agentmods.dev

mythos: Instructions file for Claude Code

CLAUDE.md

mythos CLAUDE.md is an instructions file for Claude Code from forbiddenlink/mythos. It costs 2,632 tokens per session, scanned A, original, MIT.

A project instruction document for Mythos Atlas, an interactive mythology encyclopedia. It explains the project structure, technology, design rules, and development commands, including that a monorepo stores multiple apps in one repository.

In plain words
What is it for?
Use it as the repository guide when working on the web app, optional Rust API, design system, or shared development commands.
Why use it?
It gives coding agents the project context and local rules they need before making changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is forbiddenlink/mythos's own configuration. It tells Claude Code how to work on mythos itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mythos configures →

not rated 2repo changed 3d ago A scan 2,632 tokens original MIT
View source ↗ forbiddenlink/mythos mythosatlas.com
Reuse

Borrowing it

Nothing to install: this file belongs to forbiddenlink/mythos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/forbiddenlink/mythos/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/forbiddenlink/mythos

Made for: Claude Code.

Wrote 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.

agentmods badge for mythos CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/forbiddenlink/mythos/claude-md/github.svg)](https://agentmods.dev/instructions/forbiddenlink/mythos/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/forbiddenlink/mythos/claude-md"><img src="https://agentmods.dev/badge/instructions/forbiddenlink/mythos/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mythos CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/forbiddenlink/mythos/claude-md"><img src="https://agentmods.dev/badge/instructions/forbiddenlink/mythos/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,632 This file is loaded in full into every session.
When invoked 2,632 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02632 $0.02632
Opus 5.5 $0.01053 $0.01053
Sonnet 5.5 $0.00526 $0.00526
Haiku 4.5 $0.00263 $0.00263

Measured 3d ago against content hash bee3fb42edba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mythos 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 3d 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.

CLAUDE.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to agents when working with code in this repository.

Design system: before generating any UI, read apps/web/public/design-system.txt (machine-readable token + component contract). Token SoT = apps/web/src/app/globals.css; philosophy = .impeccable.md.

Project overview

Mythos Atlas is an interactive mythology encyclopedia. Live site: https://mythosatlas.com

It's a pnpm + Turborepo monorepo with one app:

  • apps/web - Next.js 16 (App Router) + React 19 frontend. Pages read static JSON data files from src/data/ directly; there is no database and no public data API.

The former optional Rust/PostgreSQL backend (apps/api) was retired; see ARCHITECTURE.md for where it lives in history.

Stack

  • Next.js 16.3.4, React 19.2.8, TypeScript 6.0.3 (web app)
  • pnpm 10.34.5 (packageManager field enforced), Turborepo
  • Node v22.22.2 (see .nvmrc)
  • ESLint is the primary linter and Prettier the formatter (Husky + lint-staged). Biome (biome.json) runs as a complementary lint pass only: its formatter, import sorting and a11y group are off (Prettier and eslint-plugin-jsx-a11y own those). knip (knip.json) checks for unused files, dependencies and exports. CI runs all three.

Commands

Run from the monorepo root unless noted.

pnpm install
cp apps/web/.env.example apps/web/.env.local  # add ANTHROPIC_API_KEY / Upstash for Oracle

pnpm dev                              # starts all apps via Turborepo (web on :3000)
pnpm --filter web dev                 # start only the web app

pnpm build                            # build all apps
pnpm --filter web build               # build only web (uses the configured --webpack plugin pipeline)

pnpm lint                             # ESLint for the web app
pnpm --filter web exec tsc --noEmit   # TypeScript type check (web)

pnpm --filter web test                # Vitest unit tests, run once
pnpm --filter web test:watch
pnpm --filter web test:coverage       # gate over src/lib/** (see below)
pnpm --filter web exec vitest run src/__tests__/lib/search.test.ts   # single file

pnpm --filter web e2e                 # Playwright, headless Chromium (builds and starts production server on :3000)
pnpm --filter web e2e:ui

pnpm --filter web analyze             # webpack bundle analyzer (sets ANALYZE=true)

pnpm biome:check                      # complementary lint pass (CI)
pnpm biome:fix
pnpm knip                             # unused files/deps/exports (CI)

Read the full file on GitHub · 117 lines

Changes

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.

  1. 3d ago Changed · +1 lines · +77 tokens per session bee3fb42edba
  2. 29d ago Changed · -6 lines · +486 tokens per session 19f6b87a3bb0
  3. 1mo ago Changed · +4 lines · +191 tokens per session 1b17612ad49d
  4. 1mo ago Changed · +5 lines · +80 tokens per session 3cb9984ff4a9
  5. 1mo ago First seen · 113 lines · 1,798 tokens per session scan A 0953c24c66ca

Subscribe to this mod's changes

mythos CLAUDE.md is an instructions file published in the GitHub repository forbiddenlink/mythos (2 stars, last pushed 2d ago), licensed MIT. It adds 2,632 tokens to every session, about $0.0105 per session on Opus 5.5. 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 2026-09-20.

Project managementWriting and docsaimythologynextjsstorytelling
Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,581 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens