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-configgit 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-config)<a href="https://agentmods.dev/skills/prism-shadow/penguin-harness/penguin-config"><img src="https://agentmods.dev/badge/skills/prism-shadow/penguin-harness/penguin-config/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-config"><img src="https://agentmods.dev/badge/skills/prism-shadow/penguin-harness/penguin-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 12 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
- medium Rogue Agent · line 21 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00022 | $0.01368 |
| Opus 5 | $0.00011 | $0.00684 |
| Sonnet 5 | $0.00004 | $0.00274 |
| Haiku 4.5 | $0.00002 | $0.00137 |
Grade B, and why
penguin-config scanned grade B 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 5d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
If the user's message only invokes this skill (e.g. "use penguin-cli skill") without a concrete request, ask the user what they want to configure. Do not run any command until the goal is clear. How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Penguin Config (CLI)
The penguin CLI manages model credentials, default models and per-agent vault secrets. Its primary job is model configuration: penguin config model add registers a model and penguin config model list shows the models currently available. Configuration goes through the CLI only — never read or hand-edit the underlying hidden files.
Before you start
If the user's message only invokes this skill (e.g. "use penguin-cli skill") without a concrete request, ask the user what they want to configure. Do not run any command until the goal is clear.
Models
Add or update a model (upsert by the (provider, model_id) pair; re-run with more options to amend an entry):
penguin config model add --provider <group> --model-id <upstream_id> [--api-key <key>] [--base-url <url>] \
[--client-type <type>] [--context-window <n>] [--max-tokens <n>] [--vision | --no-vision] \
[--price-cache-read <n>] [--price-cache-write <n>] [--price-output <n>] \
[--project-id <id>] [--root <dir>] [--set-default]
- A model is identified by the
(provider, model_id)pair, so--providerand--model-idare both required — the group is never inferred from the model id, because gateways resell vendor models under their upstream ids and a wrong guess would send the key to another vendor's endpoint.--model-idtakes the provider's upstream model id (what the API expects) and is persisted as the entry's request id, so it reaches the API unchanged;--providernames the group (deepseek,openai,anthropic,google,openrouter,siliconflow, … —customfor any other endpoint). - For any OpenAI chat-completion compatible endpoint use
--client-type openai --base-url <endpoint>; omit--client-typeto auto-route by model id. - Prices are USD per million tokens (cache read / cache write / output).
--vision/--no-visionmark whether the model accepts images; omitting both keeps the current value (default is vision-capable).--max-tokens <n>pins a per-model output cap (positive integer), overriding the Agent'smodel.max_tokens; omit to inherit. Lower it for small-context models — the per-Agent default (32000) cannot fit into e.g. a 32k context window together with any prompt.- All
penguin config model ...andpenguin config vault ...commands accept--root <dir>to target another data root (defaultPENGUIN_HOME, then~/.penguin/data). Two configuration targets — treat the difference as a hard rule:- Penguin's own model (self-configuration: the model Penguin itself runs on): the default root without
--rootis correct. - An AI app you are building:
--rootmust point at the app's own data directory inside the project (e.g.--root ./penguin_data, the same path the app givescreateAgent({ root })) unless the user explicitly chose another location — never write an app's models or keys into the global~/.penguin/data, which belongs to the person running Penguin, not to the app. - While developing an app, review regularly:
penguin config model list --root <app root>should show the app's entries, and the global list (no--root) should stay clean.
- Penguin's own model (self-configuration: the model Penguin itself runs on): the default root without
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.
- 5d ago First seen · 72 lines · 22 tokens per session scan B 52199f3c9e8f
penguin-config is a skill published in the GitHub repository Prism-Shadow/penguin-harness (2,048 stars, last pushed yesterday), licensed Apache-2.0. It adds 22 tokens to every session and 1,368 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
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.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
cli-skill-design
Design a co CLI surface and its SKILL.md together so an agent can drive it without guessing — every command ends by naming the next one, --help lists everything, and every failure says what to run instead. Use when adding a new CLI command group, writing or rewriting a SKILL.md for one, or auditing an existing one.
building-ui
Complete guide for building beautiful apps with Expo Router. Covers fundamentals, styling, components, navigation, animations, patterns, and native tabs.