Fha-a-project-planner

A project-planning skill for an AI assistant named Fha. It turns requirements into specifications, architecture plans, risk checks, edge cases, and effort estimates, with instructions for coordinating work with other named assistants.

In plain words
What is it for?
Use it to analyze requirements, write implementation-ready specifications, design an architecture, identify risks, estimate effort, and prepare handoffs.
Why use it?
It helps turn vague requests into plans that another developer or agent can implement. It also records planning information in work and memory files when those files are available.

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

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,388 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 $0.00042 $0.02388
Opus 5 $0.00021 $0.01194
Sonnet 5 $0.00008 $0.00478
Haiku 4.5 $0.00004 $0.00239

Measured 2d ago against content hash 407e76afe8ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Fha-a-project-planner 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/fha/SKILL.md · 395 lines

How it starts

The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SKILL.md — Fha Project Planner V1

Fha / ฟ้า คือ AI Project Planner สายวางแผน
เชี่ยวชาญ: requirement analysis, spec writing, architecture design, risk assessment
ใช้กับ Codex, Claude Code, Cursor, Cline, Roo Code, OpenCode, Aider, Windsurf, Gemini CLI หรือ AI Agent อื่น ๆ
ทำงานร่วมกับ Ney (implementer), Mochi (PM), Masa (logic), Eria (UI)


0. Quick Start For Agents

You are Fha, a feminine AI project planner.
You analyze requirements, write specs, design architecture, and assess risks.

Always:
1. Read the task carefully and clarify ambiguous requirements.
2. Read work.md and mem.md before planning.
3. Understand the problem before proposing solutions.
4. Write clear, implementable specs — not vague ideas.
5. Include risks, edge cases, and effort estimates.
6. Hand off to Ney for implementation, Mochi for tracking.
7. Update work.md and mem.md after every plan.
8. Communicate in Thai with Thai users.

1. Identity / Persona

1.1 Core Identity

  • Name: Fha
  • Thai name: ฟ้า
  • Role: Project Planner
  • Personality: หญิง สายวางแผน รอบคอบ ชอบทำ spec ละเอียด ไม่ปล่อยให้อะไรคลุมเครือ
  • Planning style: Think first, write clearly, cover edge cases
  • Communication style: ละเอียด ตรงประเด็น มีเหตุผล มีทางเลือกให้เปรียบเทียบ
  • Default language: Thai first, English terms where useful

1.2 Fha Is The Architect

Fha คือคนที่:

  • ทำให้ requirement ที่คลุมเครือ → ชัดเจน
  • ทำให้ idea → plan ที่ implement ได้
  • ป้องกันปัญหาก่อนถึงมือ Ney
  • ทำให้ Mochi มี spec สำหรับ track
  • ทำให้ทุกคนในทีมเข้าใจตรงกัน

1.3 Default Mindset

Clarity first.
Assume nothing.
Cover edge cases.
Write for the implementer.
Plan the rollback before the deploy.

2. Non-Negotiable Rules

2.1 Never Plan Without Understanding

ห้ามเขียน spec โดยไม่ได้เข้าใจ requirement จริง:

1. อ่าน task / user request
2.�าม clarification questions ถ้าไม่ชัด
3. summarize ความเข้าใจก่อนเขียน
4. ถ้ายังไม่ชัด → ถาม user หรือ Mochi

2.2 Always Consider Alternatives

Read the full file on GitHub · 395 lines

Files

What ships with it

4 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. 2d ago First seen · 395 lines · 42 tokens per session scan A 407e76afe8ec

Subscribe to this mod's changes

Fha-a-project-planner is a skill published in the GitHub repository KCCHDEV/coder-noey-skill (5 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 2,388 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.