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.

{{SKILL_ENTRY:refactor}}

{{SKILL_ENTRY:release}}

Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR.

Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or {{CMD:feature}}.

Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard gates remain true stops.

Daily repo hygiene — review the day's repo state, then perform the cleanups under per-action confirmation. Fast-forward only, never destructive without a yes.

Show the project's current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current branch. Read-only.

Wire codeArbiter's statusline into ~/.claude/settings.json, or remove it.

The sanctioned task-board mutator — add a queued task, start one (flips to in-progress and stamps the date, minting a dotted ID on pick-up), or mark an in-progress task done. The only blessed write to open-tasks.md.

{{SKILL_ENTRY:security-architecture}}

{{SKILL_ENTRY:tribunal}}

Watch a PR's CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges.

Copy a file OUT of a running sandbox box to the host — host-initiated egress only (docker cp). The reverse, a host→container bind, is impossible by construction.

Tear down a sandbox box — remove its container and named volume. --keep-volume leaves the volume; with no id, prune reclaims any leaked ca.sandbox=1-labeled object. Cached images are retained.

Run a single command inside a running sandbox box and capture a JSON result — exitCode, separate stdout/stderr, and a truncated flag past the byte cap. The scriptable exec seam.

Open an interactive shell inside a running sandbox box at /work/repo. Read-only root, non-root user, no host-FS access — explore the untrusted code interactively, then exit.

Pull an untrusted repo into an ephemeral, host-FS-isolated Docker container — clone into a named volume, build a dep-cached image, run under structural isolation. Network defaults to offline. Requires Docker and nixpacks.

Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.

Inspect ADR health read-only; optionally select one ADR with --adr N.

Record user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.

Open‑WebUI Tools is a modular toolkit designed to extend and enrich your Open WebUI instance, turning it into a powerful AI workstation. With a suite of over 15…

The token-efficient agentic coding workbench. Built for a future where every token counts — it optimizes token usage at the agent-loop level, saving 70%+ on lon…

MCP server for controlling a real iPhone via macOS iPhone Mirroring...and any MacOs app. Screenshot, tap, swipe, type — from any MCP client.

One desktop for all your AI coding Agent — Claude Code, Codex CLI & Gemini CLI. Auto-detect, one-click install, unified chat, file explorer, terminal & editor.…

Pi — A cross-platform AI coding agent, bringing the Claude Code experience to your desktop. No environment setup, no terminal commands. Download and start codin…

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…

A telegram bot for searching and auto-saving.

金蝶云星空 K3Cloud MCP Server，让 AI 助手（Claude Desktop、Claude Code、Cursor、Cline、Cherry Studio、Openclaw 等任意支持 MCP 协议的客户端）通过自然语言查询和操作金蝶 ERP 系统。

Rewrite frontier research using allegorical structural mapping.

Free4Chat is a temporary collaboration fabric for Humans and Agents.

Give any AI agent a full desktop — it sees the screen, clicks, types, and runs apps like a human. Automate anything with a UI: browsers, legacy software, intern…

A personal AI agent that can work safely on your machine, remember useful context, and keep its data under your control.

A framework for AI-driven economic activity. Declarative, composable, observable, deterministic.

Open-source, self-hosted customer support desk in a single binary. A lightweight alternative to Intercom, Zendesk, Chatwoot.

54 rigorous skills for Codex, OpenCode, and Pi: code review, security audit, feature development, frontend design, MCP tools, Hugging Face ML/training, and more…

A wonderful list of Game Development resources.

Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux. Open-source Claude Science desktop alternative built on Tau…

Lexora — Personal AI workspace built around Desktop / 以 Desktop 为核心的个人 AI 工作台

Open-source, AI-native Evernote alternative with native MCP. Zero-cost on Cloudflare or self-hosted with Docker.

Full job-hunt Claude skill bundle — Job Description decoder + Resume builder (11 templates) + Behavioral Interview / story bank. Three self-contained sub-skills…