claudish-to-english: Instructions file for Claude Code

CLAUDE.md

claudish-to-english CLAUDE.md is an instructions file for Claude Code from gvzdv/claudish-to-english. It costs 1,421 tokens per session, scanned A, original, MIT.

Project instructions for a Claude Code plugin that rewrites assistant messages into plain language for display while keeping the original conversation unchanged.

In plain words
What is it for?
Use them when changing the rewrite hooks, provider support, language handling, command flags, or the optional Markdown rewrite feature.
Why use it?
They map the shell scripts and hooks, and describe how the plugin handles streamed messages, optional Markdown rewriting, language settings, and providers.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

This is gvzdv/claudish-to-english's own configuration. It tells Claude Code how to work on claudish-to-english 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 claudish-to-english 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.

About the project

claudish-to-english is a Claude Code plugin that rewrites assistant messages into plain English for display, using a local or remote language model while preserving the original response and transcript. It is used by people who want easier-to-read Claude Code output, with an optional hook for simplifying Markdown files. The catalogue entries are the plugin's hooks, instruction, skill, command, and packaging.

gvzdv/claudish-to-english · 2,569 stars · on GitHub

Reuse

Borrowing it

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

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 claudish-to-english CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gvzdv/claudish-to-english/claude-md"><img src="https://agentmods.dev/badge/instructions/gvzdv/claudish-to-english/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,421 This file is loaded in full into every session.
When invoked 1,421 The same file — it is already loaded in full.
Security scan A 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 $0.01421 $0.01421
Opus 5 $0.00711 $0.00711
Sonnet 5 $0.00284 $0.00284
Haiku 4.5 $0.00142 $0.00142

Measured 13d ago against content hash 5a0e287afa62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

claudish-to-english CLAUDE.md scanned grade A 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 13d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Plain bash + `jq` + `curl`. No build, no test suite, no dependencies to install.
CLAUDE.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

claudish-to-english

A Claude Code plugin: a MessageDisplay hook shows a plain-language rewrite of each assistant message, produced by a local or remote LLM. Display-only — Claude's reasoning and the saved transcript always keep the original text.

Plain bash + jq + curl. No build, no test suite, no dependencies to install.

CONTRIBUTING.md is the full version of this file; it is the source of truth if the two ever disagree.

Layout

File Role
rewrite.sh MessageDisplay hook — the main event. Buffers streamed chunks, rewrites on the final one
rewrite-md.sh PostToolUse hook — rewrites Markdown files (opt-in, off by default)
claudish-ctl.sh backs /claudish; writes the ~/.claude/claudish-* flag files, prints the dashboard
session-notice.sh SessionStart hook — warns that flag files from an earlier session are still active
providers.sh provider layer (ollama / anthropic / openai / codex). Sourced by both hooks
lang.sh output-language resolver + the sanitiser for untrusted config values. Sourced by both hooks
commands/claudish.md the /claudish slash command
hooks/hooks.json wires the three hooks

Config precedence is consistent throughout: flag file > env var > settings file > built-in default. Flag files exist because env vars are frozen at session launch and cannot be changed mid-session.

Non-negotiable: hooks fail open

On any problem — provider down, timeout, no jq, malformed payload, missing file — a hook emits nothing and exits 0, leaving Claude's original text on screen. This outranks every other consideration. Never add a code path where a failure can swallow or corrupt an assistant message.

When changing a hook, verify it directly. All three must print nothing, exit 0:

printf 'not json'                        | bash rewrite.sh; echo "rc=$?"
printf ''                                | bash rewrite.sh; echo "rc=$?"
printf '{"session_id":"s","final":true}' | bash rewrite.sh; echo "rc=$?"

Read the full file on GitHub · 114 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. 13d ago First seen · 114 lines · 1,421 tokens per session scan A 5a0e287afa62

Subscribe to this mod's changes

claudish-to-english CLAUDE.md is an instructions file published in the GitHub repository gvzdv/claudish-to-english (2,569 stars, last pushed 15d ago), licensed MIT. It adds 1,421 tokens to every session, about $0.0071 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

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 · 7,126 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

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

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