rl-runtime-guard
Soft, opt-in runtime guardrails for AI agents — advisory reminders injected before each request, never blocking or modifying tool output. Install when an agent keeps repeating itself, a complex task keeps failing midway, a Windows path got pasted into a Linux shell, or the agent keeps trying the sam
as observed 2026-09-06T09:04:43.486Z- Identifier
rl-runtime-guard- Source
- ClawHub
- Version observed
- 1.0.7
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-08-31T05:56:02.339Z
- Observations recorded
- 2
- Installs (reported upstream)
- 0
- Weekly downloads (upstream)
- 186
Observation history
2026-09-06T09:04:43.486Z
Fields that differed: changelog description latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"Privacy-by-default: audit logging now opt-in via auditLogPath; no user content captured" | "Soften description with 'soft, opt-in, advisory, never-blocking' framing to address ClawHub AI scanner verdict on v1.0.6" |
description |
"Pre-tool-call runtime guardrails for AI agents. Catches three classes of common agent errors at runtime — complex tasks not broken down (43% of failures), retry loops (27%), and t | "Soft, opt-in runtime guardrails for AI agents — advisory reminders injected before each request, never blocking or modifying tool output. Install when an agent keeps repeating its |
latestVersion |
"1.0.5" | "1.0.7" |
summary |
"Pre-tool-call runtime guardrails for AI agents. Catches three classes of common agent errors at runtime — complex tasks not broken down (43% of failures), retry loops (27%), and t | "Soft, opt-in runtime guardrails for AI agents — advisory reminders injected before each request, never blocking or modifying tool output. Install when an agent keeps repeating its |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.