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-supportgit 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-support)<a href="https://agentmods.dev/skills/prism-shadow/penguin-harness/penguin-support"><img src="https://agentmods.dev/badge/skills/prism-shadow/penguin-harness/penguin-support/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-support"><img src="https://agentmods.dev/badge/skills/prism-shadow/penguin-harness/penguin-support.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 | $0.00042 | $0.01286 |
| Opus 5.5 | $0.00017 | $0.00514 |
| Sonnet 5.5 | $0.00008 | $0.00257 |
| Haiku 4.5 | $0.00004 | $0.00129 |
Grade A, and why
penguin-support scanned grade A with 0 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 2d ago.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PenguinHarness support
Before you start
If the user only names this Skill without a question, ask what they need help with. A ticket or follow-up already contains the question: read the sources and answer it directly.
Answer the question
Answer questions about PenguinHarness using its official documentation at https://penguin.ooo/docs/ and source code at https://github.com/Prism-Shadow/penguin-harness. Answer in the user's language. Use the current product term Agent Workbench / 工作台 in answers and navigation steps. Older sources may call it Workflow; keep that spelling in code paths and historical quotations, but do not tell a user to look for a “Workflow” tab in the current UI. Explain the old name only when the version difference matters to their question.
For each question, read relevant sources before answering. Start with the matching document
in packages/docs/content/: quickstart for installation, models for model setup, agents
for Agent creation, skills for plugins, and chat for using conversations. The docs website
renders in JavaScript; if a fetch returns a shell, read the repository's Markdown instead.
Keep one reusable reference checkout at <App Data Dir>/agents/<Agent ID>/scratchpad/penguin-harness-reference,
not inside the per-session scratchpad. Check whether it exists before cloning. On first use:
git clone --depth 1 --filter=blob:none --sparse https://github.com/Prism-Shadow/penguin-harness <reference>
git -C <reference> sparse-checkout set packages/docs/content packages/core/src packages/server/src packages/web/src packages/cli/src plugins/agent-development/skills
git -C <reference> rev-parse HEAD
Reuse it across tickets. Fetch updates when the question depends on current behavior; never
reset a checkout containing user changes. If git is unavailable, fetch specific files from
https://raw.githubusercontent.com/Prism-Shadow/penguin-harness/main/.
Navigation and ownership questions
For “where do I open the workbench?” or “which Agent owns it?”, once the checkout is ready, read the Plugin Skill's introduction and the chat page's tab placement in one command:
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.
- 2d ago First seen · 90 lines · 42 tokens per session scan A 3b5623b5e948
penguin-support is a skill published in the GitHub repository Prism-Shadow/penguin-harness (2,753 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 1,286 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-15.
Other skills, from other repositories
agentscope-java
Expert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or…
apply-patch
Apply multi-file or tricky edits atomically with git apply instead of many fragile editfile calls. Use when changing several files at once or when editfile fails to match.
git-checkpoint
Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.
pptagent
Create and revise editable PowerPoint presentations from a brief using HTML slide sources, rendering, and visual review. Use when the requested deliverable is a PPTX deck. The host authors the slides; text-only hosts can use an external visual reviewer.
agentfield-use
Whenever you have a discrete task to perform — one the user delegated, or one that arose inside your own work — check FIRST whether an installed AgentField agent covers it, and offload to it by default when one does. Coverage, not task size, is the test: even a small job goes to a covering agent. The check is cheap …
browser-workflow-skill-builder
Create robust browser automation skills for sites like LinkedIn, X/Twitter, YouTube, Stripe, or other logged-in web apps by saving page context, analyzing HTML/CSS, writing skill-local JS extract/verify scripts, and using CSS selector actions with screenshot verification.