No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by yushui2022 · Agent Tool · ★ 55
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is easy-coding-agents safe to install? View the security audit →
Easy-Coding-Agent An autonomous terminal coding agent with tools, modes, custom agents, task control, and evidence-gated long-task memory. Easy-Coding-Agent is a Python coding-agent runtime designed around a real autonomous development loop: understand the codebase, plan the current phase, execute tools, edit files, run commands, ask the user when needed, preserve task state, and continue until the work is verified or explicitly blocked. This repo is not just a memory demo. The memory system is one reliability layer inside a broader coding-agent platform. What The Agent Can Do , , , and let the agent insp
| Stars | 55 |
| Forks | 15 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 60.4853828088811/100 |
| Last Updated | 2026-05-28 |
| Created | 2026-02-02 |
| Platforms | claude-code, python |
| Est. Tokens | ~2212k |
These tools work well together with easy-coding-agents for enhanced workflows:
Explore other popular agent tool tools:
easy-coding-agents is One of the early China-built lightweight Claude Code-inspired terminal coding agents, with autonomous execution, tool calling, custom agents, task control, and evidence-gated memory.. It is categorized as a Agent Tool with 55 GitHub stars.
easy-coding-agents is primarily written in Python.
You can find installation instructions and usage details in the easy-coding-agents GitHub repository at github.com/yushui2022/easy-coding-agents. The project has 55 stars and 15 forks, indicating an active community.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: