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/comfuture/novelist/agents-mdgit clone --depth 1 https://github.com/comfuture/novelistWhat 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 | $0.01247 | $0.01247 |
| Opus 5 | $0.00624 | $0.00624 |
| Sonnet 5 | $0.00249 | $0.00249 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
novelist AGENTS.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 2d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repository Purpose
This repository develops and distributes Novelist, an agent-assisted novel-writing plugin for Codex, Claude Code, and Antigravity CLI.
The repository root is not a novel workspace. The canonical plugin payload is
plugins/novelist/. Generated novel projects come from
plugins/novelist/assets/scaffold/.
Canonical Sources
plugins/novelist/skills/: all nine canonical plugin skills.plugins/novelist/assets/scaffold/: the canonical generated-workspace scaffold.plugins/novelist/.codex-plugin/plugin.json: Codex adapter metadata.plugins/novelist/.claude-plugin/plugin.json: Claude Code adapter metadata.plugins/novelist/plugin.json: Antigravity CLI adapter metadata..agents/plugins/marketplace.json: Codex repository marketplace..claude-plugin/marketplace.json: Claude Code repository marketplace.scripts/create_scaffold.py: canonical standalone scaffold exporter.scripts/create-scaffold.sh,.ps1, and.bat: thin platform entry points.
Do not recreate .agents/skills/ or a novel scaffold at the repository root.
Do not edit installed plugin cache copies.
Adapter Boundaries
Keep shared workflows in plugins/novelist/skills/. Do not fork complete skill
trees by host.
skills/*/agents/openai.yamlis Codex/OpenAI presentation metadata.- Claude-specific packaging belongs under
.claude-plugin/. - Antigravity's root
plugin.jsonaccepts only its documented minimal fields. - Host-specific image-generation instructions belong in
create-visual-asset/references/. - The shared visual workflow must stay provider-neutral and must not claim an image was generated when no raster provider is connected.
Scaffold Contract
Novel source files use Markdown with YAML frontmatter. Documentation files
named README.md, AGENTS.md, and CLAUDE.md do not need source frontmatter.
The canonical scaffold must remain self-contained inside the plugin. Never add runtime reads from the repository root, symlinks, or hardlinks. Preserve:
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.
- 2d ago First seen · 126 lines · 1,247 tokens per session scan A 86f9b32b6ce4
novelist AGENTS.md is an instructions file published in the GitHub repository comfuture/novelist (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,247 tokens to every session, about $0.0062 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.
Other instructions, from other repositories
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.
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.
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).
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.