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 instructions/geobond13/fiction-forge/claude-mdgit clone --depth 1 https://github.com/geobond13/fiction-forgeWrote 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/instructions/geobond13/fiction-forge/claude-md)<a href="https://agentmods.dev/instructions/geobond13/fiction-forge/claude-md"><img src="https://agentmods.dev/badge/instructions/geobond13/fiction-forge/claude-md.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 | $0.00570 | $0.00570 |
| Opus 5 | $0.00285 | $0.00285 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
fiction-forge CLAUDE.md 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fiction-Forge Project Instructions
Project Context
This is a novel manuscript project managed with fiction-forge tools. The AI assistant has access to a fiction context MCP server with 5 tools for querying story reference material.
Available MCP Tools
When editing or writing chapters, use these tools proactively:
search_bible— Search all reference docs for world/plot/character infoget_character— Get voice notes and state for a character at a specific chapterget_chapter_context— Get opening/closing lines of surrounding chapterscheck_continuity— Validate text against continuity rulesget_foreshadowing— Check plant/payoff thread status
Writing Conventions
- Opening lines: First line of every chapter in ALL CAPS (first few words)
- Scene breaks: Use
---(horizontal rule) between scenes within a chapter - Metadata: HTML comment block at top of each chapter with POV, Location, Timeline
- Songs/letters/epigraphs: Use blockquotes (
>prefix) - Emphasis:
*italics*for emphasis and internal thought
Editorial Rules
When editing prose:
- Cut, don't replace. Remove overused patterns; don't substitute with different patterns.
- One touch per sentence. Each sentence gets edited once per pass.
- Preserve openings and closings. First and last paragraphs of each chapter are protected.
- No new content during cut passes. Only remove and tighten.
- Check continuity after every edit. Use the
check_continuitytool.
File Structure
book/— Chapter files (numbered:01_Title.md,02_Title.md)reference/— Story bible, characters, foreshadowing, continuityproject.yaml— All tool configurationoutput/— Generated EPUB, PDF, HTML, scan reports
Common Tasks
Writing a new chapter
Write Chapter N: [Title].
Use get_chapter_context to check adjacent chapters.
Use get_character for each character in the scene.
Target: 3,000-4,000 words.
Check continuity when done.
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 · 68 lines · 570 tokens per session scan A b866c6fd1bbd
fiction-forge CLAUDE.md is an instructions file published in the GitHub repository geobond13/fiction-forge (19 stars, last pushed 1mo ago), licensed MIT. It adds 570 tokens to every session, about $0.0029 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 instructions, from other repositories
humanizer AGENTS.md
Instructions for blader/humanizer, covering guide for agents, what this repo contains, key files, rules for changes and writing style.
avoid-ai-writing CLAUDE.md
Claude Code instructions for conorbronsdon/avoid-ai-writing, covering claude.md, what this is, repository structure, how to make changes and architecture of the skill.
show-me-the-story AGENTS.md
AGENTS.md instructions for Nigh/show-me-the-story, covering agents.md — ai 小说生成器项目指南, 项目概述, 编译与运行, 完整编译（含前端构建） and 或手动分步.
humanizer-skill AGENTS.md
AGENTS.md instructions for Aboudjem/humanizer-skill, covering agents.md — humanizer skill, what this repo is, file map, how to install the skill and how to invoke the skill.
writing-agent CLAUDE.md
Claude Code instructions for dongbeixiaohuo/writing-agent, covering 写稿 agent 核心路由指令（v0.10.0） and 路由顺序.
vale-ai-tells CLAUDE.md
Claude Code instructions for tbhb/vale-ai-tells, covering claude code instructions, project overview, repository structure, development workflow and rule conventions.