🐧 Harness for RSI. Let AI Build AI. Multi-Agent Auto-Dev Platform. Everything is Transparent.
PenguinHarness is a local-first platform in which multiple AI agents create, evaluate, optimize, and deploy agent applications. It is for people building AI software who want agents to generate applications and improve their own behavior through skills.
Skill Claude CodeCodex
Use when developing PenguinHarness itself — changing packages/{core,server,web,cli,desktop,landing,docs,skills}, the built-in model catalog, the installers or the release workflow; writing or auditing changelog entries; writing a blog post or capturing release screenshots; deciding what to do about data already on…
Skill Claude CodeCodex
Use when changing the PenguinHarness Web App (packages/web) — adding or restyling any UI, picking a status colour, adding an icon, laying out a row or a form field, writing user-facing copy, or building a popup. Covers the semantic tone tokens, the icon size/stroke/gap scale, the semantic-versus-formatting rule for…
Skill Claude CodeCodex
Use when standing PenguinHarness up to try a change by hand — launching the Web App, the desktop shell, the landing page or the docs site to click through it, screenshot it, or reproduce a report. Covers the four dev entry points and their ports, which data root each writes to, and the four ways a healthy setup looks…
Skill Claude CodeCodex
Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.
Skill Claude CodeCodex
Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.
Skill Claude CodeCodex
Improve an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.
Skill Claude CodeCodex
Call model APIs through @prismshadow/agenthub — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.
Skill Claude CodeCodex
Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline.
Skill Claude CodeCodex
Create and edit Bento presentations — self-contained .bento.html decks whose document is JSON. Use whenever the user wants a slide deck or presentation: from scratch, from source material, or by improving an existing file.
Skill Claude CodeCodex
Complete data-analysis tasks with bounded inspection, correct data semantics, native artifact handling, complete delivery, and risk-based verification.
Skill Claude CodeCodex
Search the web and scrape pages into clean markdown with the Firecrawl API — query-based discovery, single-URL extraction including public PDFs, driven by curl with a vault-stored API key.
Skill Claude CodeCodex
Rewrite or edit prose in any language so it reads like edited human writing in the register of books, newspapers and encyclopedias rather than default AI output. A small drafting core — vary every pattern, build density from anchored facts in whole grammar, cap the quotables, put a real writer with real material…
Skill Claude CodeCodex
Fine-tune LLMs with LlamaFactory — register datasets, train via YAML configs, merge LoRA adapters and serve the result.
Skill Claude CodeCodex
Deploy and serve local models with Ollama — pull and run them, then expose the OpenAI-compatible endpoint to apps and agents.
Skill Claude CodeCodex
Manage model API keys, default models and per-agent vault secrets with the penguin CLI.
Skill Claude CodeCodex
Drive PenguinHarness itself from a shell — list and create agents and sessions, send and steer messages mid-flight, and query costs and scheduled tasks via the penguin CLI over the local server.
Skill Claude CodeCodex
Use whenever the user wants to build an agent application — their own program with an embedded agent, such as an AI app, an agentic app or a RAG app. This is writing application code on the Penguin Harness SDK, not configuring an Agent State inside PenguinHarness. Covers self-contained projects, the createSession/run…
Skill Claude CodeCodex
Run Claude Code on a remote host over SSH — a persistent expect-driven login session, headless claude -p with the stdin fix, the interactive TUI inside a remote tmux driven by send-keys/capture-pane (one keystroke at a time, capture-verified; relayed user messages go through verbatim), and multi-turn continuity via…
Skill Claude CodeCodex
Install skills from external ecosystems into this agent's agentstate/skills/ — resolve Claude Code plugin marketplaces, the Codex plugin repo, skills.sh registry names, GitHub repos, or local folders to their skill directories, review every file, and normalize SKILL.md frontmatter to the Penguin format.
Skill Claude CodeCodex
Complete software-engineering tasks — investigate and review code, implement bug fixes, features and refactors with minimal scope, validate changes, and report verified outcomes.
Skill Claude CodeCodex
Deploy and serve LLMs with vLLM behind an OpenAI-compatible endpoint, with tool calling enabled for agent workloads.
Skill Claude CodeCodex
Penguin visual language for generated web pages and app UIs — GitHub-style simplicity with a single blue accent, light and pure-black dark themes, design tokens, component and chat-interface recipes, plus an opt-in warm paper editorial theme.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: