openclaw-debugger

openclaw-debugger is a skill for Claude Code, Codex from mergisi/awesome-openclaw-agents. It costs 71 tokens per session (1,077 once invoked), scanned A, original, MIT.

A troubleshooting guide for OpenClaw, a system for running named AI agents such as Orion or Echo.

In plain words
What is it for?
Use it to check the gateway, inspect recent logs, and diagnose errors such as invalid credentials, rate limits, refused connections, and timeouts.
Why use it?
It helps identify why an agent is silent, stuck, crashing, timing out, or failing to connect to its model provider by checking the likely causes in order.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to check the gateway, inspect recent logs, and diagnose errors such as invalid credentials, rate limits, refused connections, and timeouts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mergisi/awesome-openclaw-agents/openclaw-debugger
About the project

awesome-openclaw-agents is a curated collection of ready-to-use SOUL.md configurations that define AI agents for tasks across areas such as development, marketing, finance, support, and automation. It is for OpenClaw users who want predefined agent roles and workflows to adapt or deploy. The catalogue entries are agent-related skills drawn from this collection.

mergisi/awesome-openclaw-agents · 3,953 stars · on GitHub · crewclaw.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add mergisi/awesome-openclaw-agents --skill openclaw-debugger
Clone the repo
git clone --depth 1 https://github.com/mergisi/awesome-openclaw-agents

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for openclaw-debugger

README.md
[![agentmods](https://agentmods.dev/badge/skills/mergisi/awesome-openclaw-agents/openclaw-debugger/github.svg)](https://agentmods.dev/skills/mergisi/awesome-openclaw-agents/openclaw-debugger)
Your own site
<a href="https://agentmods.dev/skills/mergisi/awesome-openclaw-agents/openclaw-debugger"><img src="https://agentmods.dev/badge/skills/mergisi/awesome-openclaw-agents/openclaw-debugger/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for openclaw-debugger

Your own site · 80×15
<a href="https://agentmods.dev/skills/mergisi/awesome-openclaw-agents/openclaw-debugger"><img src="https://agentmods.dev/badge/skills/mergisi/awesome-openclaw-agents/openclaw-debugger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,077 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 54
    Code scans file system directories looking for sensitive files. This could be reconnaissance for credential theft.
    Fix: Remove unnecessary filesystem scanning. If file access is needed, use explicit, scoped paths. Avoid reading ~/.ssh, ~/.aws, or credential directories.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00071 $0.01077
Opus 5 $0.00036 $0.00539
Sonnet 5 $0.00014 $0.00215
Haiku 4.5 $0.00007 $0.00108

Measured 9d ago against content hash ffaedf0533d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

openclaw-debugger scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **GLM-5.1 / Minimax M2.7:** check `~/.openclaw/providers.json` for the base URL and hit `/v1/models` with curl.
skills/claude/openclaw-debugger/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenClaw Debugger

Diagnose a broken OpenClaw agent (Orion, Echo, Radar, or any custom agent from awesome-openclaw-agents). Produces a structured diagnosis report identifying the most likely root cause.

Compatible with OpenClaw 2026.4.11 and later. For deeper reference see TROUBLESHOOTING.md in this repo.

When to use

  • Agent returns empty output or times out
  • openclaw agent --agent <name> --message "..." hangs
  • Heartbeat dashboard shows the agent as stale
  • Model provider errors (429, 401, connection refused)
  • User says "openclaw is broken" / "agent is down" / "why is Orion not replying"

Instructions

Work through the checklist in order. Stop at the first failing step and report it — no need to run later steps until that's fixed.

1. Gateway health

openclaw agent --status
  • If the gateway is down, tell the user to run openclaw gateway restart.
  • If it reports "port 18789 in use by another process", find and kill the stale process (lsof -i :18789).

2. Tail recent logs

tail -n 200 ~/.openclaw/logs/gateway.log
tail -n 200 ~/.openclaw/agents/<name>/logs/agent.log

Grep for ERROR, PANIC, 401, 429, timeout. The first error in the tail is usually the real cause — everything after is fallout.

3. Heartbeat status

cat ~/.openclaw/agents/<name>/heartbeat.json
  • Check last_seen timestamp. More than 5 minutes old = worker crashed.
  • If status is starting for more than 60s, the agent is stuck in init (usually a bad SOUL.md or missing env var).

4. Session file integrity

ls -la ~/.openclaw/agents/<name>/sessions/sessions.json
  • If the file is >5 MB, sessions may be corrupt. Back it up and delete:
    mv ~/.openclaw/agents/<name>/sessions/sessions.json{,.bak}
    
  • If the JSON is invalid (python3 -m json.tool < sessions.json), same fix.

5. Model provider reachability

Read ~/.openclaw/agents/<name>/SOUL.md frontmatter to find the configured model and provider. Then:

Read the full file on GitHub · 110 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 110 lines · 71 tokens per session scan A ffaedf0533d7

Subscribe to this mod's changes

openclaw-debugger is a skill published in the GitHub repository mergisi/awesome-openclaw-agents (3,953 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 1,077 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.