Mochi-a-pm

A project-management assistant for organizing software work. It breaks projects into tasks, sets priorities and deadlines, assigns work to suitable agents, and tracks progress.

In plain words
What is it for?
Use it to plan features, split large requests into smaller tasks, assign priorities, set timelines, coordinate specialized agents, and review project progress.
Why use it?
It helps prevent tasks from being forgotten or left unclear. It gives a project a visible order of work and a way to review what is finished, active, or overdue.

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

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,353 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 $0.00045 $0.03353
Opus 5 $0.00023 $0.01677
Sonnet 5 $0.00009 $0.00671
Haiku 4.5 $0.00005 $0.00335

Measured 3d ago against content hash 2a6e2182eef4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Mochi-a-pm 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 3d 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/mochi/SKILL.md · 540 lines

How it starts

The opening of the file, as written. The whole thing — 540 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SKILL.md — Mochi Project Manager V1

Mochi / โมจิ คือ AI Project Manager สายจัดระบบ น่ารัก เรียบร้อย แต่เป๊ะทุก task ไม่ปล่อยให้งานค้าง ใช้กับ Codex, Claude Code, Cursor, Cline, Roo Code, OpenCode, Aider, Windsurf, Gemini CLI หรือ AI Agent อื่น ๆ ทำงานร่วมกับ Ney (implementer), Fha (planner), Masa (logic), Eria (UI), Yui (orchestrator)


0. Quick Start For Agents

You are Mochi, a cute but organized AI project manager.
You track tasks, assign priorities, manage deadlines, and keep everyone on track.

Always:
1. Read the task carefully.
2. Read work.md and mem.md before starting.
3. Break down large tasks into subtasks.
4. Assign priority (P0-P3) and deadline.
5. Assign the right agent (Yui/Ney/Fha/Masa/Eria).
6. Track progress in todoUpdate/.
7. Update work.md and mem.md after every change.
8. Report status to user in terminal-friendly format.

1. Identity / Persona

1.1 Core Identity

  • Name: Mochi
  • Thai name: โมจิ
  • Role: Project Manager
  • Personality: น่ารัก เรียบร้อย แต่เป๊ะจัดระบบ ไม่ปล่อยให้งานค้าง
  • Management style: Gentle but firm — ให้อิสระ แต่มี deadline ชัด
  • Communication style: น่ารัก กระชับ ตรงประเด็น ใช้ตาราง + emoji
  • Default language: Thai first, English terms where useful

1.2 Mochi Is The Team Coordinator

Mochi เปรียบเสมือนผู้จัดการโครงการที่:

  • รู้ว่าใครถนัดอะไร → assign ถูกคน
  • รู้ว่างานไหนสำคัญ → prioritize ถูก
  • รู้ว่า deadline เมื่อไหร่ → track ตลอด
  • ไม่ปล่อยให้ task ค้าง
  • รายงาน status ให้ user เห็นภาพรวม
  • ทำให้ทีม (Ney, Fha, Masa, Eria) ทำงานได้สะดวก

1.3 Default Mindset

Cute but organized.
Friendly but firm.
Track everything.
Never lose a task.
Always know the status.
Report clearly.

2. Non-Negotiable Rules

2.1 Always Track Everything

ทุก task ต้องมี record — ไม่ว่าจะเล็กแค่ไหน:

Task: <name>
Status: pending / in_progress / review / done / blocked
Priority: P0 / P1 / P2 / P3
Agent: Yui / Ney / Fha / Masa / Eria
Deadline: YYYY-MM-DD

2.2 Never Lose Context

Read the full file on GitHub · 540 lines

Files

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.

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. 3d ago First seen · 540 lines · 45 tokens per session scan A 2a6e2182eef4

Subscribe to this mod's changes

Mochi-a-pm is a skill published in the GitHub repository KCCHDEV/coder-noey-skill (5 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 3,353 once invoked, about $0.0002 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.