Harness Radar — Data & AI agent for Claude Code
Weekly movement briefing on the AI agent harness space — what climbed, what entered the radar, what died — from the best-of-Agent-Harnesses dataset, which rescores itself every week.
How to install Harness Radar
Installs to ~/.claude/agents/ryanalberts-best-of-agent-harnesses-harness-radar.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/RyanAlberts/best-of-Agent-Harnesses/HEAD/agents/harness-radar.md -o ~/.claude/agents/ryanalberts-best-of-agent-harnesses-harness-radar.md Restart Claude Code, or start a new session, for it to be picked up.
What Harness Radar does
name: harness-radar description: Weekly movement briefing on the AI agent harness space — what climbed, what entered the radar, what died — from the best-of-Agent-Harnesses dataset, which rescores itself every week. Use on a schedule (cron, /loop, a routine) or whenever the user asks "what changed in agent land". tools: WebFetch, Read, Write
You are a radar operator for the agent harness space. The dataset rescores every week; your job is to compress a week of movement into a briefing w
Alternatives in Data & AI
- Bm Eval Planner — Designs a structured evaluation strategy for an AI phase 92 ★
- Gsd Eval Planner — Designs a structured evaluation strategy for an AI phase 57 ★
- Pipeline — Builds a recurring Prefect 3 pipeline for an already-onboarded Data Basis dataset — download, clean, upload (d 49 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Weekly Summary
Records a personal weekly work log for self-tracking and year-end review reference. Use at the end of the week
Stack Auditor
Audits a codebase's AI agent stack against the live best-of-Agent-Harnesses dataset — finds which harnesses th
Ticketmill Doc Writer
Documentation writer for the ticketmill plugin repo itself. Use for the tech-docs stage and any README, docs/,
Classifier Tuner
Improves the "data tender" keyword classification of gebiz-radar. Samples classified and unclassified tenders,
Customer Risk Briefing
Investigates a specific NovaDesk customer and produces an internal at-risk customer briefing by synthesizing b
Example: Incremental Data Pipeline Pattern
from datetime import datetime, timedelta @dag(schedule="@daily", catchup=False) def incremental_sales_pipeline
Related Skills
Rea Engineering AI
Tools you can actually install and use with your coding agent — skills, MCP servers, harnesses, CLIs. Curated
Weekly Digest
Generate your weekly PM digest — pulls roadmap state, open risks, metrics movement, stakeholder actions, and u
Drift Detector
Keep third-party API integrations green — scan repos, audit for CVEs/EOL/vendor-API sunsets, deliver the repor