souls-directory: Instructions file for Claude Code

CLAUDE.md

souls-directory CLAUDE.md is an instructions file for Claude Code from thedaviddias/souls-directory. It costs 1,675 tokens per session, scanned A, original, MIT.

Project context for souls.directory, a website where people browse, upload, and share Markdown files that define AI personalities. It records the project’s technologies, including Next.js, Tailwind CSS, Convex, and GitHub-based sign-in.

In plain words
What is it for?
Use it when changing the website, database queries, authentication, styling, or its Next.js application structure.
Why use it?
It tells an AI assistant which architecture and data services the project actually uses, helping prevent incompatible implementation choices.

Instructions file for Claude Code

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

This is thedaviddias/souls-directory's own configuration. It tells Claude Code how to work on souls-directory 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 souls-directory configures →

Reuse

Borrowing it

Nothing to install: this file belongs to thedaviddias/souls-directory. 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/thedaviddias/souls-directory/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/thedaviddias/souls-directory

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 souls-directory CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/thedaviddias/souls-directory/claude-md/github.svg)](https://agentmods.dev/instructions/thedaviddias/souls-directory/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/thedaviddias/souls-directory/claude-md"><img src="https://agentmods.dev/badge/instructions/thedaviddias/souls-directory/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 souls-directory CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/thedaviddias/souls-directory/claude-md"><img src="https://agentmods.dev/badge/instructions/thedaviddias/souls-directory/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,675 This file is loaded in full into every session.
When invoked 1,675 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 $0.01675 $0.01675
Opus 5 $0.00838 $0.00838
Sonnet 5 $0.00335 $0.00335
Haiku 4.5 $0.00168 $0.00168

Measured 10d ago against content hash d19bbfdaf842, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

souls-directory 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 10d 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 · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Project Context for AI Assistants

Project Overview

souls.directory is a curated directory of AI personality templates ("souls") — markdown-based SOUL.md files that define how AI agents behave. Users can browse, upload, and share these personality templates.

Tech Stack

  • Framework: Next.js (App Router) with TypeScript
  • Styling: Tailwind CSS with custom CSS variables (grayscale, dark-mode-only theme)
  • Database/Backend: Convex (NOT Supabase, NOT Prisma, NOT any SQL database)
  • Auth: Convex Auth (@convex-dev/auth) with GitHub OAuth
  • Package Manager: pnpm with Turborepo monorepo
  • Linter: Biome (not ESLint)
  • Fonts: Geist Sans + Geist Mono

Critical Rules

Database is Convex

  • Queries: useQuery(api.tableName.queryName)
  • Mutations: useMutation(api.tableName.mutationName)
  • Schema: apps/web/convex/schema.ts
  • Functions: apps/web/convex/*.ts

Auth Pattern

Always use getAuthenticatedUser(ctx) or getCurrentUser(ctx) from convex/lib/access.ts.

NEVER look up users by email via ctx.auth.getUserIdentity() — this is unreliable. The helper functions use getAuthUserId(ctx) from @convex-dev/auth/server which returns the Convex user _id directly.

No Barrel Files

Do NOT create index.ts files that re-export from multiple modules. Import directly from the specific file.

// BAD
import { SoulCard, Header } from '@/components'

// GOOD
import { SoulCard } from '@/components/souls/soul-card'
import { Header } from '@/components/layout/header'

Upload Page is Fragile

The upload wizard at apps/web/app/upload/page.tsx has been a source of repeated regressions. When modifying it:

  1. Do NOT add complex state management (localStorage persistence, useReducer, etc.) without careful testing
  2. Do NOT wrap handlers in unnecessary useCallback — React's FileReader async callbacks are sensitive to stale closures
  3. Do NOT use <label htmlFor> for file inputs — use a <button> with explicit onClick={() => fileInputRef.current?.click()}
  4. The file upload flow is:
    • User clicks button → fileInputRef.current?.click()
    • Browser shows file picker → user selects file
    • onChange fires → handleFileSelectsetFiles(prev => [...prev, ...selected])
    • normalizedFiles memo recalculates
    • useEffect reads first .md file → setContent(text)
  5. Test file upload manually after ANY change to the upload page or its hooks

Read the full file on GitHub · 142 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. 10d ago First seen · 142 lines · 1,675 tokens per session scan A d19bbfdaf842

Subscribe to this mod's changes

souls-directory CLAUDE.md is an instructions file published in the GitHub repository thedaviddias/souls-directory (158 stars, last pushed 1mo ago), licensed MIT. It adds 1,675 tokens to every session, about $0.0084 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.

Related

Other instructions, from other repositories

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 · 7,296 tokens

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.

openai/codex · 5,153 tokens

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 · 6,785 tokens

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.

github/spec-kit · 7,104 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 tokens