RSI Loop v2 — AVO-Inspired Agent Self-Improvement

Recursive Self-Improvement (RSI) loop for EvoClaw agents. Provides a structured observe→analyze→synthesize→deploy pipeline that enables agents to detect thei...

What to check before installing/using this skill: - Review deployer.py, synthesizer.py, and any 'apply_gene' logic. Confirm how the code enforces blast_radius and IMMUTABLE_CORE (is AGENTS.md / SOUL.md actually blocked at runtime?). - Expect the skill to write files under skills/rsi-loop/data/ and skills/rsi-loop/memory/ (append-only lineage & events). If you need to keep an audit trail, review those artifacts; if not, run in a disposable environment first. - The skill can execute scripts in other skill directories (e.g., skills/intelligent-router/*). Decide whether you want an automated process that can run those commands or change those files — if not, restrict filesystem permissions or run the skill in a sandbox/container. - The code refers to an EVOLVE_STRATEGY env var and other platform integrations (MQTT, model provider names) but declares none; if you plan to enable auto-deploy, make explicit policies and environment variables you trust. Consider setting auto-approve thresholds to 0 (no auto-approve) until you’ve audited behavior. - Because this skill can autonomously modify repo files and run cross-skill commands, treat it like a privileged operator: test in a safe sandbox, inspect tests and the deploy path, and require human-in-the-loop approval for any change touching production files. If you want, I can scan specific files (deployer.py, synthesizer.py, openclaw_shim.py) for the exact enforcement logic and list the places where it reads/writes files or invokes external commands.

Type: OpenClaw Skill Name: rsi-loop Version: 2.0.0 The bundle implements a 'Recursive Self-Improvement' (RSI) framework that enables an agent to autonomously analyze its own logs, generate 'improvement' proposals, and deploy code or configuration changes. While the stated intent is agent evolution, the implementation in 'scripts/deployer.py' is highly risky, as it executes arbitrary shell commands (shell=True) defined in 'data/genes.json' and can modify the agent's workspace. The bundle includes security-conscious features like an 'IMMUTABLE_CORE' list to protect sensitive files (e.g., SOUL.md) and 'blast_radius' checks to limit the scope of changes, which suggests a complex tool rather than intentional malware. However, the autonomous self-modification and shell execution capabilities represent a significant RCE surface if the agent's synthesis logic is compromised or manipulated via prompt injection.