clawdocDiagnose OpenClaw agent failures, cost spikes, and performance issues with 14 pattern detectors. Use when: task failed unexpectedly, costs seem high, agent b...
Install via ClawdBot CLI:
clawdbot install ashishjaingithub/clawdocGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
exec (Accesses system directories or attempts privilege escalation
/var/log/Calls external URL not in known-safe list
https://github.com/openclaw/clawdoc/actions/workflows/ci.yml/badge.svgAudited Apr 17, 2026 · audit v1.0
Generated Oct 7, 2026
An AI agent built for customer support starts failing tasks and burning tokens at an alarming rate. The Clawdoc skill scans session logs, detects the infinite retry loop and model routing waste patterns, and produces a ranked prescription with the exact cost impact.
A SaaS company runs nightly AI cron jobs for report generation and monitoring. Costs quietly triple over a month due to cron context accumulation. Clawdoc's cross-session history analysis flags the growing inputTokens and prescribes model downgrades and context trimming.
A dev-tools company's autonomous coding agent begins re-reading files and wandering directories after context compaction. Clawdoc detects the task drift and compaction damage patterns, quantifies wasted tokens, and prescribes prompt and workspace fixes.
A large e-commerce company operates hundreds of OpenClaw agents for personalization and order support. The ops team runs Clawdoc's brief mode every morning to get a one-line telemetry summary and acts on any warnings before they become outages or budget overruns.
A fintech firm needs to prove its AI agents are cost-efficient and reliable for regulatory review. Clawdoc's full diagnosis mode generates an evidence-backed report showing healthy sessions, cost breakdowns, and root causes for every failure, which is stored in the compliance knowledge base.
The core Clawdoc scripts are open source and free to run locally, while a hosted dashboard provides team-wide session aggregation, alerting, and scheduled health checks. This drives adoption from developers and converts teams that need centralized visibility.
Clawdoc is offered as a metered service within a broader AI observability product. Customers pay only for the volume of session data analyzed, making it attractive for variable workloads and large fleets.
A done-for-you service where Clawdoc experts run audits on customer agent fleets, deliver remediation reports, and implement config changes for a share of the verified savings. It targets enterprises with significant AI spend but no dedicated AI ops team.
💬 Integration Tip
Set CLAWDOC_LEARNINGS=1 to pipe findings into your .learnings/LEARNINGS.md and turn diagnosis into persistent agent improvements; for cron monitoring, schedule the brief mode with headline.sh --brief and pair it with jq for alerting on cost thresholds.
Scored Oct 7, 2026
Firecrawl CLI for web scraping, crawling, and search. Scrape single pages or entire websites, map site URLs, and search the web with full content extraction. Returns clean markdown optimized for LLM context. Use for research, documentation extraction, competitive intelligence, and content monitoring.
Incident Commander Skill
Monitors OpenClaw cron job health, identifies failures, timeouts, and delivery issues.
Observability Designer (POWERFUL)
Use when defining SLIs/SLOs, managing error budgets, or building reliable systems at scale. Invoke for incident management, chaos engineering, toil reduction, capacity planning.
QQ bot integration for OpenClaw with session isolation, logging, and AI auto-reply. Supports private chat and group @messages.