DeepSeek Harness fast mode: fewer round trips at the same thinking effort. Adaptive parallel tool fan-out, output discipline that never trims the answer, a cancellable stall guard, and one off-by-default switch (lazy) that steps a stalled turn one rung do

Given a change_brief YAML (output from diff-intake), generates an exhaustive list of candidate analytics events to instrument. Takes the perspective of an engineer with a PM mindset — surfaces everything worth considering so a PM can decide what actually matters. Use this as step 2 of the analytics

Given event_candidates YAML (output from discover-event-surfaces), generates a concrete instrumentation plan for priority-3 (critical) events. Acts as a Software Architect: discovers existing analytics patterns in the codebase, reads the hinted files to determine what variables are in scope, designs

Gives DeepSeek Harness three automatic Jev judgments — prune oversized tool output, screen fetched pages for injected instructions, suggest which skill to use — plus the jev_ask and jev_gate tools, a persistent judgment ledger, and a /jev-status diagnosis

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

Review a pull request diff and write structured feedback to review.json for the workflow to publish. Use when reviewing a checked-out PR from local artifacts like pr_diff.txt and pr_description.txt and producing machine-readable review output instead of posting directly to GitHub.

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

Context compression plugin for Claude Code. Automatically trims large tool output—JSON, YAML, stack traces, and logs—before it enters the context window.

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.

Generate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Nano Banana 2's strengths (rapid iteration, in-image typogra

Edit images with Flux 1 Kontext Pro (Black Forest Labs' precise local image-edit model) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Flux Kontext's strengths (single-reference precise loca

Edit images with OpenAI GPT Image 2 (the `/edit` endpoint of ChatGPT Images 2.0) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents GPT Image Edit's strengths (preservation language, multilingua

Generate images with Flux 2 Klein (Black Forest Labs' distilled fast variant of Flux 2) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Flux 2 Klein's strengths (sub-second latency, multi-ref

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.

Generate, inpaint, and outpaint music with ACE Step on RunComfy via the `runcomfy` CLI. ACE Step is StepFun-AI's open-weights music foundation model — tag-driven composition (genre, mood, instruments), multilingual lyrics with section markers, 5 s to 4 min stereo output, $0.0002–0.0003 per second (≈

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 MCP clients to create and control persistent, PTY-backed terminal sessions on macOS: launch commands and interactive programs, read output incrementally via byte cursors, send keystrokes, wait on conditions, and detect running/awaiting-input/exited states. Sessions run inside a Seatbelt sandbox with command policies, human approvals, secret redaction, and hash-chained audit logging.