penguin-harness: Skill for Claude Code

.agents/skills/penguin-harness-manual-test/SKILL.md

penguin-harness-manual-test is a skill for Claude Code, Codex from Prism-Shadow/penguin-harness. It costs 77 tokens per session (1,280 once invoked), scanned A, original, Apache-2.0.

A manual-testing guide for PenguinHarness, covering its web app, desktop app, landing page, and documentation site. It explains how to start each one, which local address to open, and where test data is stored.

In plain words
What is it for?
Use it to launch PenguinHarness locally, click through changes, take screenshots, and reproduce reported problems across the four interfaces.
Why use it?
It prevents confusion between development data and data used by the installed app, and helps diagnose setups that appear broken. It also shows how to avoid port conflicts and verify that each entry point is working.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Prism-Shadow/penguin-harness's own configuration. It tells Claude Code and Codex how to work on penguin-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything penguin-harness configures →

About the project

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.

Prism-Shadow/penguin-harness · 2,105 stars · on GitHub · penguin.ooo

Reuse

Borrowing it

Nothing to install: this file belongs to Prism-Shadow/penguin-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Prism-Shadow/penguin-harness/main/.agents/skills/penguin-harness-manual-test/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Prism-Shadow/penguin-harness

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for penguin-harness-manual-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/prism-shadow/penguin-harness/penguin-harness-manual-test/github.svg)](https://agentmods.dev/skills/prism-shadow/penguin-harness/penguin-harness-manual-test)
Your own site
<a href="https://agentmods.dev/skills/prism-shadow/penguin-harness/penguin-harness-manual-test"><img src="https://agentmods.dev/badge/skills/prism-shadow/penguin-harness/penguin-harness-manual-test/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.

agentmods 80×15 button for penguin-harness-manual-test

Your own site · 80×15
<a href="https://agentmods.dev/skills/prism-shadow/penguin-harness/penguin-harness-manual-test"><img src="https://agentmods.dev/badge/skills/prism-shadow/penguin-harness/penguin-harness-manual-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,280 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00077 $0.01280
Opus 5 $0.00039 $0.00640
Sonnet 5 $0.00015 $0.00256
Haiku 4.5 $0.00008 $0.00128

Measured 3d ago against content hash 59fa431d57c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

penguin-harness-manual-test scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**`curl` returns 502 but the server is fine.** A shell `http_proxy` routes loopback through the
.agents/skills/penguin-harness-manual-test/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Standing PenguinHarness up to test by hand

Node >= 24. dev:* runs dev-prebuild.mjs first (keeps pnpm install current, prebuilds workspace deps); pnpm desktop runs a full pnpm -r build, so it is slow to start.

Entry points

Command Open Data root
pnpm dev http://localhost:7365 ~/.penguin/dev-data
pnpm desktop its own window ~/.penguin/dev-data
pnpm dev:landing http://localhost:7366 none (static)
pnpm dev:docs http://localhost:7367 none (static)

Other fixed ports (packages/core/src/internal/ports.ts): 7364 installed server, 7368 dev backend, 7369 pnpm penguin web (data root ~/.penguin/dev-data-cli — its own, so it can serve while an Agent it hosts runs pnpm dev; the lock is per root). On a shared box, ss -tln before assuming one is free; PORT= inline moves it.

The user's installed app, server and CLI all use ~/.penguin/data — their real Agents, Sessions and keys. Never point a dev run there. Both surfaces print the root they took (Data root: …, [shell] dev instance … on data root …); read it rather than assume.

Four ways a working setup looks broken

7368 shows a stale app. The dev backend also serves packages/web/dist — the last pnpm -r build, not what Vite is serving. Screenshot 7365, never 7368.

curl returns 502 but the server is fine. A shell http_proxy routes loopback through the proxy. Use curl --noproxy '*'. Browsers and the server itself are unaffected.

/api on 127.0.0.1 returns 401. That address is reserved as the Workspace-preview host. Use localhost.

The server exits 3 saying the data root is in use. Another instance — usually the user's own desktop app — holds <root>/server.lock. The lock is per root, not per port, so PORT= will not get past it. Use a different root; do not kill their process.

One instance at a time

Only one local dev instance runs at a time, counting every agent's. A separate root gets you past the lock but not past the browser: cookies and the admin claim are shared across instances, so bringing a second one up corrupts the first's session state. Stop the previous PR's instance before starting the next.

Read the full file on GitHub · 97 lines

Changes

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.

  1. 3d ago Changed · +24 lines 59fa431d57c3
  2. 13d ago First seen · 73 lines · 77 tokens per session scan A 08853b9c1c49

Subscribe to this mod's changes

penguin-harness-manual-test is a skill published in the GitHub repository Prism-Shadow/penguin-harness (2,105 stars, last pushed today), licensed Apache-2.0. It adds 77 tokens to every session and 1,280 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.