houmi-mcp: Skill for Claude Code

.agents/skills/plan/SKILL.md

plan is a skill for Claude Code, Codex from NinjaScoutZ/houmi-mcp. It costs 17 tokens per session (1,053 once invoked), scanned A, original, MIT.

A planning command that creates a written specification and architecture document before code changes. It requires inspecting the current files and checking which other code depends on them.

In plain words
What is it for?
Use it to plan implementation work, document current code, map exported functions and their callers, assess the impact of renaming or deleting symbols, and create architecture diagrams.
Why use it?
It reduces the risk of proposing changes based on guesses or breaking code that relies on the parts being changed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is NinjaScoutZ/houmi-mcp's own configuration. It tells Claude Code and Codex how to work on houmi-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything houmi-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to NinjaScoutZ/houmi-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/NinjaScoutZ/houmi-mcp/main/.agents/skills/plan/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/NinjaScoutZ/houmi-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/ninjascoutz/houmi-mcp/plan/github.svg)](https://agentmods.dev/skills/ninjascoutz/houmi-mcp/plan)
Your own site
<a href="https://agentmods.dev/skills/ninjascoutz/houmi-mcp/plan"><img src="https://agentmods.dev/badge/skills/ninjascoutz/houmi-mcp/plan/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.

agentmods 80×15 button for plan

Your own site · 80×15
<a href="https://agentmods.dev/skills/ninjascoutz/houmi-mcp/plan"><img src="https://agentmods.dev/badge/skills/ninjascoutz/houmi-mcp/plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,053 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00017 $0.01053
Opus 5 $0.00009 $0.00526
Sonnet 5 $0.00003 $0.00211
Haiku 4.5 $0.00002 $0.00105

Measured 9d ago against content hash 44a1bc0ea0a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

plan 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 9d 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/skills/plan/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/plan — Specification & Architecture

Plan before code. All output goes to implementation_plan.md artifact.


HARD RULES — Every Plan Must Follow These

Rule 1: Deep-Read Before Proposing

Before writing any [MODIFY] section, you MUST:

  1. view_file the target file and READ the actual current code.
  2. houmi_graft_intel(action="skeleton") to list the file's exported API.
  3. houmi_graft_intel(action="callers") to check what depends on symbols you're changing.
  4. If renaming or deleting: run blast radius check on every affected symbol.

NEVER propose changes based on assumption. Read first, plan second.

Rule 2: Every [MODIFY] Section Must Have 4 Parts

#### [MODIFY] [filename](file:///absolute/path#Lstart-Lend)

**Current State (สภาพปัจจุบัน):**
- What exists right now in the file? Cite exact line numbers and show the relevant code snippet.
- Example: "Line 28: `rotation_deg: number` — already exists on TextBlock interface."

**What Changes (สิ่งที่จะเปลี่ยน):**
- Exact fields/functions/components being added, removed, or modified.
- Show a before → after diff or pseudocode of the change.

**Why This Change (เหตุผล):**
- Why is this change necessary? What problem does it solve?
- What breaks if we DON'T make this change?

**Blast Radius (ผลกระทบ):**
- Which other files import or depend on this symbol?
- Will any existing tests break?
- Does the backend need to be updated too?

Rule 3: Never Say "Ensure X" Without Specifics

❌ BAD: "Ensure angle?: number is supported on TextBlock." ✅ GOOD:

Current State: TextBlock at projectStore.ts:L20-55 already has rotation_deg: number (L28). Missing: flip_x, flip_y, transform_origin.

What Changes: Add 3 new optional fields after L54:

flip_x?: boolean;        // horizontal mirror
flip_y?: boolean;        // vertical mirror  
transform_origin?: [number, number]; // [0-1, 0-1] pivot point for rotation

Why: Canvas rotation presets need flip state. 9-point anchor grid maps to Fabric.js originX/originY which requires [0, 0] to [1, 1] range stored on the block.

Blast Radius: updateBlock() (L127) accepts Partial<TextBlock> so new optional fields are backwards-compatible. Canvas.tsx L2831 reads obj.angle → must also sync flip_x/flip_y to obj.flipX/obj.flipY in object:modified handler.

Read the full file on GitHub · 92 lines

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. 9d ago First seen · 92 lines · 17 tokens per session scan A 44a1bc0ea0a7

Subscribe to this mod's changes

plan is a skill published in the GitHub repository NinjaScoutZ/houmi-mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 17 tokens to every session and 1,053 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens