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/dankermu/novel-writer-plugin/claude-mdgit clone --depth 1 https://github.com/DankerMu/novel-writer-pluginWrote 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/dankermu/novel-writer-plugin/claude-md)<a href="https://agentmods.dev/instructions/dankermu/novel-writer-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/dankermu/novel-writer-plugin/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 | $0.02911 | $0.02911 |
| Opus 5 | $0.01456 | $0.01456 |
| Sonnet 5 | $0.00582 | $0.00582 |
| Haiku 4.5 | $0.00291 | $0.00291 |
Grade A, and why
novel-writer-plugin 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 5d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Claude Code plugin for Chinese web novel (网文) multi-agent collaborative writing. 6 specialized agents orchestrated through a state-machine workflow with spec-driven quality gates and anti-AI output strategies.
Commands
CI runs on push via .github/workflows/docs-ci.yml (markdownlint + lychee + manifest validation).
Python Environment
All scripts/*.sh use a project-local venv (.venv/) for Python isolation. Setup:
Scripts auto-resolve ${SCRIPT_DIR}/../.venv/bin/python3, falling back to system python3 if venv is absent. Currently stdlib-only (no third-party deps).
Architecture
4-Layer Spec Hierarchy (Spec-Driven Writing)
| Layer | File Pattern | Purpose | Mutability |
|---|---|---|---|
| L1 World Rules | world/rules.json |
Physics, magic, society hard constraints | Immutable |
| L2 Character Contracts | characters/active/*.json |
Ability bounds, behavior patterns | Protocol-gated |
| L3 Chapter Contracts | volumes/vol-{V:02d}/chapter-contracts/ |
Pre/post conditions, acceptance criteria | Negotiable w/ audit |
| LS Storyline Specs | storylines/storylines.json |
Multi-POV constraints, prevents cross-line leaks | Volume-scoped |
Agents validate outputs against these layers. QualityJudge performs dual-track verification: contract compliance (hard gate) + 9-dimension scoring (soft eval, including tonal_variance for register micro-injection density). ContentCritic evaluates reader engagement (Track 3) + content substance (Track 4: information density, plot progression, dialogue efficiency) + POV knowledge boundary & cross-storyline leak detection (Track 5: detects proper nouns/info leaking into narration that the POV character shouldn't know yet, and cross-storyline entity leaks in non-convergence chapters) + cross-chapter logic review (Track 6: reads recent 3 chapters full text to detect hard contradictions and plot holes; narrative techniques like time skips/POV switches are not flagged).
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.
- 5d ago First seen · 147 lines · 2,911 tokens per session scan A 15c592831a24
novel-writer-plugin CLAUDE.md is an instructions file published in the GitHub repository DankerMu/novel-writer-plugin (13 stars, last pushed 4mo ago), licensed MIT. It adds 2,911 tokens to every session, about $0.0146 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).