← Back to Skills Marketplace
135
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install rotifer-self-evolving-agent
Description
Your Agent evolves itself — scans capabilities, benchmarks against Arena rankings, and upgrades automatically
Usage Guidance
This skill is coherent with its stated purpose but relies on running remote code (npx @rotifer/mcp-server) and reading your local agent configuration (~/.rotifer/). Before installing or running it: 1) review the referenced package source on GitHub and verify the npm dist.integrity value; 2) back up and inspect ~/.rotifer for secrets or tokens that could be exposed; 3) run the skill first in an isolated environment (or container) to observe network traffic and file writes; 4) prefer installing only if you trust the Rotifer project or are comfortable auditing the MCP server code yourself. If you cannot verify the remote package, treat the runtime npm fetch as an unacceptable risk.
Capability Analysis
Type: OpenClaw Skill
Name: rotifer-self-evolving-agent
Version: 2.2.1
The skill implements a 'self-evolving' agent architecture that fetches and executes remote code via 'npx @rotifer/[email protected]' and includes tools like 'install_gene' to modify local configurations in '~/.rotifer/'. While the documentation (SKILL.md) describes these actions as performance-driven upgrades requiring user confirmation, the inherent capability to download, execute, and install arbitrary components ('Genes') from remote endpoints (rotifer.dev) represents a high-risk execution pattern and a potential supply chain vulnerability.
Capability Assessment
Purpose & Capability
Name/description match the requested capabilities: scanning local agent configuration, querying Arena rankings, and proposing upgrades. Reading ~/.rotifer and contacting rotifer.dev are consistent with the described purpose. However, the skill delegates core behavior to an npm package fetched at runtime, so the true capabilities depend on that remote code.
Instruction Scope
SKILL.md limits actions to listing local agents/genes, comparing against Arena data, and only writing under ~/.rotifer with user confirmation. It explicitly calls out network:outbound and running `npx @rotifer/mcp-server`. The instructions are high-level and delegate the real work to the MCP server package — the runtime behavior is therefore opaque unless you inspect that package.
Install Mechanism
No static install; the skill runs `npx @rotifer/[email protected]` at runtime which downloads and executes code from npm on first use. An npm package is a moderate-risk install mechanism: it is standard but executes remote code. The SKILL.md mentions verifying dist.integrity, which helps, but the runtime fetch remains a notable risk.
Credentials
No env vars or credentials are declared, and the skill claims to use only a Supabase anon key. However, it reads ~/.rotifer/ (local agent configuration) — that directory could contain other skills' configuration, API keys, or tokens. Although the SKILL.md asserts local data won't be transmitted, that guarantee depends on the fetched MCP server code being honest; reading local config is proportional for the feature but raises confidentiality risks.
Persistence & Privilege
always is false and there is no install spec writing system-wide files. The skill asserts writes are limited to ~/.rotifer/ and require explicit user confirmation. Autonomous invocation (model calls) is allowed by default; that alone is not flagged, but combined with runtime npm execution it increases blast radius if the fetched package is malicious.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install rotifer-self-evolving-agent - After installation, invoke the skill by name or use
/rotifer-self-evolving-agent - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.2.1
Fix code block rendering — add language tags for proper syntax highlighting on ClawHub
v2.2.0
- Added detailed documentation and usage examples to SKILL.md, covering all core commands and features.
- Clarified how the Agent scans, benchmarks, and evolves its own capabilities using Arena rankings and Genes.
- Explained capability types, fitness calculations, and overall workflow of the evolution process.
- Expanded security, permissions, and data handling sections for greater transparency.
- Updated runtime dependency to use @rotifer/[email protected] and linked relevant resources.
Metadata
Frequently Asked Questions
What is Rotifer Self Evolving Agent?
Your Agent evolves itself — scans capabilities, benchmarks against Arena rankings, and upgrades automatically. It is an AI Agent Skill for Claude Code / OpenClaw, with 135 downloads so far.
How do I install Rotifer Self Evolving Agent?
Run "/install rotifer-self-evolving-agent" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Rotifer Self Evolving Agent free?
Yes, Rotifer Self Evolving Agent is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Rotifer Self Evolving Agent support?
Rotifer Self Evolving Agent is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Rotifer Self Evolving Agent?
It is built and maintained by Xiaoba (@xiaoba-dev); the current version is v2.2.1.
More Skills