claudish

claudish is a command for Claude Code from gvzdv/claudish-to-english. It costs 66 tokens per session (472 once invoked), scanned A, original, MIT.

A command for controlling Claudish, a tool that rewrites assistant responses. It can show its status, switch rewriting on or off, change style, language, or model, and restore the previous original response.

In plain words
What is it for?
Viewing the Claudish dashboard, changing rewrite settings, selecting styles such as a short summary, and reprinting the last unrevised response.
Why use it?
It gives users a quick way to inspect or change response rewriting without restarting the session.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claudish-to-english plugin — 1 skill, 1 command, 3 hooks shipped together

Good fit Viewing the Claudish dashboard, changing rewrite settings, selecting styles such as a short summary, and reprinting the last unrevised response.

Compare 6 commands from other repositories ↓
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

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add gvzdv/claudish-to-english
Claude Code
/plugin install claudish-to-english

Made for: Claude Code.

Or install claudish-to-english, the plugin that ships this one along with the rest of its 1 skill, 1 command, 3 hooks.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/gvzdv/claudish-to-english/claudish"><img src="https://agentmods.dev/badge/commands/gvzdv/claudish-to-english/claudish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 472 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00066 $0.00472
Opus 5 $0.00033 $0.00236
Sonnet 5 $0.00013 $0.00094
Haiku 4.5 $0.00007 $0.00047

Measured 13d ago against content hash 7cd96c931a11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

claudish 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 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.

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.

commands/claudish.md · 18 lines

What it actually says

Claudish, after applying "$ARGUMENTS": !"${CLAUDE_PLUGIN_ROOT}/claudish-ctl.sh" --stdin-args <<'CLAUDISH_ARGV_EOF' $ARGUMENTS CLAUDISH_ARGV_EOF

Decide how to present the script output above, based on "$ARGUMENTS":

  • Empty, "status", "menu", or "help" — the output is a preformatted dashboard. Show it to the user verbatim inside a fenced code block, unchanged, and add nothing else. (Lines marked ⚠ are /claudish overrides that persist across sessions — the dashboard already explains them, so do not restate.)
  • "last" — the output is the ORIGINAL text of the last assistant message. Reply with the literal line <!-- claudish:original --> as the VERY FIRST line (it tells the display hook not to rewrite this reply, and is stripped from view), then one short intro line (remind the user that ctrl+o shows the whole original chat), then the text verbatim.
  • Anything else (on/off/append/replace/style/language/model/cycle/reset) — the output is a one-line state summary (claudish: <state> (style: …, language: …, model: …), where style tldr = short summary, 5y = explain like I'm five, caveman = blunt caveman speak, default = plain rewrite). Relay it to the user in one short line. If the script printed an error instead, show that.

Do nothing else.

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 · 18 lines · 66 tokens per session scan A 7cd96c931a11

Subscribe to this mod's changes

claudish is a command published in the GitHub repository gvzdv/claudish-to-english (2,569 stars, last pushed 15d ago), licensed MIT. It adds 66 tokens to every session and 472 once invoked, about $0.0003 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.