claude-code-narrator: Instructions file for Claude Code

CLAUDE.md

claude-code-narrator CLAUDE.md is an instructions file for Claude Code from shreyas-s-rao/claude-code-narrator. It costs 1,319 tokens per session, scanned B, original, MIT.

A Claude Code plugin that reads responses aloud using Kokoro, a text-to-speech system that runs on the user's computer. It uses Claude Code event hooks to speak selected messages and notifications.

In plain words
What is it for?
Use it to add spoken feedback to Claude Code sessions, including responses, tool-use updates, and notifications.
Why use it?
It lets developers hear agent output instead of reading every response on screen, while keeping speech generation local.

Instructions file for Claude Code

Written for Claude Code: $CLAUDE_PLUGIN_ROOT variable. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is shreyas-s-rao/claude-code-narrator's own configuration. It tells Claude Code how to work on claude-code-narrator 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 claude-code-narrator configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to shreyas-s-rao/claude-code-narrator. 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/shreyas-s-rao/claude-code-narrator/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/shreyas-s-rao/claude-code-narrator

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 claude-code-narrator CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shreyas-s-rao/claude-code-narrator/claude-md/github.svg)](https://agentmods.dev/instructions/shreyas-s-rao/claude-code-narrator/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/shreyas-s-rao/claude-code-narrator/claude-md"><img src="https://agentmods.dev/badge/instructions/shreyas-s-rao/claude-code-narrator/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 claude-code-narrator CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/shreyas-s-rao/claude-code-narrator/claude-md"><img src="https://agentmods.dev/badge/instructions/shreyas-s-rao/claude-code-narrator/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,319 This file is loaded in full into every session.
When invoked 1,319 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.01319 $0.01319
Opus 5 $0.00660 $0.00660
Sonnet 5 $0.00264 $0.00264
Haiku 4.5 $0.00132 $0.00132

Measured 10d ago against content hash 48ea9d002916, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

claude-code-narrator CLAUDE.md scanned grade B 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

The `UserPromptSubmit` hook for auto-hush is registered in `~/.claude/settings.json` (not in `hooks/hooks.json`) because it needs to persist across sessions and is managed by the `/narrator:on` and `/narrator:off` comman
CLAUDE.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What This Is

A Claude Code plugin that speaks responses aloud using Kokoro TTS (local neural text-to-speech). No cloud APIs — everything runs on the user's machine.

Testing

bash tests/run-all.sh          # all tests
bash tests/test-command-extraction.sh  # single test

Tests are plain bash scripts using an assert_eq pattern. Each test file is self-contained. New test files matching tests/test-*.sh are automatically picked up by run-all.sh.

Architecture

Hook fires → speak.sh → FIFO pipe → speak-daemon.sh → speak-daemon.py → audio
  • Plugin hooks (hooks/hooks.json) register for Stop, PostToolUse, and Notification events
  • Hook scripts extract text and the session's cwd, then pipe text to speak.sh with NARRATOR_CWD set
  • speak.sh is the central enqueuer: resolves local→global state, starts daemon if needed, writes JSON to FIFO
  • speak-daemon.py is a persistent Python process that keeps the Kokoro pipeline loaded in memory (~10s cold start, then <50ms per utterance), parsing per-utterance voice/speed from JSON messages
  • kokoro-speak.py is a standalone fallback for one-off speech

State and runtime files

Global state under ~/.claude-code-narrator/:

  • config — enabled/disabled, voice, speed (file-based because hooks are subprocesses)
  • fifo — named pipe for speech queue (JSON lines with text/voice/speed)
  • daemon.pid — written by Python daemon AFTER pipeline is loaded (signals readiness)
  • daemon.lock — atomic mkdir lock to prevent concurrent daemon starts
  • last-spoken — deduplication tracker for transcript-parsed text blocks

Per-directory local state (optional):

  • <cwd>/.claude-code-narrator/config — local overrides for enabled/voice/speed (missing keys fall back to global)
  • Created by /narrator:on --local, /narrator:cast --local, /narrator:speed --local, etc.

Plugin structure

Read the full file on GitHub · 83 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 · 83 lines · 1,319 tokens per session scan B 48ea9d002916

Subscribe to this mod's changes

claude-code-narrator CLAUDE.md is an instructions file published in the GitHub repository shreyas-s-rao/claude-code-narrator (26 stars, last pushed 3mo ago), licensed MIT. It adds 1,319 tokens to every session, about $0.0066 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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