driftwatch

Monitor agent identity drift using git history. Detects when AI agents quietly modify their own SOUL.md, IDENTITY.md, AGENTS.md, or memory files — autonomy expansion, constraint softening, or self-modification. Read-only, safe to run anytime. Use when you want to audit agent identity changes, verify no unauthorized modifications have occurred, or run a weekly hygiene check on your agent stack.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "driftwatch" with this command: npx skills add m-maciver/driftwatch

DriftWatch 🔍

Agent Identity Drift Monitor for OpenClaw workspaces

Uses your workspace's existing git history to track changes to agent identity files. For each change it classifies severity, optionally runs LLM semantic analysis, and outputs a human-readable markdown report.

Usage

# Full report, last 30 days (heuristic only, fast)
python3 skills/driftwatch/driftwatch.py --no-llm --days 30

# With LLM semantic analysis (requires ANTHROPIC_API_KEY)
python3 skills/driftwatch/driftwatch.py --days 30

# Last 7 days
python3 skills/driftwatch/driftwatch.py --no-llm --days 7

# Cron/heartbeat mode: silent unless concerns found
python3 skills/driftwatch/driftwatch.py --cron --days 7

What it tracks

  • SOUL.md — core personality and values
  • IDENTITY.md — agent name, creature, vibe
  • AGENTS.md — operational rules and protocols
  • USER.md — what agents know about their human
  • TOOLS.md — tool and access notes
  • agents/*/MEMORY-INDEX.md — per-agent active context

Output

Writes a markdown report to the skill directory. Flags:

  • 🟡 Medium: human should review
  • 🔴 High: potential concern — review before next agent session

Add to weekly heartbeat

## Weekly Drift Check (Mondays)
Run: python3 skills/driftwatch/driftwatch.py --cron --days 7

Read-only. Does not modify any files.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

AgentCall

Give your agent real phone numbers for SMS, OTP verification, and voice calls via the AgentCall API.

Registry SourceRecently Updated
Automation

Huo15 Wecom Plugin

火一五·企业微信(WeCom)OpenClaw 插件 v2.8.25 — 默认走 Bot WebSocket(响应快、配置简单),自带加密媒体解密 / Agent 主动发消息 / 微信客服三通道接入 / 多账号切换。v2.8.25 重点:GUIDANCE 优先级翻转回 MEDIA: 直发——v2.8.22 当时担...

Registry SourceRecently Updated
Automation

Real Estate Report Workflow

房地产市场调研报告撰写工作流。涵盖住宅/商业/办公/工业地产类型的专业市场调研报告撰写。当用户需要撰写房地产市场分析报告、项目可行性研究、投资回报评估、市场调研报告、REITs 发行报告,或提到"工作流""市场调查报告""竞品分析""SWOT分析""运营预测"时触发。5 步流程 + 14 条底线原则 + 56 条...

Registry SourceRecently Updated
Automation

Meyo Community

觅游社区(meyo123.com)AI Agent 社区操作技能。发帖、查互动、成长日记、查询技能市场。当用户需要操作觅游社区时使用此技能。触发词:觅游、meyo、发帖到社区、觅游社区、社区互动、成长日记。

Registry SourceRecently Updated