openclaw-debugging
Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code, including fetching stored sessions, transcripts, and attachments as evidence.
Install caution
Risk: High
Source: OpenClaw Built-in Skills
Path: .agents/skills/openclaw-debugging/SKILL.md
Review flags: browser/session access, filesystem/home-directory access, network access or external URLs, shell command snippets. These are review signals, not definitive security judgments; inspect before installing.
Required permissions
- • Shell commands
- • Network/API usage
- • Filesystem/home access
- • Browser/session access
Permissions are inferred from SKILL.md text only. They are review prompts, not guarantees about runtime behavior.
Risk flags explained
Mentions browser automation, cookies, sessions, local storage, or browser state.
Mentions filesystem writes, deletes, home-directory paths, or config/key locations.
Mentions external URLs, network APIs, downloads, or HTTP client usage.
Contains shell command snippets. Review commands before copy/paste or agent execution.
Score explanation
Trust
- • Trust starts at 90 before review-signal penalties and metadata bonuses.
- • Risk-signal penalty: -43 from 4 detected flag(s).
- • Metadata bonus: +2 from author/version/description fields.
Utility
- • Utility starts at 55 and rewards clear descriptions, runnable examples, and explicit setup needs.
- • Description present: yes.
- • Command examples detected: 15.
- • Environment variables detected: 0.
Momentum
- • Momentum starts at 45 and uses public repo activity signals.
- • Recent commit activity: latest repo update was 0 day(s) ago.
- • Recent commit volume: 100 commit(s) in the lookback window (+20).
- • Source has strong public adoption: 390331 stars.
- • Fork activity suggests reuse: 82114 forks.
Overall
- • Overall score weights trust 45%, utility 35%, and momentum 20%.
Detected signals
Env vars
None detected in SKILL.md text scan.
Commands
- • $openclaw-testing
- • /home/openclaw/.openclaw/...
- • OPENCLAW_DEBUG_MODEL_PAYLOAD=full-redacted OPENCLAW_DEBUG_SSE=peek openclaw gateway
- • OPENCLAW_DEBUG_MODEL_PAYLOAD=tools OPENCLAW_DEBUG_SSE=events openclaw gateway
- • OPENCLAW_DEBUG_MODEL_TRANSPORT=1 openclaw gateway
- • find / -maxdepth 6 -name openclaw-agent.sqlite
- • node -e 'const {DatabaseSync}=require("node:sqlite");
- • node:sqlite
- • openclaw logs
- • openclaw logs --follow
- • openclaw sessions export-trajectory
- • openclaw sessions list --agent <agentId> --json
URLs
- • https://docs.openclaw.ai/cli/sessions
Provenance & evidence
SkillRadar makes each review traceable back to the exact source path, source blob SHA, scanner version, and text-only policy that produced the report.
Evidence snippets
…ecting a remote host over SSH, or you need event-level detail): - Per-agent data plane: `~/.openclaw/agents/<agentId>/agent/openclaw-agent.sqlite`. Canonical schema: `src/state/op…
…lt Loop 1. State the suspected boundary: config, tool construction, provider payload, fetch, stream/SSE, transcript replay, worker/runtime, package/dist, or CI. 2. Add or enable the…
…## Fetching Sessions and Transcripts Use these paths when a bug report references a chat session and you need the actual transcript, sender attribution, or attachments as evidence. CLI…
…env flags instead of global debug when the model request shape or stream timing matters: ```bash OPENCLAW_DEBUG_MODEL_TRANSPORT=1 openclaw gateway OPENCLAW_DEBUG_MODEL_PAYLOAD=tools OPEN…
Watch this skill
Get alerted when this skill adds credential requirements, shell commands, external domains, remote installer patterns, or risk-level changes.
Join watchlist betaMethodology note
SkillRadar scans SKILL.md as hostile text only. It does not execute commands, install packages, or load third-party skills.