BrowseFull catalogOutcomesSolve a specific problemRolesStack by teamTrustFilter by risk tier
โ† Back to the Claude Observatory

penguin-harness

Skill Development Solid
Works inClaude Code
Solid Scanned โ€” metadata only

Reduces manual agent setup and iteration cycles by automating the creation and refinement of AI agents, allowing teams to deploy reasoning workloads faster aโ€ฆ

๐Ÿง Automated Agent Factory on Your Desktop: The Best Self-Improving Harness

2,914 starsApache-2.0 (commercial OK)FreeQuick setup

Reduces manual agent setup and iteration cycles by automating the creation and refinement of AI agents, allowing teams to deploy reasoning workloads faster and adapt them without constant human intervention.

Development teams building and iterating on multi-step AI agents for internal automation or customer-facing reasoning tasks.

Claude Code Claude Cowork Claude Chat

https://github.com/Prism-Shadow/penguin-harness

By Prism-Shadow

How to Get It

Option 1: Claude Desktop App (Code Mode)Click the + button next to the prompt box → Plugins → Add plugin. Search and click Install. Skills work in Claude Code only.
Option 2: Paste into Claude CodeCopy the command below and paste it into your conversation. Claude will install it.
Command
claude plugins install Prism-Shadow/penguin-harness

Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.

Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.

First thing to try

After installing, paste this into Claude:

Generate self-improving agent code that runs locally on my machine
CostFree

Trust Signals Auto-scanned

Stars2,914Contributors20Last updated2026-10-22LicenseApache-2.0 (OK for commercial use)Known CVEsNone foundSources: GitHub Advisory Database + OSV.dev · Scanned 2026-10-22 · scanner vattempted-no-data

Community Pulse Active

Discussed on Hacker News

2 mentions across 1 sources

Reviewer notes

Auto-scanned review. These are observations, not a security certification.

catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 2,914 GitHub stars; 20 contributors; last commit 5d ago; license Apache-2.0.

Things to check

  • Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.

How to evaluate tools before deploying โ†’

Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.

Evaluation

Ease of Use
4/5
Versatility
5/5
Reliability
5/5
Security
3/5
Overall score4.35 / 5.00 SolidEvaluatedOct 2026
catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 2,914 GitHub stars; 20 contributors; last commit 5d ago; license Apache-2.0.

โ† Back to the Claude Observatory

Rolling Claude out in your org? Let's talk.

Start a conversation โ†’