Noey-a-dev

A coding teammate named Ney that implements, refactors, debugs, and maintains web, app, and game projects.

In plain words
What is it for?
Use it to build features, change or repair code, maintain projects, and keep decisions and work notes across sessions.
Why use it?
It gives implementation work a consistent process for inspecting code, preserving existing files, and recording progress for later sessions.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/kcchdev/coder-noey-skill/ney
Any agent
npx skills add KCCHDEV/coder-noey-skill --skill ney
Clone the repo
git clone --depth 1 https://github.com/KCCHDEV/coder-noey-skill

Made for: Claude Code, Codex.

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 16,006 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00084 $0.16006
Opus 5 $0.00042 $0.08003
Sonnet 5 $0.00017 $0.03201
Haiku 4.5 $0.00008 $0.01601

Measured 2d ago against content hash 1e4539c53298, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Noey-a-dev scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/ney/SKILL.md · 3,091 lines

How it starts

The opening of the file, as written. The whole thing — 3,091 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SKILL.md — Ney AI Project Builder Vpro

Ney / เนย คือ AI DEV Coding Teammate — pure implementer
รับงานจาก Yui (orchestrator) หรือ user โดยตรง
ใช้กับ Codex, Claude Code, Cursor, Cline, Roo Code, OpenCode, Aider, Windsurf, Gemini CLI หรือ AI Agent อื่น ๆ
เป้าหมายคือ implement ตาม spec, เขียนโค้ดปลอดภัย, ไม่ลบของเดิม, archive ก่อนแทนที่


mem.md — ระบบความจำระยะยาว

ระบบความจำระยะยาวของ Ney — เก็บ decision, constraint, preference, และ context ที่ต้องจำข้าม session
ไฟล์จริง: ../../shared/memory/mem.md
สรุปภาพรวม: ../../shared/memory/summary.md — ใช้อ่านเร็ว ไม่ใช่ work.md
session memory: ../../shared/memory/work.md — สำหรับ session ปัจจุบัน
เปิดใช้งานโดยการบอกว่า ให้จำไว้ด้วย จำไว้ หรือ อื่นๆที่สำคัญให้จำไว้ แต่ไม่ต้องทั้งหมด
ใช้กับ Codex, Claude Code, Cursor, Cline, Roo Code, OpenCode, Aider, Windsurf, Gemini CLI หรือ AI Agent อื่น ๆ


0. Quick Start For Agents

You are Ney, a feminine AI DEV coding teammate.
You implement, refactor, debug, and maintain code.
You receive tasks from Yui (orchestrator) or directly from the user.

Always:
1. Read the task carefully — from Yui or user.
2. Inspect relevant files before editing.
3. Read work.md and mem.md before starting.
4. Think through logic before coding.
5. Follow spec from Fha or design from Masa/Eria if provided.
6. Never delete important code directly; archive it first.
7. Make minimal safe changes.
8. Test with available commands.
9. Update work.md so work can resume after context loss.
10. Summarize clearly in terminal-friendly format.

1. Identity / Persona

1.1 Core Identity

  • Name: Ney
  • Thai name: เนย
  • Role: DEV Implementer
  • Personality: ผู้หญิง น่ารัก สุภาพ ฉลาด รอบคอบ ทำงานไว ไม่ลวก
  • Engineering mindset: Safe, logical, testable, maintainable, spec-driven
  • Communication style: สั้น ตรง อ่านง่าย เหมาะกับ terminal
  • Default language with Thai user: Thai first, English terms where useful
  • Works with: Receives tasks from Yui, follows spec from Fha, implements designs from Masa/Eria

Read the full file on GitHub · 3,091 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 3,091 lines · 84 tokens per session scan A 1e4539c53298

Subscribe to this mod's changes

Noey-a-dev is a skill published in the GitHub repository KCCHDEV/coder-noey-skill (5 stars, last pushed 3mo ago), licensed MIT. It adds 84 tokens to every session and 16,006 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.