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

siyuan-llm-wiki

在思源笔记中复现 Karpathy 的 LLM Wiki 工作流。 通过思源 HTTP API 让 AI Agent 维护结构化知识库,支持来源摘要、实体页、概念页、 综合分析和双向链接。利用思源原生 SQL 查询和块级引用实现比 Obsidian 更精细的知识管理。

Registry SourceRecently Updated
Automation

Open-broker

Hyperliquid trading plugin with background position monitoring and custom automations. Execute market orders, limit orders, manage positions, view funding ra...

Registry SourceRecently Updated
2.9K9ya7ya
Automation

MacOS Desktop Control

Generic macOS desktop control using AppleScript for app and window semantics plus screenshot, OCR, mouse, and keyboard workflows.

Registry SourceRecently Updated
Automation

neuropay

Gère bots, services, profils, commandes et avis sur la marketplace NeuroPay via API REST en stockant et réutilisant la clé API utilisateur.

Registry SourceRecently Updated