model-message-stream-p…
Integrate every model the same way, and keep one API in your head instead of one per provider.
2 skills123
@prism-shadowDevelopment
Plugin
penguin-harness
A set of skills for building and running self-evolving AI agents, including ACE context-engineering loops, rich interactive reply blocks, and a company mode that runs an organization of agents with CEO, employee, and finance roles.
Plugin Signal84/100Strong
maintained100
capable77
documented75
adopted75
Claude Code
$ npx -y skills add Prism-Shadow/penguin-harness --agent claude-code
Codex
$ npx skills add Prism-Shadow/penguin-harness -a codex
Cursor
$ npx skills add Prism-Shadow/penguin-harness -a cursor
Gemini CLI
$ npx skills add Prism-Shadow/penguin-harness -a gemini-cli
GitHub Copilot
$ npx skills add Prism-Shadow/penguin-harness -a github-copilot
OpenCode
$ npx skills add Prism-Shadow/penguin-harness -a opencode
Windsurf
$ npx skills add Prism-Shadow/penguin-harness -a windsurf
Stats
3,215
Stars
348
Forks
Active
Maintenance
TypeScript
Language
Apache-2.0
License
Last commit
Created
In this plugin
- a2ui
- ace-rsi-toolkit
- company-ceo
- company-employee
- company-finance
- company-hr
- company-mirror
- company-research
- company-setup
- agent-initialization
- penguin-config
- penguin-orchestration
- penguin-plugin
- penguin-sdk
- unified-llm-api
- agent-evaluation
- benchmark-design
- ape-rsi-toolkit
- awm-rsi-toolkit
- browser-automation
- data-analysis
- agent-optimization
- humanizer
- llamafactory
- ollama
- vllm
- openskill-rsi-toolkit
- opro-rsi-toolkit
- penguin-support
- agent-porting
- plugin-porting
- skill-porting
- skilladam-rsi-toolkit
- skillopt-rsi-toolkit
- software-engineering
- web-design
- trace-rsi-toolkit
- bento-slides
- remote-claude-code
- firecrawl
What's inside
40 Skills
/a2uiMake a reply easier to read and act on with rich blocks inside ordinary Markdown — a choice the user picks from, a form that collects several answers, a procedure as steps with warnings in place, a callout, a Mermaid diagram, a weather card, a live clock or countdown, a/ace-rsi-toolkitRun ACE (Agentic Context Engineering, Zhang et al. 2025) on an agent the sequential offline way - a Reflector reads each training Trace, a Curator adds the lessons to a playbook of rules the agent reads before every task, and the final playbook is measured on a published/company-ceoRun a PenguinHarness organization as its CEO — turn the mission into a ticket tree, hire HR and finance first, partition the shared workspace, schedule the calendar, open a channel per stream, review tickets and report to the board in the all-hands channel./company-employeeThe protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [org_trigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before/company-financeRun finance for a PenguinHarness organization — set and adjust monthly budgets along the reporting line, audit spend daily with penguin org finance and penguin cost, explain budget alerts in the all-hands channel with savings proposals, and handle budget pauses./company-hrRun HR for a PenguinHarness organization — guarantee every employee has an enabled calendar event, hire and offboard employees (channels included), evaluate and improve them (with the default-rsi-toolkit plugin's agent-optimization skill), and keep the handbook's role
- /company-mirror
- /company-research
- /company-setup
- /agent-initialization
- /penguin-config
- /penguin-orchestration
- /penguin-plugin
- /penguin-sdk
- /unified-llm-api
- /agent-evaluation
- /benchmark-design
- /ape-rsi-toolkit
- /awm-rsi-toolkit
- /browser-automation
- /data-analysis
- /agent-optimization
- /humanizer
- /llamafactory
- /ollama
- /vllm
- /openskill-rsi-toolkit
- /opro-rsi-toolkit
- /penguin-support
- /agent-porting
- /plugin-porting
- /skill-porting
- /skilladam-rsi-toolkit
- /skillopt-rsi-toolkit
- /software-engineering
- /web-design
- /trace-rsi-toolkit
- /bento-slides
- /remote-claude-code
- /firecrawl
README
Why PenguinHarness
PenguinHarness is an open-source framework for agent self-evolution (recursive self-improvement, RSI). The model stays fixed; the harness evolves: prompts, Skills, tools and hooks. It runs on your computer or server as a desktop app, a Web App, a CLI and an SDK.
- Every RSI algorithm in one framework. Default, OPRO, APE, ACE, AWM, SkillAdam, SkillOpt, OpenSkill and TRACE ship as plugins and run on the same built-in Benchmarks, scoreboard and snapshots.
- One sentence builds an agent app. Describe what you need, and an agent writes the app, its page and its run instructions.
- Cheap to run. A deliberately small toolset, tuned for open models: on our data-analysis suite, the best accuracy at 1/70 of Claude Code's cost.
Self-evolution
Pick an algorithm, pick a Benchmark, and an agent improves another agent round by round. Every candidate is a new version, snapshotted before it changes, and every score lands in the Evaluation Center.
| Toolkit | Algorithm |
|---|---|
default-rsi-toolkit | Trial, reflect, improve: one hypothesis and one change per round |
opro-rsi-toolkit | OPRO: new instructions from the history of scored ones |
ape-rsi-toolkit | APE: candidate instructions induced from examples |
ace-rsi-toolkit | ACE: lessons from Traces curated into a playbook |
awm-rsi-toolkit | AWM: workflows induced from successful runs |
skilladam-rsi-toolkit | SkillAdam: evolving issue tracker and adaptive Skill edit budget |
skillopt-rsi-toolkit | SkillOpt: bounded Skill edits, score-based selection and cross-epoch reflection |
openskill-rsi-toolkit | OpenSkill: external research and independent virtual tests before frozen-State evaluation |
trace-rsi-toolkit | TRACE: skill-bank evolution from contrasting trajectories, with consistency measurement |
Every new Project includes seventeen Benchmarks, run as Harbor tasks in Docker: PenguinHarness Benchmark Sec A to Sec E (from rag-bench-essential, DeepSWE, AutomationBench, Terminal-Bench-Science and Terminal-Bench) and a Train/Test pair for each of GDPEVO Essential's six scenarios. More are in penguin-harness-benchmark.
Demo: a decision agent is evaluated, revises its working method once, and is retested on the same model. Its score goes from 84 to 100, and the cost of every run is on screen.
One sentence, one app
Build a legal review agent with a simple workspace where users upload contracts, track the review, and download a report with risky clauses, explanations, and suggested revisions.
The result: a legal review app. Users upload contracts, follow each file's review, and download a report of risky clauses with explanations and suggested revisions. Five sample reviews cost $0.0423 in model calls.
https://github.com/user-attachments/assets/28c0ef95-1dfa-47be-bad0-7326ccdf4e7c
What agents can do
Replies can also carry UI: choices, forms, steps, Mermaid diagrams and live widgets (A2UI).
Results
Each harness on the model it is usually paired with, on the same tasks:
Built-in plugins
Agents can also write and optimize their own Skills (docs).
| Category | Plugins |
|---|---|
| Agent Self-Evolution | default-rsi-toolkit, opro-rsi-toolkit, ape-rsi-toolkit, ace-rsi-toolkit, awm-rsi-toolkit, skilladam-rsi-toolkit, skillopt-rsi-toolkit, openskill-rsi-toolkit, trace-rsi-toolkit |
| Office Productivity | a2ui, data-analysis, use-firecrawl, browser-automation, use-bento-slides, humanizer, goal, continual-learning, agent-company, penguin-support |
| Software Development | software-development, use-claude-code |
| AI App Development | agent-development, agent-evaluation, model-development, skill-porting |
Supported models
These are the model families we focus on supporting. The app's Models page lists each variant and its providers.
Closed-source models
| Model | Providers |
|---|---|
| GPT 6.1 | OpenAI, OpenRouter |
| Claude 5.5 | Anthropic, OpenRouter, OpenCode Go |
| Gemini 4 | Google Gemini, OpenRouter, Penguin Go, OpenCode Go |
| Grok 4.7 | OpenRouter, OpenCode Go |
| Qwen3.8 Max | Qwen Token Plan, Qwen Pay-As-You-Go, OpenRouter, TokenDance, OpenCode Go |
Open-source models
| Model | Providers |
|---|---|
| DeepSeek V4.1 | DeepSeek, OpenRouter, Fireworks AI, Atlas Cloud, TokenDance, Penguin Go, OpenCode Go, Qwen Token Plan, Qwen Pay-As-You-Go, ModelScope |
| Kimi K3 | Moonshot AI, OpenRouter, Fireworks AI, TokenDance, OpenCode Go, Qwen Pay-As-You-Go |
| GLM 5.3 | Z.AI, OpenRouter, TokenDance, OpenCode Go |
| Hunyuan 4 | OpenRouter, TokenDance, OpenCode Go |
| MiMo v2.6 | OpenRouter, TokenDance, OpenCode Go |
OpenCode Go offers Claude Haiku 5.5; Fable 5.1, Opus 5.5 and Sonnet 5.5 are available through Anthropic and OpenRouter. Hunyuan 4 uses hy4-preview.
Custom OpenAI-protocol endpoints also work, covering 1000+ online and local models.
Install
Desktop app
Download the installer from penguin.ooo/download: macOS 11+ (dmg), Windows 10+ (exe) or Linux x64 (AppImage, deb). The app opens signed in and needs no terminal.
Stars on GitHub
Momentum
- stars in total
- 3.2k
File tree
More plugins by @prism-shadow.
View @prism-shadow’s profile@prism-shadowSimilar plugins.
See 12 penguin-harness alternatives
superpowers
A development methodology for coding agents that makes the agent brainstorm before building, follow plans, run parallel work and finish branches in a disciplined way. You get fewer skipped steps and more consistent results from your coding assistant.
15 skills1 hook311k
@obraskills
Helps you take a change from a rough idea or bug report through to a tested, reviewed result, with each step handled by a focused skill. Its skills cover pinning down domain terms, designing module interfaces, diagnosing hard bugs, and reviewing changes against your repo's coding standards.
31 skills309k
@mattpocockecc
Gives your coding agent a planning, testing and review routine to follow on every task. It plans before building, checks changes with tests, has a fresh reviewer look for regressions, and saves repeated wins as reusable skills.
200 skills71 agents1 MCP+3+2+2+2+2+2+2+1+1302k
@affaan-mreact
Developer tools for working on the React codebase itself. Provides skills for extracting error messages, managing and debugging feature flags across release channels, running Flow type checks, and fixing lint and formatting issues before committing.
14 skills4 agents252k
@facebookQuestions about penguin-harness.
A set of skills for building and running self-evolving AI agents, including ACE context-engineering loops, rich interactive reply blocks, and a company mode that runs an organization of agents with CEO, employee, and finance roles. Install it with the command on its page. It includes a2ui, ace-rsi-toolkit, company-ceo. Its skills do not fire on their own yet. Free and open source.
- What is penguin-harness?
- A set of skills for building and running self-evolving AI agents, including ACE context-engineering loops, rich interactive reply blocks, and a company mode that runs an organization of agents with CEO, employee, and finance roles.
- How do I install penguin-harness?
- Run these in Claude Code: npx -y skills add Prism-Shadow/penguin-harness --agent claude-code. Then prompt normally.
- Does penguin-harness auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin.
- Is penguin-harness free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.
- Which coding agents can use penguin-harness's skills?
- penguin-harness installs in Claude Code, and its skills also install in Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI. Each skill's page has the install command. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it