LLM Mart Basic

Post-install setup for foundry plugin. Run once after installing on a new machine, or after a plugin version upgrade to sync settings and symlinks. Merges statusLine, permissions.allow, enabledPlugins, and advisorModel into ~/.claude/settings.json; symlinks rules and TEAM_PROTOCO

Prepare release communication and check readiness. Main mode: notes with optional flags --changelog, --summary, --migration, --append (incremental: reruns the full pipeline scoped to newly-landed commits, integrating results into existing DRAFT.md/CHANGELOG.md/SUMMARY.md/MIGRATIO

OSS maintainer fast-close workflow for GitHub PRs. Three phases: (1) PR intelligence — reads full thread, linked issues, PR body to synthesize contribution motivation and classify every comment into action items; (2) conflict resolution — checks out PR branch (fork-aware via gh p

Multi-agent code review of GitHub Pull Requests (Python source, documentation (Markdown/RST), and CI/CD config PRs) covering architecture, tests, performance, docs, lint, security, and API design. TRIGGER when: user provides a GitHub PR number (e.g. 42, #42) and asks to review/au

Post-install setup for the oss plugin. Run once after installing on a new machine, or after a plugin version upgrade, to deliver this plugin's rules/*.md into ~/.claude/rules/ as namespaced symlinks. TRIGGER when: user installed or upgraded the oss plugin and its rules are not lo

Investigation-first debugging — gather evidence, form confirmed root-cause hypothesis, hand off to fix mode with diagnosis file. TRIGGER when: user reports a symptom or failing test with Python traceback, or asks to investigate a runtime/CI failure with reproducible evidence; phr

TDD-first feature development — crystallise API as a demo test, drive implementation to pass it, run quality stack and progressive review loop. TRIGGER when: user asks to build new functionality, add a capability, or implement a feature in a Python project; phrases: "add X", "imp

Reproduce-first bug resolution — capture bug in failing regression test, apply minimal fix, run quality stack and review loop. TRIGGER when: user reports a bug, regression, or unexpected behaviour in Python code with a traceback, failing test, or issue number; phrases: "fix this

Analysis-only planning — classify and scope a task without writing code; outputs a structured plan to .plans/active/. TRIGGER when: user wants to understand scope and risks before implementation; phrases: "plan this", "scope out X", "what would it take to Y", "analyse before we s

Test-first refactoring — audit coverage, add characterization tests, apply changes with safety net, run quality stack and review loop. TRIGGER when: user wants to restructure existing Python code without changing behaviour; phrases: "refactor X", "clean up Y", "extract Z", "restr

Multi-agent code review of local Python files, directories, or the current git diff covering architecture, tests, performance, docs, lint, security, and API design. Scope: Python source files in local working tree. Python-file-free targets (pure JS/TS/Go/Rust projects) are out of

Post-install setup for the develop plugin. Run once after installing on a new machine, or after a plugin version upgrade, to deliver this plugin's rules/*.md into ~/.claude/rules/ as namespaced symlinks. TRIGGER when: user installed or upgraded the develop plugin and its rules ar

Systematic ablation study runner. After research:run finds improvements, fortify identifies component candidates from git diff + diary, creates isolated git worktrees per ablation (main repo never modified), runs metric+guard in each worktree, ranks component importance, and opti

Research-supervisor review of program.md — validates experimental methodology (hypothesis clarity, measurement validity, control adequacy, scope, strategy fit), emits APPROVED / NEEDS-REVISION / BLOCKED verdict before expensive run loop.

Generate a Kaggle competition notebook as a Jupytext `# %%` Python script following the user's established ML research style: PTL for DNN training, best-fit tool selection, EDA→Baseline→Train→Inference pipeline with per-stage lens cells, small single-purpose cells each carrying a

Interactive wizard that scans the codebase, proposes a metric/guard/agent config, and writes a program.md run spec. Also runs cProfile on a file path to surface bottlenecks before prompting for optimization goal.

Post-run retrospective: reads .experiments/ JSONL, computes Wilcoxon significance, detects dead iterations, flags suspicious jumps, generates next-hypothesis queue for --hypothesis flag.

Sustained metric-improvement loop with atomic commits, auto-rollback, and experiment logging. Iterates with specialist agents, commits atomically, auto-rolls back on regression. Accepts a program.md file path. Supports --resume, --team, --colab, --codex, --researcher, --architect

Post-install setup for the research plugin. Run once after installing on a new machine, or after a plugin version upgrade, to deliver this plugin's rules/*.md into ~/.claude/rules/ as namespaced symlinks. TRIGGER when: user installed or upgraded the research plugin and its rules

Non-interactive end-to-end pipeline — auto-configure program.md (accept defaults), run judge+refine loop (up to 3 iterations), then run the campaign. Single command from goal to result.

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 lane for changes with no behavior to test-drive — prose edits, a version bump on an

Use this after a pull request has merged but your local checkout is still on the topic branch.

Prints the public command catalog straight from `COMMANDS.md` — the plugin's own single source

This is the single entry point for turning staged work into a commit — nothing in codeArbiter

The protocol for a rule conflict — not a skill route, an orchestrator-level halt. When two sources

An optional, on-demand drift audit for the bypass case: a merge, a direct push, or a manual edit

This is the populator for a project that already has code to read. Instead of interviewing you about

This is where an unexplained defect goes before anyone touches code. The investigation is

This is the populator for a project that has no code yet to read. Rather than guessing at

Proves the install is actually enforcing, rather than just present. codeArbiter's worst failure

This is the standard entry point for new work with a human in the loop at every step. A short

This is the entry point for a defect that already has a known cause, or one you can describe

This is how a repository opts into codeArbiter for the first time. It writes the root-level state

A bare-numbers governance glance — three metrics, each with a trend arrow against the prior

The sanctioned, logged escape hatch. A routine gate — a lint rule, a style check, a non-security

Explicit PR entry and a direct request to open a PR use the same branch-finishing owner.

A zero-onboarding, read-only dry-run of the reviewer fleet against whatever is currently

This is a Feature Forge preview command — the after-each-turn service ships **off** by default and

Compares architectural records with the scaffold and prior decisions using SMARTS.

This is the lane for moving or reshaping code without changing what it does — a rename, an extract,

Your car as a chat-room agent: Raspberry Pi 5 + dashcam + local AI. CodeWatch's sibling for the garage.

The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit log.

AI agent for Home Assistant — talk to your home, create automations in plain language, analyze cameras with face recognition, and get proactive anomaly alerts.…

A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first, cloud-ready for ma…

Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

Web & desktop (Electron) client for the OCTO open workplace — one React + TypeScript codebase shipping browser and PC surfaces, with first-class AI agent UX.

同花顺官方 A股金融数据服务，提供股票实时行情、历史行情、财务报表、指数、板块、涨停等数据，适用于 AI Agent、量化研究和应用开发，支持 API、MCP、CLI 和 Python。Official Tonghuashun (HiThink) A-share financial data service provi…

Open-source desktop SQL workspace for PostgreSQL, MySQL/MariaDB, SQLite and 15+ more databases like DuckDB, ClickHouse, Redis and Firestore. Built-in MCP server…

🤖 Local-assist BOSS Zhipin CLI for AI agents — search, welfare filtering, shortlist, JSON-envelope output; low-risk & compliant by default.

The local-first sidebar AI agent for ComfyUI — runs on your own Claude OR ChatGPT subscription (no API keys, no extra LLM costs). Drives your live graph: edits,…

Persistent memory for Claude Code — identity, context, and continuity across sessions

🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI…

A curated list of plugins, skills, MCP servers, patch/profile layers, orchestrators & UIs for DeepSeek Harness (DSH). Visualization · PPT · Coding · Agents · Lo…

World Memory Protocol.

Run your own organization of agents.

The most RAM efficient harness

AI-native, free, open-source alternative to Jira, Trello, ClickUp & Monday. Built for Scrum teams where humans and AI agents collaborate as equals — on the same…

Free open-source desktop app that scrapes JAV metadata and generates NFO + cover art for Jellyfin, Emby & Kodi. No Docker, no CLI — one-click install on Windows…

A cross-platform desktop app to manage Agent Skills in one place and sync them to multiple AI coding tools’ global skills directories — “Install once, sync ever…

天枢 (Tianshu) 是一个基于harness工程的终端编程智能体运行时（Tui X Gui），针对DeepSeek V4 做了前缀缓存工程优化（长会话实测稳态命中率 97–99%）和深度适配。它跳出了传统 AI 编程助手把大模型仅当成“工具”的局限，基于认知虚拟机 (CVM)、自感知层和信息素（Stigmergy…