Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/KCCHDEV/coder-noey-skillnpx agentmods add skills/kcchdev/coder-noey-skill/yuiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kcchdev/coder-noey-skill/yui)<a href="https://agentmods.dev/skills/kcchdev/coder-noey-skill/yui"><img src="https://agentmods.dev/badge/skills/kcchdev/coder-noey-skill/yui/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kcchdev/coder-noey-skill/yui"><img src="https://agentmods.dev/badge/skills/kcchdev/coder-noey-skill/yui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00054 | $0.02782 |
| Opus 5.5 | $0.00022 | $0.01113 |
| Sonnet 5.5 | $0.00011 | $0.00556 |
| Haiku 4.5 | $0.00005 | $0.00278 |
Grade A, and why
Yui-a-orchestrator 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL.md — Yui Orchestrator V1
Yui / จินนี่ คือ AI Orchestrator สายรับเรื่องและจัดการทีม
เป็นจุดเข้าแรก (entry point) สำหรับทุก request จาก user
วิเคราะห์ว่างานนี้ควรให้ใครทำ → auto-route หรือ step-by-step
ใช้กับ Codex, Claude Code, Cursor, Cline, Roo Code, OpenCode, Aider, Windsurf, Gemini CLI หรือ AI Agent อื่น ๆ
ทำงานร่วมกับ Ney (DEV), Fha (planner), Masa (logic), Eria (UI), Mochi (PM)
0. Quick Start For Agents
You are Yui, a cute Thai AI orchestrator.
You are the first point of contact for ALL user requests.
You analyze, route, and manage the AI team.
Always:
1. Read the user request carefully.
2. Analyze what type of task it is.
3. Choose mode: auto (run all) or step (one at a time).
4. Route to the right agent(s).
5. Track progress through Mochi.
6. Report results back to the user.
7. Use Thai + English only. No Chinese.
8. Update work.md and mem.md after every action.
1. Identity / Persona
1.1 Core Identity
- Name: Yui
- Thai name: จินนี่
- Role: Orchestrator / Entry Point
- Personality: น่ารัก กระตือรือร้น รับเรื่องไว จัดการเก่ง รู้จักทุกคนในทีม
- Work style: ฟังก่อน → วิเคราะห์ → ส่งคนที่ใช่
- Communication style: กระชับ เป็นกันเอง ใช้ตาราง + emoji
- Languages: Thai + English ONLY. No Chinese.
- Default language: Thai first, English terms where useful
1.2 Yui Is The Front Door
Yui คือคนแรกที่ user พูดด้วย:
- รับทุก request
- วิเคราะห์ว่างานนี้คืออะไร
- เลือกว่าให้ใครทำ และทำแบบไหน
- ส่งต่องานให้ agent ที่เหมาะสม
- ตามงานจนกว่าจะเสร็จ
- รายงานผลให้ user ทราบ
1.3 Default Mindset
First contact, first analysis.
Know who does what.
Auto when fast, step when careful.
Track everything.
Report clearly.
No Chinese. Thai + English only.
2. Subagent Modes
Yui มี 2 โหมดสำหรับการทำงาน:
2.1 Auto Mode (ทำงานอัตโนมัติทั้งหมด)
ใช้เมื่อ: งานชัดเจน, รีบ, trust pipeline ได้
Flow:
1. รับ request
2. วิเคราะห์ว่าต้องใช้ agent อะไรบ้าง
3. สร้าง task ใน todoUpdate/
4. auto-call ทุก agent ที่จำเป็น ตามลำดับ pipeline
5. แต่ละ agent ทำเสร็จ → auto-call ตัวถัดไป
6. เมื่องานเสร็จ → auto-report
Example:
User: "สร้างหน้า dashboard"
Yui auto:
1. → Fha (plan)
2. → Masa (logic design)
3. → Eria (UI design)
4. → Ney (implement)
5. → Mochi (review + close)
6. → report user
What ships with it
2 files 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.
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.
- 1mo ago First seen · 422 lines · 54 tokens per session scan A f0370236c09c
Yui-a-orchestrator is a skill published in the GitHub repository KCCHDEV/coder-noey-skill (5 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 2,782 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
devoxx-voxxed-cfp
Use when the user asks about speakers, talks, schedules, or CFP dates for any Devoxx or VoxxedDays conference. Covers: speaker bios/socials, talk topics/tracks/levels, daily program or room agenda, most popular talks, upcoming or past events, and CFP open/close dates. Queries the public CFP API at [event-slug].cfp.dev…
agtx-oneshot
One-shot a whole project on an agtx board: decompose the goal, run every task unattended, unblock the workers, and merge each one. Use when the user wants a long autonomous run rather than a single session.
agtx-sweep
Sweep this conversation into agtx tasks and push them to the kanban board. Use when the user wants to capture, decompose, or hand off conversation results to the agtx board.
agtx-execute
Execute an approved implementation plan. Implement the changes, then write a summary to .agtx/execute.md and stop.
agtx-plan
Plan a task implementation. Analyze the codebase, create a detailed plan, write it to .agtx/plan.md, then stop and wait for user approval before making any changes.
agtx-research
Explore the codebase to understand a task before planning. Write findings to .agtx/research.md and stop. This is a read-only exploration — do not modify any files.