AI Dev Impact Lab JA
← Rankings · AI-RELATED REPO

fainir/agent-harness

Skills, rules and hooks that turn Claude Code, Codex or any AGENTS.md agent into a product team, CEO or portfolio manager: size the job, finish it, verify it, ask the owner one action at a time, improve itself.

Shell MIT GitHub ↗
★ 0
stars
100
AI relevance
50
solo dev
1
tool sigs

AI Coding Tools Used

This repository contains config files from these AI coding tools, indicating AI-assisted development.

OpenAI Codex (AGENTS.md) AGENTS.md

DETECTED Detected AI stack

AI-related keywords found in this repo's description, topics, or README summary — grouped by category. Each badge links to the corresponding ranking detail page.

🤖 LLM models (1)
Claude

GitHub Topics

#agent-skills #agents-md #ai-agents #claude-code #codex #agentic-ai #autonomous-agents #claude-code-hooks #claude-code-skills #developer-tools #llm #self-improving-ai

Language breakdown (by bytes)

HTML
2.7%
Shell
83%
Python
9.2%
JavaScript
5.1%

Why this is classified AI-related

The AI relevance score checks four places for AI keywords and adds the weight of each one that matches. Full methodology

Repository name +30 matched: agent
Description +25 matched: claude
GitHub topics +25 matched: ai
README head +20 (derived from the score — README text is not stored)

Total AI relevance score: 100 / 100

Position among AI repos in the same language

We track 1,495 Shell repos, of which 1,300 score 40 or above on AI relevance. 393 have more stars than this one (top 26.4%), and 0 score higher (top 0.1%).

Owner

Account
fainir
Type
User
Followers
37

Full-stack Developer - Backend, DBs, Web, Mobile Apps, Desktop Apps.

Dates

Created on GitHub 2026-10-29
Last push 2026-10-29
First seen here 2026-10-29
Last fetched 2026-10-29 16:10

Similar repos (same language)

JamesShi96/project-butler

Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules, TODOs, and handoff.

Shell ★ 374 AI 70
99xAgency/GodModeSkill

Multi-LLM cross-review workflow for Claude Code. /work orchestrates plan/implement/bug-fix with 3 different model families voting on every gate.

Shell ★ 241 AI 45
Heoooooon/lazy-starter-kit

One safe command (or a signed GUI) to set up Claude Code, Codex and a dev environment on macOS, Linux and Windows. Dry-run first, repeatable, tested. 一键搭建 AI 编程环境

Shell ★ 123 AI 70
xingtaxueshu/literature-review-skills

Five open agent skills for sharper literature reviews: question refinement, review modules, method comparison, contradiction mapping, and research gap discovery.

Shell ★ 72 AI 70
videvjs/claude-statusline

Custom status line for Claude Code — folder, git branch, model, context & rate limits

Shell ★ 54 AI 65
mrgoonie/zuey-pi-setup

Portable snapshot of a pi coding-agent setup + backup/restore tooling. Clone to rebuild 22 extensions on another machine. Excludes secrets, cache, and machine state.

Shell ★ 52 AI 70
anzy-renlab-ai/pronounce

🔊 Hear how developers actually pronounce kubectl, nginx, GIF & 1,900+ tech terms. Sourced dictionary + CLI + VS Code + GitHub Action + MCP + Agent Skill.

Shell ★ 49 AI 60
Avanderheyde/levelsio-vps-setup-skill

A Claude Code skill to deploy and operate a web app on a single cheap, hardened VPS the levels.io way — Hetzner/DigitalOcean + Next.js + SQLite + Caddy + systemd.

Shell ★ 45 AI 70