DreamTalk: Instructions file for Claude Code

CLAUDE.md

DreamTalk CLAUDE.md is an instructions file for Claude Code from ProjectLiminality/DreamTalk. It costs 3,942 tokens per session, scanned A, original, MIT.

A repository instruction file for DreamTalk, a TypeScript and WebGPU framework for creative animation. It defines which project documents an agent should read first and distinguishes the current framework from older Python and C4D code.

In plain words
What is it for?
Use it when working on DreamTalk's TypeScript/WebGPU codebase, following its documentation order, or understanding which files describe its syntax, roadmap, decisions, and work rules.
Why use it?
It gives agents the project's current source of truth and prevents them from treating older implementation material as authoritative. It also provides a map of the main design, syntax, plan, and decision documents.

Instructions file for Claude Code

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

This is ProjectLiminality/DreamTalk's own configuration. It tells Claude Code how to work on DreamTalk 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 DreamTalk configures →

Reuse

Borrowing it

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

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 DreamTalk CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/projectliminality/dreamtalk/claude-md.svg)](https://agentmods.dev/instructions/projectliminality/dreamtalk/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/projectliminality/dreamtalk/claude-md"><img src="https://agentmods.dev/badge/instructions/projectliminality/dreamtalk/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,942 This file is loaded in full into every session.
When invoked 3,942 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 $0.03942 $0.03942
Opus 5 $0.01971 $0.01971
Sonnet 5 $0.00788 $0.00788
Haiku 4.5 $0.00394 $0.00394

Measured 3d ago against content hash 50db952ea06f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

DreamTalk 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 · 384 lines

How it starts

The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file is the soul of the DreamTalk agent — everything it needs to work effectively.

⚠️ START HERE — The new TypeScript framework (2026)

DreamTalk is being rebuilt as a TypeScript/WebGPU framework in core/. Before any work, read in order: docs/TASTE.md (law) → docs/PLAN.md (roadmap + status ledger) → docs/DECISIONS.md → docs/GATES.md. Autonomous/unattended sessions additionally follow docs/AUTONOMY.md (the work protocol: fitness function, one deliverable per session, drift guards, stop conditions) exactly. The Python/C4D library documented below remains the authoring backend and prior art — per TASTE.md it is archaeology, not authority.

Documentation Map

Document Location Contents
CLAUDE.md /CLAUDE.md This file - operational guide, philosophy, architecture overview, current horizons
README.md /README.md Public-facing intro, philosophical meaning, known limitations, future vision summary
SYNTAX.md /docs/SYNTAX.md Canonical DreamTalk syntax specification (Kairos/Kronos, parameter types, bindings, verbs, state machines)
VISION_AGENTIC_ANIMATION.md /docs/VISION_AGENTIC_ANIMATION.md North star for agentic animation (digital spirits, holonic agency, steering behaviors, formations, cable physics)
mograph-generator-rnd.md /docs/mograph-generator-rnd.md Technical R&D log for MoGraph integration, geometry-based strokes, performance analysis
xpresso-migration-plan.md /docs/xpresso-migration-plan.md Historical reference - XPresso to Python Generator migration (complete)

Current Horizons

Active projects using MindVirus as the testing vehicle for DreamTalk capabilities:

1. Double Wall / Labyrinth

MindViruses self-assemble into a labyrinth structure with hidden corridor.

  • Tests: Formation system, slot-finding, MoGraph integration, swarm orchestration
  • Key challenge: 90° turn animation as MindVirus exits corridor and becomes brick in wall

Read the full file on GitHub · 384 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 First seen · 384 lines · 3,942 tokens per session scan A 50db952ea06f

Subscribe to this mod's changes

DreamTalk CLAUDE.md is an instructions file published in the GitHub repository ProjectLiminality/DreamTalk (5 stars, last pushed 7d ago), licensed MIT. It adds 3,942 tokens to every session, about $0.0197 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 2026-09-04.

Related

Other instructions, from other repositories

CopilotTraining typescript.instructions.md

Instructions for MSBart2/CopilotTraining, covering typescript development standards, type definitions, type safety, generics and union types.

MSBart2/CopilotTraining · 476 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 · 5,182 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

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

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

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