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.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.04004 |
| Opus 5 | $0.00011 | $0.02002 |
| Sonnet 5 | $0.00004 | $0.00801 |
| Haiku 4.5 | $0.00002 | $0.00400 |
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 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.
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 — 202 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.
Before you start
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.
Follow this order:
- Validate the Test Agent, target capability, resolved evaluation Runtime, and evaluation access.
- Write a Capability Contract that defines the observable process to measure, common weaker behavior, and the general Agent State improvement the Benchmark should train.
- Plan the complete initial Case set and point allocation. For each Case, privately state the intended behavior, a plausible shortcut for a strong Test Agent, and how the Case distinguishes them. Write and leak-check the complete initial Benchmark.
- Complete one valid evaluation for every planned Case. Together these results form Pilot iteration 1; finish this complete set before refining any Case.
- For later Pilot iterations, use scores and Traces to reconstruct how the Test Agent solved each Case. A single iteration may refine multiple Cases or difficulty dimensions; rerun every affected Case.
- Freeze the first valid Pilot revision that meets the desired baseline score. If none does within the requested valid-iteration limit, restore and freeze the lowest-scoring valid Pilot revision.
- Freeze the selected revision and record its complete one-Run-per-Case Pilot result as the Formal Baseline when every cell is valid, the Agent State version remains unchanged, and no known design defect remains. Do not rerun or backfill it. The Formal score does not determine validity.
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.
- 3d ago Changed · -4 lines d267f0d7472e
- 8d 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 (2,013 stars, last pushed yesterday), licensed Apache-2.0. It adds 22 tokens to every session and 4,004 once invoked, about $0.0001 per session on Opus 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
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.
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.
web-ui-test
Test the IronClaw web UI using the Claude for Chrome browser extension.