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.
npx agentmods add skills/thtskaran/claude-skills/worldbuilder-writingnpx skills add thtskaran/claude-skills --skill worldbuilder-writinggit clone --depth 1 https://github.com/thtskaran/claude-skillsWrote 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/thtskaran/claude-skills/worldbuilder-writing)<a href="https://agentmods.dev/skills/thtskaran/claude-skills/worldbuilder-writing"><img src="https://agentmods.dev/badge/skills/thtskaran/claude-skills/worldbuilder-writing.svg" alt="Measured on agentmods" 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 | $0.00182 | $0.04987 |
| Opus 5 | $0.00091 | $0.02493 |
| Sonnet 5 | $0.00036 | $0.00997 |
| Haiku 4.5 | $0.00018 | $0.00499 |
Grade A, and why
worldbuilder-writing 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 6d 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 — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Worldbuilder's Writing System
Core Premise
Writing is not self-expression. Writing is applied psychology.
You are not putting your thoughts into words. You are engineering a specific desired experience in the mind of another person. The words are not the point. The effect the words have on the reader is the point.
Most people focus on transmission — what they want to say. Masters focus on reception — what people hear.
This distinction is everything. From this point forward, you do not care about what you want to say. You care about what people will hear, believe, feel, and do.
PHASE 0: BEFORE YOU WRITE A SINGLE WORD
0.1 — Identify the Target Mind
Before anything else, answer these questions. Do not skip them. Do not assume you know.
- Who exactly is reading this? Not demographics. Their psychology. What do they believe about themselves? What world do they live in? What language do they use? What do they want to be true?
- What is their deepest desire or fear related to this topic? Not their stated need — their psychological need. A startup founder doesn't need an engineer. They need validation that their mission attracts obsessive talent. A hiring manager doesn't need a resume. They need confidence that this person won't waste their time.
- What does this person already agree with? These are your entry points. Your atomic units.
- What would make them stop reading? These are the immune triggers. The things their brain will reject.
- What is the ONE thing you want them to believe/do after reading? Not five things. One.
0.2 — Understand the Reader's World
Every person lives inside a world — a set of beliefs, language, values, status hierarchies, and shared references. You must understand this world BEFORE you write.
Ask yourself:
- What in-group language does this audience use? (e.g., startup people say "GTM" not "marketing", "lean team" not "small team", "conviction" not "confidence")
- What are the shared myths of this group? (e.g., YC culture fetishizes the "cracked engineer who lives and breathes code")
- What examples and case studies already live in their head?
- What do they consider high-status vs low-status within their world?
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.
- 6d ago First seen · 409 lines · 182 tokens per session scan A 4b0def64e4b4
worldbuilder-writing is a skill published in the GitHub repository thtskaran/claude-skills (18 stars, last pushed 3mo ago), licensed MIT. It adds 182 tokens to every session and 4,987 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
absolute-simplify
Use when the user wants to simplify, clean up, refactor, tidy, or refine code — their staged/unstaged git changes or a target file/path. Reduces complexity, flattens nesting, removes redundancy and dead code, scores each change by value (holding low-value churn), then runs tests to prove nothing broke. Invoke on…
math-modeling
当用户要求数学建模、建模竞赛、建模分析、代码求解、结果可视化或生成数学建模论文时使用。支持完整三阶段流程、单独执行任一角色，以及在关键节点使用独立 Subagent 进行阶段内质检；默认只启用质检 Subagent，用户可明确选择额外协作。.
math-modeling
当用户要求数学建模、建模竞赛、建模分析、代码求解、结果可视化或生成数学建模论文时使用。支持完整三阶段流程、单独执行任一角色，以及在关键节点使用独立 Subagent 进行阶段内质检；默认只启用质检 Subagent，用户可明确选择额外协作。.
科研可视化工具
从数据剖析到出版级成图的完整可视化工具。先做数据剖析（列类型/样本量/分布/异常值/分组结构/相关性）， 再结合论证目标推荐图型，主动拦截科研画图经典错误，产出 Nature / Science / IEEE / Elsevier / PNAS / 中文核心期刊级别的成图。覆盖数据 EDA、图表契约、选图决策、出版级绘制、程序自检 + AI 读图闭环、多格式 导出和文件审计。数学建模场景额外支持三类图体系（原始数据/过程/结果）和子问题覆盖检查。 当用户涉及论文配图、科研画图、数据可视化、选图、期刊投稿图、figure、出版级图表、matplotlib、seaborn、…
LaTeX工具
从官方或内置模板创建、编译和校验数学建模 LaTeX 论文项目，并可配合 DOCX 工具把完整 LaTeX 论文转换为 Word。.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…