Official Verified

safety-checks

Verify before you trust — model pinning, fallbacks, and runtime safety validation

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/leegitw/safety-checks

Download Source Code (.zip)

safety-checks (安全)

Unified skill for runtime safety verification including model version pinning, fallback chain validation, cache staleness detection, and cross-session state checks. Consolidates 4 granular skills into a single safety verification suite.

Trigger: 事前検証 (pre-flight) or HEARTBEAT

Source skills: model-pinner, fallback-checker, cache-validator, cross-session-safety-check (from extensions)

Installation

openclaw install leegitw/safety-checks

Dependencies: leegitw/constraint-engine (for enforcement integration)

# Install with dependencies
openclaw install leegitw/context-verifier
openclaw install leegitw/failure-memory
openclaw install leegitw/constraint-engine
openclaw install leegitw/safety-checks

Standalone usage: Model pinning and cache checks work independently. Full integration with constraint enforcement requires constraint-engine.

Data handling: This skill performs local-only operations. All checks (model version comparison, cache age verification, file lock detection) are local file/metadata operations — no data is sent to any model, API, or external service. Results are written to output/safety/ in your workspace.

What This Solves

AI systems can silently degrade — model versions drift, caches go stale, sessions accumulate state. This skill catches these issues before they cause problems:

Model pinning — verify you're using the model you expect
Fallback validation — ensure degraded-mode paths exist and work
Cache checks — detect stale or corrupted cached data
Session hygiene — identify cross-session state contamination

The insight: Runtime verification catches what static rules miss. Check the system state, not just the configuration.

Usage

/sc <sub-command> [arguments]

Sub-Commands

Command	CJK	Logic	Trigger
`/sc model`	機種	model.version→pinned✓∨drift✗	HEARTBEAT
`/sc fallback`	代替	chain.exists→safe✓∨missing✗	HEARTBEAT
`/sc cache`	快取	response.age>TTL→stale✗	HEARTBEAT
`/sc session`	会話	cross_session.state→clean✓∨interference✗	HEARTBEAT

Arguments

/sc model

Argument	Required	Description
--expected	No	Expected model version (default: from config)
--strict	No	Fail on any version mismatch

/sc fallback

Argument	Required	Description
--chain	No	Specific fallback chain to check in config

Note: This command validates that fallback configurations exist in your config file. It does NOT make network calls or test actual connectivity. It's a config file audit.

/sc cache

Argument	Required	Description
--ttl	No	TTL in seconds (default: 3600)
--clear	No	Clear stale cache entries

/sc session

Read Full Documentation on GitHub

Metadata

Author@leegitw

Stars1656

Updated2026-02-28

View Author Profile

AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill

Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-leegitw-safety-checks": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Related Skills

doctorbot-ci-validator

Stop failing in production. Validate your GitHub Actions, GitLab CI & Keep workflows offline with surgical precision. Born from Keep bounty research, perfected for agents.

bamontejano 4473

run-command-safety-check

在执行 shell 方案前检查危险模式，如 pipe-to-shell、覆盖式删除、危险重定向或混淆执行。；use for shell, security, command-review workflows；do not use for 提供攻击性命令, 帮用户绕过限制.

52yuanchangxing 4473

scar-safety

Agent safety that learns from incidents. Reflex arc blocks repeat threats without LLM calls.

aibenyclaude-coder 4473

skill-frontmatter-doctor

修复 frontmatter、metadata、requires、install 和目录结构问题，贴合当前 OpenClaw 规范。；use for skills, frontmatter, validation workflows；do not use for 编造不存在的字段, 忽略单行 JSON 约束.