DSH's officially top-recommended TUI plugin — high performance, low overhead, cute pixel whale, smooth mouse interaction. One-command install via npm. / DSH 官方首推的 TUI 插件，高性能低占用，可爱像素鲸鱼，流畅鼠标交互，npm 一键安装

Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP integration. Plan features with parallel research agents, execute with automatic verification, review with 4-agent parallel audits, and capture learnings as reusable knowledge.

Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "imp

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.

Enables AI coding agents to inspect GitHub repositories and shell commands for download-and-execute payloads, obfuscation, typosquatted dependencies, autorun hooks, and fake-star signals before following or running them.

Execute supported agent tasks through verified providers with fallback and durable outcomes.

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs

Public adapters and discovery catalog for Triptych OS (Agent OS): agent frameworks, MCP/A2A/x402 protocols, workflows, wallets, SDKs, and examples for execute-first routing, governed handoffs, and receipt-aware agent commerce.

Automatic strong/cheap model-tier routing for DeepSeek Harness: intent-gated tier landing on the agent/request waterfall, plan-mode handoff (strong plans, cheap implements), deterministic high-risk guards on tools/pre-execute, failure escalation with TTL

Public adapters and discovery catalog for Triptych OS (Agent OS): agent frameworks, MCP/A2A/x402 protocols, workflows, wallets, SDKs, and examples for execute-first routing, governed handoffs, and receipt-aware agent commerce.

Turn Claude Code into a plan-execute-validate loop with parallel work, intelligent retry, and memory

Human-agent interface for projects: you prioritize and decide, your AI agents execute. Over MCP.

Distributed agent coordination platform where agents live, connect, coordinate, execute, and evolve together.

Enables agents to capture real browser interactions over CDP, compile them into deterministic replay scripts with parameterized inputs and stored secrets, and execute those workflows with real input events — no page re-reading or LLM in the replay loop. Also emits portable Agent Skills from recorded workflows.

Enables agents to reach pump.fun's full API surface — official developer routes, bonding-curve reads, Solana RPC, and unsigned trade building — by writing JavaScript against one merged OpenAPI document, using just two tools (search and execute). Model-authored code runs in a network-less sandbox, so multi-step questions resolve in a single round trip while credentials stay on the host Worker.

Exposes the Jupyter notebooks open in VS Code to MCP-compatible AI agents, letting them edit cells in the open editor and execute them in the live kernel without file conflicts. Agents can make partial edits, track stale cells, inspect variables, and manage kernels while preserving the user's interpreter choices and unsaved work.

Enables agents to execute shell commands and upload/download files on remote Linux hosts over SSH/SFTP with just two tools, returning structured, verifiable results such as exit codes, separated stdout/stderr, timeout and truncation flags, and the current working directory. Supports connection reuse, host alias resolution, host-key verification, and cross-call session state so multi-step work needs fewer calls.

Enables AI agents to execute commands and read files or directories on pre-registered, fingerprint-verified SSH hosts by alias or IP, while keeping encrypted passwords local and inaccessible to the agent.

All-in-one workflow plugin—loops, swarms, and teams on Claude Code's Task System. All enforce exit criteria—swarm is faster with parallel queue execution, teams add contract-first coordination. Plan your way, execute your way. Optional: Beads for persistent memory, Ralph TUI for dashboard.

ChannelTerm is an open-source MCP server that enables humans and AI agents to share live serial and SSH terminal sessions for embedded systems development and debugging. It allows AI agents to read device output, execute commands, assist with GDB debugging, and transfer files while keeping developers in control.

Enables developers to register custom tool-calling functions, execute path-safe file operations within an isolated workspace, and keep in-memory memory and audit state for AI agent workflows.

Exposes a governed dbt MetricFlow semantic layer to AI agents through three tools — list metrics, list dimensions and query metrics — so questions about federal contract spend are answered from defined metrics rather than raw tables. Guardrails reject undefined metrics, raw columns, SQL in filters and bulk exports, and no tool can execute SQL.

Enables agents to run SweetScape 010 Editor Binary Templates and Scripts headlessly against local files. It provides tools to locate the editor binary, execute templates or scripts, and use controlled exit behavior for compile and runtime failures.

Enables AI agents to search and invoke 1,939 Atlassian automation tools across Jira, Confluence, Bitbucket, Admin, Assets, and more, with cached reads and JSON-RPC over stdio. It helps agents find tools without calling Atlassian and execute operations while reducing rate-limit pressure.