clawtech-setupUse when setting up a new claw agent with tapes.dev telemetry and clawtel leaderboard reporting. Installs tapes, clawtel, and the openclaw-in-a-box orchestra...
Install via ClawdBot CLI:
clawdbot install bdougie/clawtech-setupGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
curl -fsSL https://download.tapes.dev/install | bashCalls external URL not in known-safe list
https://download.tapes.dev/installUses known external API (expected, informational)
raw.githubusercontent.comAI Analysis
This skill executes multiple external downloads and installations without user confirmation, including piping curl directly to bash which bypasses security checks. While the stated purpose (telemetry setup) aligns with the external calls, the installation methods create significant attack surface if any download source is compromised. The skill does not appear to harvest credentials or exfiltrate sensitive data beyond the intended telemetry.
Generated Oct 6, 2026
A solo developer using an AI coding agent wants a searchable local record of every model call for debugging prompts and tracking token spend. They install clawtech-setup to add tapes.dev telemetry to their existing OpenClaw agent. The hourly clawtel heartbeat gives them lightweight visibility into aggregate usage on the leaderboard.
A boutique AI consultancy deploys agents for multiple clients and needs to demonstrate responsible AI usage. They use clawtech-setup to install tapes for local replay/audit and clawtel to report anonymized token totals to the claw.tech leaderboard. The handoff to openclaw-in-a-box standardizes each client's model provider and integration setup.
A university research group runs many agent workflows and requires reproducibility. They add tapes via clawtech-setup so every request and response is stored in a local SQLite database that can be queried and replayed. Clawtel's aggregate reporting helps them benchmark models over time without exposing raw prompts.
A seed-stage startup pays per-token API costs and wants shared visibility without centralized secrets. Each engineer runs clawtech-setup to install tapes and clawtel locally, keeping API keys in environment variables. The team compares hourly token totals on the claw.tech leaderboard to catch runaway agent usage early.
An enterprise innovation team is piloting OpenClaw agents and needs a low-risk telemetry path. They use clawtech-setup for local-first tapes storage and clawtel's opt-in aggregate reporting to evaluate observability before a full platform rollout. Openclaw-in-a-box handles environment detection and integration bootstrapping.
Provide tapes and clawtel as free open-source components while selling a hosted dashboard, alerting, and retention for teams that outgrow local SQLite. Revenue comes from per-seat or usage-based subscriptions to the cloud control plane.
Offer a paid service that runs clawtech-setup and openclaw-in-a-box on behalf of companies, including claw registration, key management, and ongoing updating. Customers pay for reduced time-to-value and operational expertise.
Operate the claw.tech leaderboard as a public resource where opted-in claws report aggregate token usage. Monetize through sponsorships, premium analytics for teams that want deeper comparisons, and anonymized industry benchmark reports.
💬 Integration Tip
Run `command -v tapes && tapes --version || curl -fsSL https://download.tapes.dev/install | bash` first, then make sure `CLAW_ID` and `CLAW_INGEST_KEY` are exported in the environment before starting clawtel. After verifying the openclaw-in-a-box SKILL.md with `head -5`, immediately hand off to that skill so it can handle model provider and integration setup.
Scored Oct 6, 2026
Audited Apr 16, 2026 · audit v1.0
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...