LLM Mart Basic

Read a detached Codex bridge job's current state.

Ask Claude Code a read-only question from Codex through the sandbox-external bridge.

Ask Claude Code to implement one bounded write-capable change through the sandbox-external bridge.

Request a read-only adversarial review from Claude Code through the sandbox-external bridge.

Configure, authenticate, repair, and verify the Codex to Claude Code Bridge; safe stages run by default and sensitive stages require separate approval.

Safely manage Codex Rig role-agent shims: doctor, status, install, or remove; one action only.

Audit Codex configuration, workflow, and prompt-efficiency (instruction cost, value-per-token) drift; emit ranked gaps and measurable gates.

Calibrate skills/role cards for leaks/gaps with recall, precision, and confidence-accuracy checks.

Apply selected review fixes; bare PR targets use current online items, while PR +review adds the latest matching artifact.

Close PRs at an evidence gate or review local diffs/PRs with specialists and JSON artifacts.

Implement changes with a linear plan-build-verify workflow and measurable quality gates.

Investigate code debugging and root-cause narrowing; use measurable gates before fixes.

Build/extend grounded Kaggle Jupytext notebooks for training, EDA, inference, or resume workflows, grounding schema and submission format through the authenticated kaggle CLI.

Optimize a measurable metric with bounded iterations, guardrails, and regression gates.

Assess SemVer release readiness with gates/artifacts; never tag, publish, upload, or force-push.

Research docs, papers, or state of the art; provide source-backed recommendations and caveats.

Dry-run active plugin cache drift; refresh/reinstall only with approval; keep shims separate.

Adversarial review — drills to bedrock, treats claims as unproven until evidence. NOT for: plan design (foundry:solution-architect), test coverage (foundry:qa-specialist), config formatting (foundry:curator). TRIGGER: "challenge this", "devil's advocate", "poke holes in". SKIP: w

Content specialist — blog posts, slide decks, social threads, talk abstracts. Reads approved outline, applies four-beat arc. NOT for in-code docs/README/FAQs (foundry:doc-scribe), release notes (oss:release). TRIGGER: "write a blog post", "create slides", "draft a thread". SKIP:

Config quality reviewer. Scope: agents/skills/rules (*.md) — verbosity, duplication, cross-refs, roster overlap; applies fixes. NOT for hooks (foundry:sw-engineer), ADRs (foundry:solution-architect), adversarial challenge (foundry:challenger). TRIGGER: "audit this agent", "review

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 inspect` prints the full record for a single lease: state, provider,

Run named, repo-local jobs defined in your Crabbox config.

`crabbox list` shows the current Crabbox machines (leases) for a provider. It is

`crabbox login` authenticates the CLI against a coordinator, stores the

`crabbox logout` clears the stored broker token from your user config so the CLI

`crabbox logs` prints the retained command output for a recorded run.

`crabbox marketplace` previews the Crabbox credits gateway: one Crabbox billing

`crabbox media` turns a recorded desktop video into lightweight review

`crabbox open` prepares an existing SSH-capable lease for an external editor.

`crabbox pause` pauses a single lease, freeing the remote compute while

`crabbox pond` is the cross-provider peer-discovery and lifecycle surface for a

`crabbox pool` contains machine-pool helpers. `pool list` keeps the older

`crabbox ports` bridges provider-native port publishing for an existing Crabbox

`crabbox prewarm` leases a reusable box and prepares it for test runs. For

`crabbox providers` prints the provider capability matrix that the CLI compiles

`crabbox receipt <run-id>` retrieves a brokered run's committed terminal

`crabbox results` prints the structured test summary attached to a recorded

`crabbox resume` resumes a lease previously paused with [`pause`](pause.md),

`crabbox run` syncs the current dirty checkout to a box, runs a command there,

`crabbox screenshot` captures a single PNG from a desktop lease without opening a

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat ap…

Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evid…

Ultimate Multi-Agent OS for Autonomous AI NPCs 2026

Personal AI Agent Hub 2026 — Build Your 24/7 Autonomous Assistant

Proven 2026 Multi-Agent AI Review System – Verdict-Driven Quality Control

Slash API Batch: Cut AI Costs by 50% in 2026

Web dashboard for Hermes Agent — multi-platform AI chat, session management, scheduled jobs, usage analytics

Agent Skills for Solopreneurs

AirLLM dramatically reduces inference memory usage, letting 70B large language models run on a single 4GB GPU card

Zero, your trustworthy AI teammate for real work.

一套 DSH runtime，Desktop、Web 与 TUI 三种开发体验。

Open-source operational advisor for ClickHouse — real-time monitoring plus AI-driven index/partition/materialized-view recommendations.

⚙️ TypeScript Style Guide and Agent Skill. A concise set of conventions and best practices for consistent, maintainable code.

Framework for AI agents to build and maintain a digital brain through Obsidian wiki

Apache Maka (Incubating) is a local-first AI agent workspace. Model messages, tool calls, tool results, permission decisions, and termination events are recorde…

Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active H…

Agentic development harness for Claude Code — SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Sin…

NocoBase is an open-source AI + no-code platform for building business systems fast. Instead of generating everything from scratch, AI works on top of productio…

An open-source AI coding agent that lives in your terminal.

PawWork — free, open-source desktop AI agent for macOS and Windows. Alternative to Codex App and Claude Cowork. BYOK with 75+ providers, ChatGPT OAuth, local mo…