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/jerseycheese/narraitor/claude-mdgit clone --depth 1 https://github.com/jerseycheese/NarraitorWrote 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/jerseycheese/narraitor/claude-md)<a href="https://agentmods.dev/instructions/jerseycheese/narraitor/claude-md"><img src="https://agentmods.dev/badge/instructions/jerseycheese/narraitor/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 | $0.02629 | $0.02629 |
| Opus 5 | $0.01314 | $0.01314 |
| Sonnet 5 | $0.00526 | $0.00526 |
| Haiku 4.5 | $0.00263 | $0.00263 |
Grade A, and why
Narraitor CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Verify: `curl -s localhost:3000 | head -1` returns HTML; Storybook responds on 6006. How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Narraitor
Canonical instructions for coding agents in this repo. AGENTS.md is gitignored here, so
this tracked file is the single canon — edit it, not a copy.
Narraitor is an AI-driven narrative RPG framework. You build a world (its theme, attributes, skills, and tone), create characters in it, and play through a generated, choice-driven story with a tracked inventory and journal. Single-player web app: no backend database, player data lives in the browser (IndexedDB via Zustand persistence), and AI generation runs through the player's own provider key.
Stack
- Next.js 15 (App Router) + React 19, TypeScript strict. Node >= 20, npm.
- Zustand 5 — one store per domain under
src/state/(characterStore,inventoryStore,journalStore,worldStore, ...), persisted to IndexedDB viapersistence.ts. - Plain CSS + design tokens —
var(--token)plusclsx. No Tailwind (removed in the design-system migration); nocn(), nocva, notailwind-merge. - AI generation through
src/lib/ai/(Google Gemini via@google/genai), keyed by the player's own provider key rather than a server-held key. - Secrets in
.env.local. Never commit them.
Run it
npm run dev # scripts/dev.sh — port 3000 in the main checkout; worktrees auto-select
npm run storybook # port 6006
npm run kill # emergency: pkill -f 'next dev'
Check whether a dev server is already running before starting one (lsof -iTCP:3000).
rcv-simulator-va's main checkout also defaults to 3000 — don't run both at once.
Verify: curl -s localhost:3000 | head -1 returns HTML; Storybook responds on 6006.
The quality gate
Run before any commit — CI runs these separately and the production build enforces lint and types anyway:
npm test # Jest unit/integration
npm run type-check # tsc --noEmit
npm run lint # ESLint (Next + test/script globs, JSX/markup hygiene)
npm run lint:css # Stylelint over **/*.css — run after ANY .css edit
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 · 204 lines · 2,629 tokens per session scan A 6a10c07ec017
Narraitor CLAUDE.md is an instructions file published in the GitHub repository jerseycheese/Narraitor (30 stars, last pushed today), licensed MIT. It adds 2,629 tokens to every session, about $0.0131 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
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 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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.