LLM Mart Basic

Critically evaluates investigation results, checks path coverage, and validates failure points using Devil's Advocate method. Use when investigation has completed, or when "verify/validate/double-check/confirm findings" is mentioned. Focuses on verification and conclusion derivat

Creates implementation-focused work plans from approved Design Docs. Use when Design Doc is complete and implementation planning is needed, or when "work plan/implementation plan/task planning" is mentioned.

Generates integration/E2E test skeletons from Design Doc ACs using ROI-based selection and journey-based E2E reservation. Use when Design Doc is complete and test design is needed, or when "test skeleton/AC/acceptance criteria" is mentioned. Behavior-first approach for minimal te

Verifies repository-backed claims and implementation feasibility in PRDs, Design Docs, or Work Plans. Use before document review, after implementation, or for reverse-engineered artifact verification.

Collects compact repository evidence for scope confirmation, technical option selection, complete design, and verification. Use before Design Doc creation when repository facts can change scope, reuse, contracts, cost, or proof.

Detects conflicts across multiple Design Docs and provides structured reports. Use when multiple Design Docs exist, or when "consistency/conflict/sync/between documents" is mentioned. Focuses on detection and reporting only, no modifications.

Reviews one document or one ADR batch against governing requirements, repository evidence, and the needs of its next consumer. Use before user approval or when document consistency and completeness need verification.

Verifies changed integration and E2E tests against skeletons, proof obligations, or explicit prompt claims. Use PROACTIVELY after test implementation completes, or when "test review/skeleton verification" is mentioned. Returns quality reports with failing items and fix instructio

Comprehensively collects problem-related information and creates evidence matrix. Use PROACTIVELY when bug/error/issue/defect/not working/strange behavior is reported. Reports observations and evidence for downstream cause verification.

Creates PRD and structures business requirements. Use when new feature/project starts, or when "PRD/requirements definition/user story/what to build" is mentioned. Defines user value and success metrics.

Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.

Collects compact scope and cost evidence for requirement confirmation while the user and orchestrator retain requirements, Structural Scale, and document-routing decisions. Use when new requirements, scope, or implementation extent must be confirmed.

Discovers functional scope from existing codebase for reverse documentation. Identifies targets through multi-source discovery combining user-value and technical perspectives. Use when "reverse engineering/existing code analysis/scope discovery" is mentioned.

Reviews implementation for security compliance against an authoritative Design Doc or Work Plan. Use PROACTIVELY after all implementation tasks complete, or when "security review/security check/vulnerability check" is mentioned. Returns structured findings with risk classificatio

Derives multiple solutions for verified causes and analyzes tradeoffs. Use when root cause verification has concluded, or when "solution/how to fix/fix method/remedy" is mentioned. Focuses on solutions from given conclusions without investigation.

Converts an approved Work Plan into the fewest executable implementation task files. Use when work plans are approved and task materialization is needed.

Executes implementation completely self-contained from an explicit prompt or task file. Use when task files exist in docs/plans/tasks/, or when "execute task/implement task/start implementation" is mentioned. Asks no questions, executes consistently from investigation to implemen

Creates a scoped ADR batch or one backend/general Design Doc from confirmed requirements and decision-relevant repository evidence. Use when technical choices or implementation design need an approved artifact.

Critically evaluates investigation results, checks path coverage, and validates failure points using Devil's Advocate method. Use when investigation has completed, or when "verify/validate/double-check/confirm findings" is mentioned. Focuses on verification and conclusion derivat

Creates implementation-focused work plans from approved Design Docs. Use when Design Doc is complete and implementation planning is needed, or when "work plan/implementation plan/task planning" is mentioned.

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.

This is the only sanctioned way a version tag gets created, and it holds no knowledge of any

A read-only review of the current change, dispatched by path against a reviewer-to-path matrix:

This is the outlet for "I need to write code to find out" rather than "I know what to build." The

This is codeArbiter's autonomy mode. It collapses the usual spec-plan-execute cycle into one

The daily hygiene checklist, made routine and gated: fetch and offer a fast-forward pull, list

A read-only snapshot of `.codearbiter/` state: the project's `stage:` maturity value, every

Wires codeArbiter's renderer into `~/.claude/settings.json`, or removes it. A plugin can't own a

The only blessed way to mutate `.codearbiter/open-tasks.md`. It runs a thin writer over pure

An opt-in, lightweight STRIDE pass over a design before it's built — invoked deliberately, never

codeArbiter's deepest, most expensive review, convened rarely and never as a required gate. Eleven

Watches a pull request's CI checks to completion without polling by hand. The wait is a real

A fixture command named debug, colliding with the debug skill/agent.

A fixture command named prune, used to regression-test forge badges.

Another command, description only, no argument hint.

A sample command for fixtures — single sanctioned path to a thing.

Convert an animated HTML file (like /fig output) to a perfectly looping high-quality small GIF using Playwright + ffmpeg

Find a free licensed image on the internet and add it to the project, optimized

Art-direction photo pass over the site: add photography only where it earns its place

Audit consolidate or forget stale sensitive or superseded Tree Ring Memory entries

Capture a concise validated lesson decision warning or preference in Tree Ring Memory

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it.…

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

:memo: Vimlike Modal Text Editor in Rust

CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Hermes Agent memory plugin/provider for scope-aware recall, SQLite truth, LanceDB semantic search, and hybrid retrieval.

For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式，带到每一个 AI 工具里。

A coding agent: give it a prompt and it reads, writes, runs commands, and searches code in a loop until the work is done, using native tool-calling across OpenA…

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and…

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

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…

See your agent think. Zero-config observability & governance for 26 AI agent runtimes: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, Ope…

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP…

Yet another coding agent harness, lightweight and written in go.

a coding Agent from pi. ∞ providers, sub-agents, hashline edits, and a permission gate

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting…

🧠 Leon is your open-source personal assistant.

The Station, an open-world multi-agent environment that models a miniature scientific ecosystem.

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

VelaTerm = iTerm2 + Codex, The Best Terminal for AI Coding