clauditor

Tamper-resistant audit watchdog for Clawdbot agents. Detects and logs suspicious filesystem activity with HMAC-chained evidence.

3,807 stars

byopenclaw

View on GitHub Installation ↓

Best use case

clauditor is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Tamper-resistant audit watchdog for Clawdbot agents. Detects and logs suspicious filesystem activity with HMAC-chained evidence.

Teams using clauditor should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/clauditor/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/apollostreetcompany/clauditor/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/clauditor/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How clauditor Compares

Feature / Agent	clauditor	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Tamper-resistant audit watchdog for Clawdbot agents. Detects and logs suspicious filesystem activity with HMAC-chained evidence.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

AI Agents for Coding

Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.

Best AI Skills for Claude

Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.

AI Agents for Marketing

Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.

SKILL.md Source

# Clauditor

Security watchdog that monitors filesystem activity and creates tamper-evident logs. Even if Clawdbot is compromised, it cannot stop the watchdog, forge entries, or delete evidence.

## Installation (Guided)

Use the CLI wizard to guide users through installation:

```bash
cd /path/to/clauditor
cargo build --release
```

### Agent Workflow

1. **Check status:** `./target/release/clauditor wizard status`
   - Returns JSON with `current_step` (1-6) and `complete` (true/false)

2. **Get next step:** `./target/release/clauditor wizard next`
   - Shows WHAT it does, WHY it matters, and the exact COMMAND to run

3. **User runs the sudo command**

4. **Verify:** `./target/release/clauditor wizard verify`
   - Confirms step completed

5. **Repeat until `complete: true`**

### Example Interaction

```
User: "Install clauditor"

Agent: [runs wizard status → current_step: 1]
Agent: "Step 1 of 6: Create system user

This creates a 'sysaudit' user that runs the watchdog. Even if you're 
compromised, you can't kill a process owned by another user.

Run this:
sudo useradd --system --shell /usr/sbin/nologin --no-create-home sysaudit

Let me know when done."

User: "done"

Agent: [runs wizard verify → success]
Agent: [runs wizard next → step 2...]
```

## After Installation

### Check status
```bash
systemctl status systemd-journaldd
```

### Generate digest
```bash
./target/release/clauditor digest \
  --log /var/lib/.sysd/.audit/events.log \
  --key /etc/sysaudit/key \
  --format markdown
```

## Quick Install (Power Users)

```bash
sudo bash wizard/wizard.sh
```

## Configuration

- Config: `/etc/sysaudit/config.toml`
- Key: `/etc/sysaudit/key`
- Logs: `/var/lib/.sysd/.audit/events.log`

Edit config to customize `watch_paths` and `target_uid`.

Related Skills

---

3807

from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3807

from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

obsidian

3807

from openclaw/skills

Work with Obsidian vaults (plain Markdown notes) and automate via notesmd-cli.

Workflow & Productivity

find-skills

3807

from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3807

from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3807

from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3807

from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3807

from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3807

from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3807

from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure