Claude Fable 5.1 prompting guide as Claude Code skills (KO/EN/ZH). Output quality goes up on Opus 5 and Sonnet 5 too.

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

Run Linux-style commands on Windows via deterministic bash→PowerShell translation. No VM, no WSL. MCP server + CLI built for AI agents (Claude Code, Codex, OpenCode...). GNU-style output, bash-style errors, UTF-8/GBK handled.

Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm.

Markdown and HTML renderer for Svelte 5 — built for rendering streaming AI agent output from Claude Code, ChatGPT, and agentic workflows. XSS-safe defaults, streaming-aware sanitization, token caching, TypeScript types, and Svelte 5 runes.

Oh My Pi bash runtime ported as a deepseek-harness tool plugin: persistent shell session, output minimizer, managed background jobs, command interception

AI 编译纯文本小说工作台 for the dsh web GUI: import a novel outline (docx/text), plan volumes & chapters with LLM, generate chapter by chapter (3000-4000 chars each), auto AI review & book audit, and export the full book as Markdown/TXT into your chosen output fold

VCP visual-synesthesia protocol plugin for DeepSeek Harness: render agent HTML output as real UI (cards / KaTeX math / Mermaid diagrams / built-in calligraphy fonts / zero-JS interactions), plug-and-play on any DSH environment

Claude Code experience for the pi coding agent: reads your .claude config (rules, commands, skills, hooks, output styles, MCP servers, agents) and adds todo, checkpoints, memory, web, subagents, and goals

x64dbg-MCP Server is a native MCP (Model Context Protocol) plugin for x64dbg that exposes the debugger's full functionality over HTTP. Connect any MCP-compatible AI assistant and control x64dbg programmatically: set breakpoints, step through code, read memory, dump registers, and more. Built with Zig — zero dependencies, single-binary output, cros

Opt-in, token-authenticated MCP server built into the Shelly Android terminal app: read-only tools for terminal output, git status, registered agents and repos on the phone, plus off-by-default run_command and write_file that need an on-device approval tap per call.

Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.

Enables coding agents to record product demos, changelog GIFs, help-center guides, and bug repros by driving a signed-in browser or Mac window, then rendering branded MP4 and GIF outputs with delivery checks.

Enables coding agents to navigate and verify a contract-backed semantic graph of TypeScript backends, inspect change impact, run checks, explain failures, and draft human-reviewable contracts through bounded MCP tools and matching JSON CLI output.

Keeps large tool outputs out of an agent's context window by spilling them to disk and handing back a short pointer instead. Lets the agent pull only what it needs — exact numbered line ranges read directly from disk, or verbatim relevant lines returned by a small model answering a question about the stored output, plus tools to open, list, and close documents.

Enables an LLM to orchestrate multiple downstream MCP tools inside one isolated sandbox in a single turn, filtering intermediate results in memory and returning only the final output to cut context tokens.

Enables Codex to delegate subtasks to concurrent background coding agents that can each run on any model provider supported by Pi, such as DeepSeek, Anthropic, Gemini, OpenRouter, or local models. Exposes MCP tools for listing models, spawning and waiting on agents, sending follow-ups, and aborting, backed by a live local web panel showing status, token usage, and streaming output.

Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client. Rust, zero LLM calls.

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 AI agents and assistants to inspect live system telemetry, check TCP port connectivity, audit environment variables for leaked secrets, analyze and summarize log files, and list Docker containers — all with token-efficient, compressed output.

Exposes MCP tools that compute longevity and metabolic metrics (autophagy index, GKI, MAGE), cardio-renal biomarkers (BUN/creatinine ratio, cardiac output and TPR, nocturnal BP dipping), chronobiology estimates (DLMO, melanopic lux, caffeine clearance), plus neuro-recovery and biomechanics scores. Runs as a zero-dependency Python JSON-RPC 2.0 stdio server so any MCP-compatible client can query these physiological domain calculators.

Enables AI agents to read WeChat Official Account articles by fetching mp.weixin.qq.com links from the user's own machine and network and converting them into clean Markdown with title, account, author, and publish-time metadata. Provides both single-article and batch-reading tools (up to 20 URLs) with optional image handling, character limits, and JSON output.

A Claude Code plugin for managing requirement documents, tracking changes, and outputting specs — enabling downstream tools to generate code based on high-quality specs and complete E2E testing.