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.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Prism-Shadow/penguin-harness --skill penguin-sdkgit clone --depth 1 https://github.com/Prism-Shadow/penguin-harnessWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/prism-shadow/penguin-harness/penguin-sdk)<a href="https://agentmods.dev/skills/prism-shadow/penguin-harness/penguin-sdk"><img src="https://agentmods.dev/badge/skills/prism-shadow/penguin-harness/penguin-sdk/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/prism-shadow/penguin-harness/penguin-sdk"><img src="https://agentmods.dev/badge/skills/prism-shadow/penguin-harness/penguin-sdk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00224 | $0.08875 |
| Opus 5.5 | $0.00090 | $0.03550 |
| Sonnet 5.5 | $0.00045 | $0.01775 |
| Haiku 4.5 | $0.00022 | $0.00887 |
Grade D, and why
penguin-sdk scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
`curl -N -sS -X POST localhost:4630/api/ask -H 'content-type: application/json' -d '{"question":"<something the corpus answers>"}'` — expect streamed `data:` deltas ending in a `sources` event that carries `source`, `url Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
find corpus -type f ! -regex '.*\.\(md\|mdx\|txt\|html?\)$' -delete && rm -rf corpus/*/.git Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: Use to build a standalone external program with an agent in it, or connect an external program to a Penguin agent. For an app inside PenguinHarness with its own Agent and workbench tab, use agent-initializat Copies of this mod
1 near-identical copy found in the catalogue:
- ux-audit — 86% identical, 452 lines differ
How it starts
The opening of the file, as written. The whole thing — 434 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Penguin Harness SDK and Agent API
This skill builds programs that use a Penguin agent. A program reaches one in either of two ways, embedded with the SDK or through the Penguin server's Agent API, and the user picks which. Workbenches — pages and server code an Agent keeps inside PenguinHarness — are a third thing, and the penguin-plugin skill's.
To have an agent perform a task for you, use the run_subagent tool: both ways are for programs, not for handing off your own work.
Two ways to reach an agent
The SDK: @prismshadow/penguin-core, embedded in the program.
- What it is. The agent loop as a TypeScript library. The program creates its own Agent from a data directory inside the project and runs its Sessions in-process. No Penguin server is involved, at build time or at run time.
- What you get. The basic agent loop: the Agent State files (
AGENTS.md, Skills, tools), the streamed AMSP records and anapprovecallback for every tool call, in a self-contained folder that runs wherever Node 24 does, on the program's own model key. - What you don't get. No server-managed Sessions (the program keeps its own), no visibility in the Web App, no approvals UI (the program answers in code) and no cost center. The embedded agent belongs to the program: changes to an Agent inside PenguinHarness never reach it.
- Choose it when the program must stand alone: shipped to other machines or people, run where no Penguin server is, or with the agent built into the product.
The API: Penguin's Agent API, over AMSP.
- What it is. The program calls an Agent that lives in PenguinHarness, over HTTP. The Penguin server runs each turn and streams it back over AMSP as the Session's records, the ones its Trace holds, and the program continues a conversation by its Session id. TypeScript uses the
@prismshadow/amspclient (AgentClient); any other language, or curl, speaks HTTP and SSE directly. - What you get. The Agent as PenguinHarness runs it: its
AGENTS.md, Skills and memory, on the Project's models and credentials, so the program holds no model key. The server keeps the conversations as archived chats (Settings › Archived chats in the Web App), where a person finds one and unarchives it to read it and answer its approvals, and their usage lands in the cost center. - What it requires. A running Penguin server that the program can reach over the network; API access turned on for that Agent by the Project's owner, on the Agent's API tab; and a key created there, shown once. You never turn these on yourself (see The API path).
- Choose it when the Agent already exists in PenguinHarness or should be managed there, people need to see its conversations or costs, or the program is not written in TypeScript.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed 4ee1ae8ec1e7
- 5d ago Changed 022080b484e6
- 10d ago Changed · +7 tokens per session 1ab5687b3964
- 11d ago Changed a37e5027dc8d
- 12d ago Changed · -104 lines · +217 tokens per session b3fc2f9b8d21
- 14d ago Changed · +1 lines 4063f020abd1
- 15d ago Changed · +73 lines 7ae122edfeda
- 22d ago Changed fa1820146821
- 24d ago Changed ad9fce89d24e
- 1mo ago First seen · 464 lines · 0 tokens per session scan D 7e3efa0f866a
penguin-sdk is a skill published in the GitHub repository Prism-Shadow/penguin-harness (2,944 stars, last pushed today), licensed Apache-2.0. It adds 224 tokens to every session and 8,875 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it D with 3 findings (sends data to an external url, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Vector Databases
Guides retrieval-store design, indexing, and query behavior for embedding-backed systems without confusing storage with application truth.
memory-rag-poisoning-detection
Detect persistent-memory poisoning and RAG/knowledge-base contamination via dialogue testing. Use when the agent has long-term memory, a user/preference store, or writes to a retrievable knowledge base.
molecular-rag
Retrieve structurally similar compounds with known properties from ChEMBL/ZINC to ground predictions and inform optimization. Based on MolRAG (Xian 2025, ACL).
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.
neuron-rag
Implement RAG (Retrieval-Augmented Generation) with Neuron AI including vector stores, embeddings providers, document loaders, retrieval strategies, and metadata filtering. Use this skill whenever the user mentions RAG, retrieval, vector search, document retrieval, semantic search, knowledge bases, chat with…
awesome-chatgpt
Search this repository's awesome-ChatGPT-repositories list for open-source ChatGPT and LLM projects such as RAG frameworks, agents, chatbots, CLIs, prompts, and browser extensions. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, or AI development; not for editing or adding list…