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 plugin-portinggit 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/plugin-porting)<a href="https://agentmods.dev/skills/prism-shadow/penguin-harness/plugin-porting"><img src="https://agentmods.dev/badge/skills/prism-shadow/penguin-harness/plugin-porting/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/plugin-porting"><img src="https://agentmods.dev/badge/skills/prism-shadow/penguin-harness/plugin-porting.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 | $0.00074 | $0.04011 |
| Opus 5.5 | $0.00030 | $0.01604 |
| Sonnet 5.5 | $0.00015 | $0.00802 |
| Haiku 4.5 | $0.00007 | $0.00401 |
Grade B, and why
plugin-porting scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
cat "$WORK/mcp.json" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
SHA="$(curl -s --max-time 30 "https://api.github.com/repos/<owner>/<repo>/commits/<ref>" \ How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Porting
A PenguinHarness plugin is an npm package installed on the server and shared by every Project: the Plugins page shows its card, and anyone installs it on an Agent from there ("Manage installs"), which writes its skills and adds its MCP servers to that Agent's tools. This skill turns a plugin written for another tool into that package: fetch the source at a pinned commit, recognise its layout, build the package in a scratch folder by the rules below, review it, install it with the CLI, verify. To put a few skills into this Agent alone instead, use the skill-porting skill.
Before you start
- If the message only names this skill, ask for the source: a GitHub link (a repository, a folder, or a file inside the plugin's folder), a Codex or Claude Code plugin name, or a local folder.
- Installing puts the package on the whole server with the administrator's authority that the CLI's local token carries. Its skills become standing instructions for every Agent that installs it, so the review below is not optional.
- Work in a scratch folder (
mktemp -d). Never write into the server's data root by hand:penguin plugin installis the only way in. - Keep the conversation small: list trees with
find, read files withsed -n '1,120p', and nevercata whole tree.
The package format
<folder>/
├── package.json # the manifest (below)
├── README.md # optional; the plugin's detail dialog shows it
├── icon.svg # optional; the card's icon
└── skills/<name>/SKILL.md # one directory per skill, with the text files it refers to
{
"name": "@ported/<name>",
"version": "1.0.0",
"description": "English one-line description.",
"keywords": ["penguin-plugin", "ported"],
"author": "Upstream author",
"homepage": "https://…",
"repository": { "type": "git", "url": "https://github.com/<owner>/<repo>", "directory": "<path>" },
"license": "MIT",
"penguin": {
"title": "Display Name",
"short_description": "One short line for the card.",
"category": "software-development",
"icon": "icon.svg",
"quick_start": { "prompt": "A first request that shows the plugin working." },
"mcp_servers": [
{
"name": "cloudflare-api",
"config": {
"transport": "http",
"url": "https://mcp.cloudflare.com/mcp",
"headers": { "Authorization": "Bearer ${CLOUDFLARE_API_TOKEN}" },
"oauth": {}
},
"setup": [{ "key": "CLOUDFLARE_API_TOKEN", "label": "Cloudflare API token" }]
}
]
}
}
What ships with it
3 files 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.
- 6d ago First seen · 152 lines · 74 tokens per session scan B 61c441f0647a
plugin-porting is a skill published in the GitHub repository Prism-Shadow/penguin-harness (2,753 stars, last pushed today), licensed Apache-2.0. It adds 74 tokens to every session and 4,011 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads mcp configuration, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-11.
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.