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 benchmark-designgit 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/benchmark-design)<a href="https://agentmods.dev/skills/prism-shadow/penguin-harness/benchmark-design"><img src="https://agentmods.dev/badge/skills/prism-shadow/penguin-harness/benchmark-design/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/benchmark-design"><img src="https://agentmods.dev/badge/skills/prism-shadow/penguin-harness/benchmark-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 14 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00029 | $0.04762 |
| Opus 5.5 | $0.00012 | $0.01905 |
| Sonnet 5.5 | $0.00006 | $0.00952 |
| Haiku 4.5 | $0.00003 | $0.00476 |
Grade A, and why
benchmark-design 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 9d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Benchmark Design
Build a multi-Case Benchmark for one Test Agent, calibrate its difficulty with one Run per Case, and record the selected frozen Pilot as the Formal Baseline.
This Skill changes the Benchmark, never the Test Agent. It does not run or score the Test Agent. Delegate every evaluation with run_subagent, and tell each worker to use agent-evaluation. Stop after the Baseline; do not begin optimization.
A Benchmark whose Cases are run through Harbor (their statements say so; the built-in PenguinHarness Benchmarks) is a frozen upstream task set that ships with PenguinHarness: never create, refine, recalibrate or re-baseline one.
To import an existing Benchmark, follow Importing a package in reference/package.md: fetch the selected package, read its files, and copy the manifest and cases directly into the Project's benchmarks/<id>/ with an empty scoreboard. Preserve its version, record the source, and ask before replacing an existing directory. Importing does not run the design, calibration or evaluation workflow below.
Before you start
An import request is answered by reference/package.md alone: do not ask for a target capability, a desired baseline score or a Pilot limit, which a package does not have. If the request does not identify a Test Agent, target capability, desired baseline score, and Pilot iteration limit, ask for the missing inputs. When they are already supplied, proceed without asking the user to restate them. Treat the current Agent as the Builder. A user-specified evaluation (provider, model_id) takes priority; otherwise inherit the current Builder Session's complete Provider and Model ID from the Environment. Never use a Project default as an implicit evaluation runtime.
Workflow
- A Pilot is a one-Run-per-Case evaluation used to improve the Benchmark. Unselected Pilot results never enter the Scoreboard; the selected result becomes the Formal Baseline after Freeze.
- Freeze means the Benchmark revision and evaluation settings stop changing.
- A Formal Baseline is the accepted result of the selected complete valid Pilot revision, recorded after that exact revision is frozen on one unchanged Agent State version.
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.
- 9d ago Changed 7c9b383c36f6
- 10d ago Changed · +7 tokens per session 0d23190de551
- 12d ago Changed · +3 lines 6316a0d9daf9
- 13d ago Changed · +2 lines e880e03b2733
- 1mo ago Changed · +5 lines d87e769dd2a6
- 1mo ago Changed · -4 lines d267f0d7472e
- 1mo ago First seen · 206 lines · 22 tokens per session scan A a4328df26ea1
benchmark-design is a skill published in the GitHub repository Prism-Shadow/penguin-harness (2,916 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 4,762 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
verify-changes
Verify code changes by running the project's typecheck, build, lint, and targeted tests, then fix and re-run until clean. Use after editing any source file.
Skill: Verify skill
Skill for opinionated verification workflow for validating code changes.
install-verification
Use when verifying that a generated agent package can be installed, discovered by runtimes, and checked without private dependencies.
local-test
Build, run, and test IronClaw locally using Docker containers and Chrome MCP browser automation.
qa-review
QA review for code changes — test coverage analysis, edge case identification, test plan generation, regression detection, test health tracking over time.
review
Review code changes, pull requests, patches, or a scoped code area for actionable correctness, security, compatibility, and test risks with file and line evidence. Use for review or audit requests; do not use for general proofreading, feature implementation, or debugging a reported failure when the user wants a fix.