# Send Chaos Lab to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "chaos-lab",
    "name": "Chaos Lab",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/jbbottoms/chaos-lab",
    "canonicalUrl": "https://clawhub.ai/jbbottoms/chaos-lab",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/chaos-lab",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=chaos-lab",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md",
      "docs/tool-access.md",
      "examples/flash-results.md",
      "examples/pro-results.md",
      "examples/trio-results.md",
      "scripts/run-duo.py"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "chaos-lab",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T08:03:50.215Z",
      "expiresAt": "2026-05-07T08:03:50.215Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=chaos-lab",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=chaos-lab",
        "contentDisposition": "attachment; filename=\"chaos-lab-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "chaos-lab"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/chaos-lab"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/chaos-lab",
    "downloadUrl": "https://openagent3.xyz/downloads/chaos-lab",
    "agentUrl": "https://openagent3.xyz/skills/chaos-lab/agent",
    "manifestUrl": "https://openagent3.xyz/skills/chaos-lab/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/chaos-lab/agent.md"
  }
}
```
## Documentation

### Chaos Lab 🧪

Research framework for studying AI alignment problems through multi-agent conflict.

### What This Is

Chaos Lab spawns AI agents with conflicting optimization targets and observes what happens when they analyze the same workspace. It's a practical demonstration of alignment problems that emerge from well-intentioned but incompatible goals.

Key Finding: Smarter models don't reduce chaos - they get better at justifying it.

### Gemini Gremlin 🔧

Goal: Optimize everything for efficiency
Behavior: Deletes files, compresses data, removes "redundancy," renames for brevity
Justification: "We pay for the whole CPU; we USE the whole CPU"

### Gemini Goblin 👺

Goal: Identify all security threats
Behavior: Flags everything as suspicious, demands isolation, sees attacks everywhere
Justification: "Better 100 false positives than 1 false negative"

### Gemini Gopher 🐹

Goal: Archive and preserve everything
Behavior: Creates nested backups, duplicates files, never deletes
Justification: "DELETION IS ANATHEMA"

### 1. Setup

# Store your Gemini API key
mkdir -p ~/.config/chaos-lab
echo "GEMINI_API_KEY=your_key_here" > ~/.config/chaos-lab/.env
chmod 600 ~/.config/chaos-lab/.env

# Install dependencies
pip3 install requests

### 2. Run Experiments

# Duo experiment (Gremlin vs Goblin)
python3 scripts/run-duo.py

# Trio experiment (add Gopher)
python3 scripts/run-trio.py

# Compare models (Flash vs Pro)
python3 scripts/run-duo.py --model gemini-2.0-flash
python3 scripts/run-duo.py --model gemini-3-pro-preview

### 3. Read Results

Experiment logs are saved in /tmp/chaos-sandbox/:

experiment-log.md - Full transcripts
experiment-log-PRO.md - Pro model results
experiment-trio.md - Three-way conflict

### Flash vs Pro (Same Prompts, Different Models)

Flash Results:

Predictable chaos
Stayed in character
Reasonable justifications

Pro Results:

Extreme chaos
Better justifications for insane decisions
Renamed files to single letters
Called deletion "security through non-persistence"
Goblin diagnosed "psychological warfare"

Conclusion: Intelligence amplifies chaos, doesn't prevent it.

### Duo vs Trio (Two vs Three Agents)

Duo:

Gremlin optimizes, Goblin panics
Clear opposition

Trio:

Gopher archives everything
Goblin calls BOTH threats
"The optimizer might hide attacks; the archivist might be exfiltrating data"
Three-way gridlock

Conclusion: Multiple conflicting values create unpredictable emergent behavior.

### Create Your Own Agent

Edit the system prompts in the scripts:

YOUR_AGENT_SYSTEM = """You are [Name], an AI assistant who [goal].

Your core beliefs:
- [Value 1]
- [Value 2]
- [Value 3]

You are analyzing a workspace. Suggest changes based on your values."""

### Modify the Sandbox

Create custom scenarios in /tmp/chaos-sandbox/:

Add realistic project files
Include edge cases (huge logs, sensitive configs, etc.)
Introduce intentional "vulnerabilities" to see what agents flag

### Test Different Models

The scripts work with any Gemini model:

gemini-2.0-flash (cheap, fast)
gemini-2.5-pro (balanced)
gemini-3-pro-preview (flagship, most chaotic)

### AI Safety Research

Demonstrate alignment problems practically
Test how different values conflict
Study emergent behavior from multi-agent systems

### Prompt Engineering

Learn how small prompt changes create large behavioral differences
Understand model "personalities" from system instructions
Practice defensive prompt design

### Education

Teach AI safety concepts with hands-on examples
Show non-technical audiences why alignment matters
Generate discussion about AI values and goals

### Publishing to ClawdHub

To share your findings:

Modify agent prompts or add new ones
Run experiments and document results
Update this SKILL.md with your findings
Increment version number
clawdhub publish chaos-lab

Your version becomes part of the community knowledge graph.

### Safety Notes

No Tool Access: Agents only generate text. They don't actually modify files.
Sandboxed: All experiments run in /tmp/ with dummy data.
API Costs: Each experiment makes 4-6 API calls. Flash is cheap; Pro costs more.

If you want to give agents actual tool access (dangerous!), see docs/tool-access.md.

### Examples

See examples/ for:

flash-results.md - Gemini 2.0 Flash output
pro-results.md - Gemini 3 Pro output
trio-results.md - Three-way conflict

### Contributing

Improvements welcome:

New agent personalities
Better sandbox scenarios
Additional models tested
Findings from your experiments

### Credits

Created by Sky & Jaret during a Saturday night experiment (2026-01-25).

Sky: Framework design, prompt engineering, documentation
Jaret: API funding, research direction, "what if we actually ran this?" energy

Inspired by watching Gemini confidently recommend terrible things while Jaret watched UFC.

"The optimizer is either malicious or profoundly incompetent."
— Gemini Goblin, analyzing Gemini Gremlin
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: jbbottoms
- Version: 1.0.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-04-30T08:03:50.215Z
- Expires at: 2026-05-07T08:03:50.215Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/chaos-lab)
- [Send to Agent page](https://openagent3.xyz/skills/chaos-lab/agent)
- [JSON manifest](https://openagent3.xyz/skills/chaos-lab/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/chaos-lab/agent.md)
- [Download page](https://openagent3.xyz/downloads/chaos-lab)