LLM Mart Basic

Use when the user asks which phx-* command fits a task (review, plan,

Initialize plugin in a project — install Iron Laws, auto-activation rules,

Walk through the Elixir/Phoenix plugin commands, workflow, and features

Investigate Elixir/Phoenix bugs root-cause first. Reproduce failures,

Use this skill for a specific cloud workflow. Mention provider, trigger phrases, expected inputs, and when not to use it.

Plan who does each step of a task in this repo, on which model, at which effort: Haiku or Sonnet subagents for search, recon, and log-reading; code edits on Opus 5.5; start at medium effort and escalate on evidence (high, then xhigh, then Fable 5.1 for one stuck task); the orches

The ordered finish-line runner for any change in this repo — generators, then the asset-integrity refresh last on its own, then the full gate suite, then commit and push; use before declaring any change finished or whenever the stop hook reports uncommitted or untracked changes.

Re-verify and extend catalog/model-registry.json — the fail-closed model-name and reasoning-effort matrix scripts/model-policy.mjs validates against — via delegated Context7-backed research, orchestrator-owned registry edits, and the full validation chain; use when a policy check

The repeatable loop for watching a pull request until it is merged or closed, pairing webhook subscription with a scheduled self check-in so CI results, new pushes, and merge-conflict transitions are never missed; use when asked to watch, babysit, or autofix a PR, or right after

Route accounting questions to the narrowest specialist in the catalog. Use when you do not already know the specialist needed. Not for direct accounting answers; Maestro classifies, dispatches, and synthesizes only. Dispatches single agent for focused tasks, parallel team (max 3)

Multi-jurisdiction business combinations reference framework covering acquisition accounting, purchase price allocation, goodwill, and post-combination integration under ASC 805 and IFRS 3.

Multi-jurisdiction financial close cycle reference framework covering month-end, quarter-end, and year-end close. Provides regulatory filing deadlines by jurisdiction (SEC, EU TD, UK DTR, TSE/FSA, CSRC, SEBI, ASX, HKEX), record-to-report process steps, reconciliation standards, i

Multi-jurisdiction consolidation scope and intercompany elimination reference framework covering ASC 810 / IFRS 10 control models, VIE (Variable Interest Entity) primary beneficiary analysis, NCI measurement, equity method accounting (ASC 323 / IAS 28), intercompany eliminations

Multi-jurisdiction equity-based compensation reference framework covering stock options, RSUs, ESPPs, and performance awards under ASC 718 and IFRS 2.

Multi-jurisdiction fixed assets, depreciation, and impairment reference framework covering PP&E, intangibles, right-of-use assets, and goodwill under US GAAP and IFRS.

Multi-jurisdiction reference framework for foreign currency translation and remeasurement covering functional currency determination, ASC 830 / IAS 21 method selection, CTA in OCI, highly inflationary economy treatment, net investment hedge interactions, and multi-GAAP comparison

Multi-jurisdiction hedge accounting reference framework covering ASC 815 (US GAAP) and IFRS 9 hedge designation, effectiveness testing, OCI mechanics, IFRS 9 rebalancing, cost-of-hedging approach, discontinuation rules, embedded derivatives, and local GAAP treatments (German HGB

Multi-jurisdiction indirect tax and e-invoicing reference framework covering VAT/GST compliance and mandatory electronic invoicing mandates across EU, Brazil, India, Mexico, China, UK, and Australia.

Multi-jurisdiction lease accounting reference framework covering ASC 842 (US GAAP) and IFRS 16, with additional coverage of UK FRS 102 (2024 periodic review amendments effective 1 Jan 2026), German HGB, JGAAP (ASBJ Statement No. 34, effective FY beginning on/after 1 Apr 2027), CA

Multi-jurisdiction payroll accounting reference framework covering compensation expense recognition, employee benefits, pension/post-retirement obligations, and payroll tax compliance.

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

Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control.

An open-source Digital Worker platform for reliable execution, continuous co-evolution, and building Enterprise AI assets.

A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

A governance harness for AI coding.

DeepSeek Harness 手机版：可直接安装的 Android APK，AI 免 Root 操作手机（Shizuku/root 可选），文件编辑只需所有文件访问权限，前台保活 + AI 通知

Local-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.

Orbi — the factory that builds and operates AI software factories. GitHub Issues in, releases and runnable system out

Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.

The SDK for browser agents. Interact, search, extract, and fetch any site reliably across the web

Agent-native shopping for extreme value: verifiable same-product price evidence, checkout, orders, delivery, and after-sales.

The extensible power-user platform for Google Antigravity. Adds a native In-App Browser, animated Desktop Pets, revamped Gemini UI, and custom BYOK Gemini Pro k…

Open-source, single-binary, self-hosted AI agent — your models and data stay on your machine. A coding agent on par with Claude Code and a personal assistant li…

Your pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH · Claude Code · Code…

Bridge between QQ (SnowLuma OneBot v11) and DeepSeek Harness agents: social simulation, safe MCP tools, slang learning and more.

A 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from Claude Code, Aider,…

针对 AI 自动化渗透 Agent 的新一代反制蜜罐，通过反向代理将API密饵载入真实业务、反向提示词注入等方式反制自动化渗透 Agent，实现多款主流通用Agent的反制上线控制。

Open-source, local-first AI agent for coding and real work. BYOK models, MCP, skills, plugins, workflows, and private knowledge bases.

A free AI-agent toolbox for Android, 一站式安卓AI Agent工具箱

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. I…

Independent, unofficial CLI to edit CapCut and JianYing (剪映) projects — subtitles, timing, speed, volume, templates, cut long-form to shorts. No API needed, rea…