agentmods.dev

story-architect-mcp: Skill for Claude Code

.agents/skills/novel-writer-assistant/SKILL.md

novel-writer-assistant is a skill for Claude Code, Codex from PTCuong-1102/story-architect-mcp. It costs 155 tokens per session (4,358 once invoked), scanned A, original, MIT.

A writing skill for planning novel arcs and pacing. An arc is a connected section of a story, while pacing is the speed and balance of action, dialogue, and description.

In plain words
What is it for?
It is for structuring arcs, planning scenes, setting action or description targets, analysing pacing and emotion, appending scenes, and viewing results in an HTML dashboard.
Why use it?
It helps turn a broad story idea into scenes with clear goals and conflicts, while checking that the story does not move too quickly or too slowly.

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 PTCuong-1102/story-architect-mcp's own configuration. It tells Claude Code and Codex how to work on story-architect-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 story-architect-mcp configures →

not rated 0repo changed 8d ago A scan 155 tokens original MIT
View source ↗ PTCuong-1102/story-architect-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to PTCuong-1102/story-architect-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/PTCuong-1102/story-architect-mcp/main/.agents/skills/novel-writer-assistant/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/PTCuong-1102/story-architect-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 novel-writer-assistant

README.md
[![agentmods](https://agentmods.dev/badge/skills/ptcuong-1102/story-architect-mcp/novel-writer-assistant/github.svg)](https://agentmods.dev/skills/ptcuong-1102/story-architect-mcp/novel-writer-assistant)
Your own site
<a href="https://agentmods.dev/skills/ptcuong-1102/story-architect-mcp/novel-writer-assistant"><img src="https://agentmods.dev/badge/skills/ptcuong-1102/story-architect-mcp/novel-writer-assistant/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 novel-writer-assistant

Your own site · 80×15
<a href="https://agentmods.dev/skills/ptcuong-1102/story-architect-mcp/novel-writer-assistant"><img src="https://agentmods.dev/badge/skills/ptcuong-1102/story-architect-mcp/novel-writer-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,358 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 $0.00155 $0.04358
Opus 5 $0.00077 $0.02179
Sonnet 5 $0.00031 $0.00872
Haiku 4.5 $0.00015 $0.00436

Measured 8d ago against content hash b442f294cc57, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

novel-writer-assistant 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 8d 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/novel-writer-assistant/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Novel Writer Assistant (Đồng Tác Giả & Biên Tập Viên Tiểu Thuyết Chuyên Nghiệp)

Kỹ năng này biến AI thành một Đồng Tác Giả & Biên Tập Viên Tiểu Thuyết Chuyên Nghiệp, vận dụng sức mạnh toàn diện của server story-architect-mcp v0.2.0 để sáng tác bản thảo trực tiếp, quản lý phân cảnh, theo dõi trạng thái nhân vật theo thời gian, giữ vững tính liên tục đa tuyến, kiểm soát nhịp độ, phân tích cảm xúc và tạo Dashboard trực quan sinh động.

🎯 NGUYÊN TẮC HOẠT ĐỘNG CỐT LÕI

  1. CONTINUITY & CHARACTER STATE TRACKING (Liên tục & Theo dõi nhân vật):

    • Trước khi bắt đầu phân cảnh hay chương mới, LUÔN LUÔN truy vấn dữ liệu dự án qua story_query_context, story_map_relationships và story_get_character_timeline.
    • Đảm bảo tính nhất quán về: Hồ sơ nhân vật (tính cách, ngoại hình, năng lực), vị trí địa lý, các mối quan hệ hiện tại, và trạng thái tâm lý/sức khỏe/vật phẩm sở hữu (story_track_character_state).

  2. RELATIONSHIP PROVENANCE & SHORTEST PATH (Nguồn gốc quan hệ & Đường đi liên kết):

    • Xác minh nguồn gốc quan hệ (Provenance): Phân biệt rõ các nhãn EXTRACTED (do tác giả/agent khẳng định), INFERRED (máy tự động suy ra từ tần suất cùng xuất hiện trong bản thảo), và LEGACY (dữ liệu cũ).
    • Thận trọng với quan hệ INFERRED: Không sử dụng các quan hệ mang nhãn INFERRED làm tiền đề cho các plot twist hoặc biến cố cốt truyện lớn mà chưa kiểm chứng lại với tác giả.
    • Truy vấn đường đi liên kết ngắn nhất: Khi cần kết nối 2 nhân vật chưa từng gặp mặt hoặc ở hai phe khác nhau, dùng story_query_context với tham số from và to để tìm ra chuỗi quan hệ trung gian logic nhất (Graph BFS Pathfinding).

  3. GOD-NODES & SOCIAL NETWORK BALANCE (Cân bằng mạng lưới xã hội & Nhân vật hạt nhân):

    • Chạy story_stats định kỳ để theo dõi top 5 "God-Nodes" (các nhân vật có độ bậc liên kết trung tâm cao nhất). Tránh việc dồn toàn bộ tương tác vào duy nhất một nhân vật khiến thế giới truyện mất đi tính đa chiều.

  4. SHOW, DON'T TELL (Tả cảnh & Hành động thay vì kể lể):

    • Tránh tóm tắt cảm xúc hay bối cảnh theo kiểu liệt kê thô (vd: "Anh ấy rất tức giận").
    • Thể hiện qua hành động cử chỉ, ánh mắt, phản ứng sinh lý, chi tiết môi trường và thoại nhân vật (vd: "Bàn tay anh xiết chặt lấy thành bàn, các khớp ngón tay trắng bệch...").

Read the full file on GitHub · 191 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. 8d ago Changed · +16 lines · +37 tokens per session b442f294cc57
  2. 11d ago First seen · 175 lines · 118 tokens per session scan A 21f3ae9629b1

Subscribe to this mod's changes

novel-writer-assistant is a skill published in the GitHub repository PTCuong-1102/story-architect-mcp (0 stars, last pushed 9d ago), licensed MIT. It adds 155 tokens to every session and 4,358 once invoked, about $0.0008 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.

Creative and mediaWriting and docs
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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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