OpenClaw-superpowers

Details

External ID

47384832

Source

HN

Company

—

Product

OpenClaw-superpowers

Website domain

github.com

Launched

March 15, 2026

Cohort

—

Upvotes

8

Upvotes percentile

0.491389913899139

Tags

—

Fetched at

Sept. 7, 2026, 9:26 p.m.

Updated at

Sept. 7, 2026, 9:26 p.m.

Description

I built a skill library for OpenClaw (always-on AI agent runtime, not session-based) where the agent can teach itself new behaviors during normal conversation.The idea: you tell your agent "every time I ask for a code review, always check for security issues first." It invokes a create-skill skill, writes a new SKILL.md, and that behavior is live immediately — no restart, no config change, no developer required.What I think is actually useful (the safety cluster):• loop-circuit-breaker: OpenClaw retries ALL errors identically. This halts on the 2nd identical failure before it burns your context window. • spend-circuit-breaker: No built-in cap in OpenClaw. This tracks cumulative API cost and pauses non-essential crons at configurable thresholds. • workspace-integrity-guardian: Hashes SOUL.md, AGENTS.md, MEMORY.md. A corrupted SOUL.md = hijacked agent that survives restarts. • dangerous-action-guard: Explicit confirmation before rm -rf, git push --force, emails, financial actions. With audit log. • prompt-injection-guard: Scans external content (web scrapes, emails, docs) before acting on it.Also: fact-check-before-trust (secondary verification for factual claims), project-onboarding (auto-generates PROJECT.md from a codebase), skill-vetting (security scanner — ~17% of community skills are malicious).

• Source listing
• Website