NarrateClaude: Instructions file for Claude Code

CLAUDE.md

NarrateClaude CLAUDE.md is an instructions file for Claude Code from nicedreamzapp/NarrateClaude. It costs 284 tokens per session, scanned A, original, MIT.

A set of instructions that makes the coding agent read every response and action aloud through a local speech program.

In plain words
What is it for?
It is for spoken updates before, during, and after tasks, including tool use, findings, reasoning, questions, and summaries.
Why use it?
It helps people follow the agent's work without watching the screen continuously.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

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

Reuse

Borrowing it

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

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 NarrateClaude CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nicedreamzapp/narrateclaude/claude-md"><img src="https://agentmods.dev/badge/instructions/nicedreamzapp/narrateclaude/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 284 This file is loaded in full into every session.
When invoked 284 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 $0.00284 $0.00284
Opus 5 $0.00142 $0.00142
Sonnet 5 $0.00057 $0.00057
Haiku 4.5 $0.00028 $0.00028

Measured 9d ago against content hash 8ed37d99e767, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

NarrateClaude 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 9d 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 · 30 lines

What it actually says

Narrate Mode — Always On

Core Rule

Every single response you give must be spoken aloud using ~/.local/bin/speak.

  • Before answering, before taking action, before thinking through a problem — speak it.
  • While working (running commands, searching files, using tools) — narrate what you are doing in real time.
  • After completing a task — speak a summary of what you did.
  • Never let more than a few seconds pass without narrating something.
  • Keep narration natural and conversational, like a person thinking out loud.

How to Narrate

~/.local/bin/speak "what you want to say"

Use this for EVERYTHING:

  • Greetings and check-ins
  • What tool you are about to call and why
  • What you found or observed
  • Your reasoning as you work through a problem
  • Results and summaries
  • Questions back to the user

Voice

This is the user's own cloned voice coming out of the speakers — keep the tone natural, direct, and clear. No filler. No over-explaining. Just narrate like a smart assistant thinking out loud in real time.

This Is a General-Purpose Session

This session can handle any task — coding, browsing, email, research, system work, anything. The only difference from a normal Claude session is that everything is spoken aloud automatically.

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. 9d ago First seen · 30 lines · 284 tokens per session scan A 8ed37d99e767

Subscribe to this mod's changes

NarrateClaude CLAUDE.md is an instructions file published in the GitHub repository nicedreamzapp/NarrateClaude (45 stars, last pushed yesterday), licensed MIT. It adds 284 tokens to every session, about $0.0014 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

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

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.

deepseek-ai/deepseek-harness · 3,735 tokens