LaunchKit · 2026
Back to Skills

agent-sentinel

AI & LLMsv0.1.1

The operational circuit breaker for this agent.

2
2.2k downloads
by @jimmystacks

Setup & Installation

openclaw skills install @jimmystacks/agent-sentinel

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install agent-sentinel

Version History

v0.1.1Feb 1, 2026 - Version note by skill developer:

- Added cloud connectivity support with instructions to link your agent to AgentSentinel for real-time monitoring and human approval. - Install now requires agentsentinel-sdk[remote] to ensure remote syncing via httpx. - Updated tool documentation to include the new login command and clarify usage. - Improved status command output to show cloud connection status. - Enhanced documentation to mention dashboards and workflows at agentsentinel.dev.

What This Skill Does

AgentSentinel adds a budget enforcement and action safety layer to AI agents. It intercepts potentially destructive or expensive commands before execution, requiring explicit approval when thresholds are exceeded. An optional cloud connection enables real-time dashboards and human-in-the-loop approval workflows.

Unlike simple prompt-level guardrails, AgentSentinel enforces limits at the tool-call level and can escalate to a human approver before irreversible actions complete.

When to use it

  • Blocking an agent from deleting files without confirmation
  • Capping API spend per session to avoid runaway costs
  • Requiring human approval before an agent executes unknown code
  • Monitoring cumulative cost across a long multi-step coding task
  • Pausing an automated workflow when a sensitive data transfer is detected

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: clean up all temp files in /tmp

AGENT
  1. 1Agent calls check_safety with cmd='rm -rf /tmp' and estimated cost
  2. 2sentinel_wrapper.py evaluates the command against budget and restriction rules
  3. 3check_safety returns APPROVAL_REQUIRED for a destructive delete
  4. 4Agent calls request_approval with the action and reason
  5. 5Human approves or denies via dashboard; agent proceeds only on approval
OUTPUT

Files deleted only after explicit human confirmation, with cost logged to the session.

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

AGENT_SENTINEL_API_KEY environment variable (from agentsentinel.dev dashboard, required for cloud features)