convert GitHub issues to Linear tasks

Triage and prioritize issues effectively

Convert Linear tasks to GitHub issues

READ the llms.txt file from https://raw.githubusercontent.com/ethpandaops/xatu-data/refs/heads/master/llms.txt via `curl`. Do nothing else and await further instructions.

Log work from orchestrated tasks to external project management tools like Linear, Obsidian, Jira, or GitHub Issues.

Model customer and market responses with segment analysis, behavioral prediction, and response optimization.

Clean and organize project memory

Create entity relationship diagrams using Mermaid from SQL/database files

Migrate JavaScript project to TypeScript

Assist with system migration planning

Create migration guides for updates

Track and monitor project milestone progress

Update and modernize project dependencies

Move tasks between status folders following the task management protocol.

Optimize build processes and speed

Reduce and optimize bundle sizes

Optimize database queries and performance

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.