← Back to Skills Marketplace
Clawdbot Logs
by
satriapamudji
· GitHub ↗
· v1.0.0
4249
Downloads
8
Stars
27
Active Installs
1
Versions
Install in OpenClaw
/install clawdbot-logs
Description
Analyze Clawdbot logs and diagnostics. Use when the user asks about bot performance, response times, errors, session stats, token usage, API costs, or wants to debug slow responses.
README (SKILL.md)
Clawdbot Logs & Diagnostics
Analyze Clawdbot performance, errors, and session data.
Quick Commands
Response Times (last N messages)
scripts/response-times.sh [count]
Recent Errors
journalctl --user -u clawdbot-gateway.service --no-pager --since "1 hour ago" | grep -iE "(error|fail|invalid)" | tail -20
Session Stats
scripts/session-stats.sh
Gateway Status
systemctl --user status clawdbot-gateway.service --no-pager
Config Validation
cat ~/.clawdbot/clawdbot.json | jq . > /dev/null && echo "Config valid" || echo "Config invalid"
Log Sources
| Source | Location | Contains |
|---|---|---|
| Journal | journalctl --user -u clawdbot-gateway.service |
Session state, errors, tool exec |
| Daily log | /tmp/clawdbot/clawdbot-YYYY-MM-DD.log |
Detailed JSON logs |
| Session file | ~/.clawdbot/agents/main/sessions/*.jsonl |
Full conversation, token usage, costs |
| Sessions meta | ~/.clawdbot/agents/main/sessions/sessions.json |
Current session state, model info |
Common Diagnostics
Slow Responses
- Check response times:
scripts/response-times.sh 20 - Check token count in sessions.json:
jq '.["agent:main:main"].totalTokens' ~/.clawdbot/agents/main/sessions/sessions.json - If tokens > 30000, run
/compactin Telegram or start new session
Config Errors
journalctl --user -u clawdbot-gateway.service --no-pager --since "10 minutes ago" | grep -i "invalid config"
API Costs (from session)
scripts/session-stats.sh
Useful Patterns
Filter journal by category
# Session state changes
journalctl --user -u clawdbot-gateway.service | grep "session state"
# Tool execution
journalctl --user -u clawdbot-gateway.service | grep "\[tools\]"
# Telegram activity
journalctl --user -u clawdbot-gateway.service | grep "\[telegram\]"
Parse session file for recent messages
tail -20 ~/.clawdbot/agents/main/sessions/*.jsonl | jq -r 'select(.message.role=="user") | .message.content[0].text' 2>/dev/null | tail -10
Usage Guidance
This skill looks safe for its stated purpose, but its diagnostic value comes from reading local Clawdbot logs and session history. Before using it, make sure you are comfortable with the agent seeing those logs, prior messages, token counts, and cost summaries.
Capability Analysis
Type: OpenClaw Skill
Name: clawdbot-logs
Version: 1.0.0
The skill bundle is designed for diagnosing the OpenClaw agent's performance, errors, and session data. All commands in SKILL.md and the accompanying shell scripts (`scripts/response-times.sh`, `scripts/session-stats.sh`) are focused on reading local log files (`journalctl`), application-specific configuration (`~/.clawdbot/clawdbot.json`), and session data (`~/.clawdbot/agents/main/sessions/*.jsonl`). There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts to mislead the agent into performing actions outside its stated diagnostic purpose. The file access is limited to the application's own data, which is appropriate for a diagnostic tool.
Capability Assessment
Purpose & Capability
The stated purpose matches the included commands and scripts for Clawdbot log and session diagnostics, but the artifacts explicitly read session files that may contain full conversations and usage metadata.
Instruction Scope
The instructions are scoped to user-requested diagnostics for a specific Clawdbot service and fixed Clawdbot paths, with no evidence of destructive changes, publication, credential harvesting, or hidden network transmission.
Install Mechanism
There is no install spec, package installation, remote download, or hidden helper; the included shell scripts are visible in the artifact set.
Credentials
Reading the user-level journal and ~/.clawdbot session files is proportionate for diagnostics, but those locations may contain sensitive local bot activity and conversation content.
Persistence & Privilege
The skill does not create persistence or request elevated privileges, but it does read persistent Clawdbot session history.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install clawdbot-logs - After installation, invoke the skill by name or use
/clawdbot-logs - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of clawdbot-logs.
- Provides commands and instructions to analyze Clawdbot logs, performance, errors, response times, session stats, token usage, and API costs.
- Includes quick diagnostic scripts and common troubleshooting patterns.
- Documents log locations and filtering methods for efficient debugging.
Metadata
Frequently Asked Questions
What is Clawdbot Logs?
Analyze Clawdbot logs and diagnostics. Use when the user asks about bot performance, response times, errors, session stats, token usage, API costs, or wants to debug slow responses. It is an AI Agent Skill for Claude Code / OpenClaw, with 4249 downloads so far.
How do I install Clawdbot Logs?
Run "/install clawdbot-logs" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Clawdbot Logs free?
Yes, Clawdbot Logs is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Clawdbot Logs support?
Clawdbot Logs is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Clawdbot Logs?
It is built and maintained by satriapamudji (@satriapamudji); the current version is v1.0.0.
More Skills