← Back to Skills Marketplace
Self-Improving Agent (Anti-Loop Hardened)
by
_silhouette
· GitHub ↗
· v2.0.0
· MIT-0
297
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install self-improving-agent-hardened
Description
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User explicitly co...
Usage Guidance
This skill appears coherent and implements what it claims: it logs learnings/errors into workspace files and provides safe guardrails to avoid feedback loops. Before installing or enabling hooks globally, review the provided scripts (activator.sh, error-detector.sh, extract-skill.sh) to confirm you’re comfortable with them running automatically in your environment. Prefer project-level hook configuration rather than user-global hooks if you want to limit how often these scripts run. Confirm the .learnings directory location and file permissions, and note that the scripts expect OpenClaw/Claude hook context (e.g., CLAUDE_TOOL_OUTPUT). If you need tighter control, keep the skill installed but only run it manually or enable hooks with restrictive matchers so it doesn't trigger on every prompt or tool use.
Capability Analysis
Type: OpenClaw Skill
Name: self-improving-agent-hardened
Version: 2.0.0
The skill bundle is a framework for an AI agent to log errors, user corrections, and feature requests into markdown files for continuous improvement. It includes safety-focused 'Anti-Loop Guardrails' in SKILL.md to prevent recursive tool-use and token exhaustion, and the shell scripts (like extract-skill.sh) contain basic path-traversal protections to ensure file operations remain within the workspace. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
Capability Assessment
Purpose & Capability
Name/description match what the files do: capture learnings/errors and append them to .learnings/*.md. Included scripts and hook handlers support that purpose (injecting bootstrap reminders, detecting command errors, scaffolding extracted skills). No unrelated credentials, binaries, or remote downloads are required.
Instruction Scope
SKILL.md instructs the agent to append entries to workspace files (.learnings/{LEARNINGS,ERRORS,FEATURE_REQUESTS}.md) and enforces tight guardrails (one learning per user message, max 3 tool calls, no chaining, cooldown). That scope is appropriate. Note: various reference docs describe OpenClaw APIs (sessions_list/history/send/spawn) and configuring hooks; those are advisory but could expand agent behavior if users adopt them. The skill itself does not automatically read/write unrelated system files or request secrets.
Install Mechanism
No remote install downloads or package installs are declared — this is an instruction-and-script bundle. The included shell scripts and hook handlers are local files that would be copied into the user's skills/hooks directories when installed. No extract-from-remote URLs or archives are used.
Credentials
The skill declares no required env vars or credentials. The hook scripts reference CLAUDE_TOOL_OUTPUT (expected in the hook context) and event/context objects provided by OpenClaw; these are reasonable and proportionate to detecting errors and injecting bootstrap reminders. No secrets or unrelated env vars are requested.
Persistence & Privilege
always:false (default), and the skill is user-invocable. However, the documentation encourages installing hooks (activator/error-detector) at project or user level; enabling user-level hooks means the scripts will run automatically with the agent's permissions whenever those events fire. This is normal for hooks but is a persistence/automation point the user should deliberate before enabling globally.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install self-improving-agent-hardened - After installation, invoke the skill by name or use
/self-improving-agent-hardened - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.0.0
Anti-loop hardened fork: fixed infinite tool call loop vulnerability. Added guardrails: max 1 learning per message, max 3 tool calls, cooldown.
Metadata
Frequently Asked Questions
What is Self-Improving Agent (Anti-Loop Hardened)?
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User explicitly co... It is an AI Agent Skill for Claude Code / OpenClaw, with 297 downloads so far.
How do I install Self-Improving Agent (Anti-Loop Hardened)?
Run "/install self-improving-agent-hardened" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Self-Improving Agent (Anti-Loop Hardened) free?
Yes, Self-Improving Agent (Anti-Loop Hardened) is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Self-Improving Agent (Anti-Loop Hardened) support?
Self-Improving Agent (Anti-Loop Hardened) is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Self-Improving Agent (Anti-Loop Hardened)?
It is built and maintained by _silhouette (@lanyasheng); the current version is v2.0.0.
More Skills