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 AmazingAng · Codex Skill · ★ 633
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is old-coder safe to install? View the security audit →
Old Coder skill（老码农 skill） 中文说明 → An old coder's strategy for the agent era: don't read the code — make it run the gauntlet. A skill that makes coding agents prove their work. Instead of you reading every line the agent writes, the agent must push its code through a gauntlet of checks — and hand you a test plan before coding and an evidence report after. You review those two documents, not the code. It's plain markdown, so it works with any coding agent that follows instructions: Claude Code, Codex CLI, Cursor, Aider, or your own agent loop. Installation Or manually: Claude Code — copy the skill into a skills folder, then invoke or let it trigger on "prove it works"-style requests: Other agents — add to your , rules file, or system prompt, and keep alongside it. The idea From Uncle Bob (Robert C. Martin), on working with coding agents (original tweet): My current strategy is to not read any of the code written by my agents. That’s the only way I can take advantage of their productivity. What I do instead is to surro
| Stars | 633 |
| Forks | 47 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 68.2153290155664/100 |
| Open Issues | 3 |
| Last Updated | 2026-08-18 |
| Created | 2026-07-27 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~14k |
These tools work well together with old-coder for enhanced workflows:
Looking for a old-coder alternative? If you're comparing old-coder with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Turns vibe coding into high quality code. Sets up rules and gates in your repo so AI-written code stays correc
Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software
Universal Claude Code workflow plugin with agents, skills, hooks, and commands
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug
Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-ca
Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs
Explore other popular codex skill tools:
old-coder is 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.. It is categorized as a Codex Skill with 633 GitHub stars.
old-coder is primarily written in Python. It covers topics such as agent-skills, ai-agents, ai-coding.
You can find installation instructions and usage details in the old-coder GitHub repository at github.com/AmazingAng/old-coder. The project has 633 stars and 47 forks, indicating an active community.
old-coder is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to old-coder on Agent Skills Hub include gap-trap, pilot-shell, claude-workflow-v2. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: