AI agent

old-coder

An old coder's strategy for the agent era: don't read the code — make it run the gauntlet. Evidence-first development skill for coding agents, inspired by Uncle Bob.

Rank

#46 of 2,829

Stars

300★ +5/wk

On radar

since 2026-08-04

Why it's ranked

old-coder is an AI agent ranked #46 of 2,829 on the Cresting momentum radar, with a score of 63.1. It has 300 GitHub stars, +5 in the last 7 days, and has been tracked since 2026-08-04.

Every score decomposes into published factors, the same math for every tool, paid or not. Read the methodology →

Related ai agents

• hbg-classical-poem-silk-videoAgent Skill for turning Chinese classical poems into vertical Chinese-art videos with ImageGen stills, Docker I2V, calligraphy captions, retained ambience, BGM and final MP4 QA.#2 · 153★
• humanizer-cli33 ways to spot AI-written text, right in your terminal. Before/after examples, draft checker, zero dependencies.#3 · 570★
• skill-recorderDesktop app that records your on-screen work session and uses the GitHub Copilot CLI to reconstruct it as an intent + ordered steps, then builds a reusable Skill or Automation for Microsoft Scout, Microsoft Copilot Cowork, or Copilot Studio.#4 · 1,806★
• LongHorizon-HarnessThe long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.#5 · 175★
• nuphus-mcpDesktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protocol (stdio)#6 · 104★