Claudish to English

A working prototype plugin for Claude Code, named Claudish to English, rewrites assistant messages into plain English using a local LLM via ollama, and is display-only, preserving the original text in transcripts. The plugin fails open—if ollama is down or a model is missing, users see Claude's original output unchanged—and requires ollama, a pulled model (default gemma4:26b-mlx, ~17 GB), jq, and curl. It is installable from the gvzdv/claudish-to-english marketplace or the Anthropic community marketplace after review, and all behavior is controlled by CLAUDISH_* environment variables.

A Claude Code plugin that shows a plain-English rewrite of each assistant message, produced by a local LLM via ollama . It is display-only : Claude's own reasoning and the saved transcript keep the original text — only what you read on screen changes. An optional second hook rewrites Markdown files into plain English when they are written or edited opt-in, off by default . Status: working prototype. Every hook fails open— if anything goes wrong ollama down, timeout, missing dependency , you simply see Claude's original text. The plugin can never swallow or corrupt an answer. This plugin shells out to a local model. Nothing works until these are in place: | Requirement | Why | Install | |---|---|---| ollama, running | Does the rewriting, locally | brew install ollama then ollama serve | | A pulled model | The actual rewriter | ollama pull gemma4:26b-mlx ~17 GB; choose the model that fits into your memory | jq | Parses hook JSON | ships with macOS; else brew install jq | curl | Talks to ollama | ships with macOS | Warm the model once after ollama serve the first call is a slow cold load : ollama run gemma4:26b-mlx "hi" If the local model isn't ready, the plugin does nothing to your text — Claude's output shows normally, unchanged. That is by design, not a bug. It skips fails open when ollama is down, the request times out, or the model isn't pulled. The first time that happens in a session it tells you why: the display hook appends a one-line notice on screen, and the Markdown hook shows a systemMessage . So a silent skip is never a mystery once per session; set CLAUDISH NOTICE=0 to silence it . Pick a model you actually have. The default is gemma4:26b-mlx . Pull it as above , or pull a smaller/faster model and point the plugin at it by setting CLAUDISH MODEL to that model's exact ollama tag in your env see Configuring the plugin configuring-the-plugin . If CLAUDISH MODEL names a model you have not pulled, every rewrite is skipped — with the one-time notice above. Directly from this repository also serves its own marketplace : /plugin marketplace add gvzdv/claudish-to-english /plugin install claudish-to-english@gvzdv-plugins After review by the Anthropic team, the plugin will be available to install from the community marketplace: /plugin marketplace add anthropics/claude-plugins-community /plugin install claudish-to-english@claude-community If the install summary says Run /reload-plugins to activate. , run that command. Try before installing loads it for one session, no install : claude --plugin-dir /path/to/claudish-to-english Run /reload-plugins after edits; if it doesn't load, check the /plugin Errors tab. All behavior is controlled by CLAUDISH environment variables full list in Configuration configuration-env-vars below . When you install from a marketplace, set them in Claude Code's env block in settings.json — do not edit the plugin's own hooks/hooks.json , which lives in the read-only plugin cache ~/.claude/plugins/cache/… and is overwritten on every update.For a personal, all-projects setup, use ~/.claude/settings.json : { "env": { "CLAUDISH MODEL": "gemma4:26b-mlx", "CLAUDISH MODE": "append" } } The hooks are subprocesses Claude Code spawns, so they inherit these. A few things to know: Restart Claude Code after editing The value is captured at launch, so a running session keeps the old one. env .The highest-precedence settings file that defines env does not merge across scopes. env supplies the entire block — it isn't combined with lower scopes. Precedence: managed → local → project → user. Keep all your CLAUDISH vars in whichever file wins. Scopes: ~/.claude/settings.json all your projects · .claude/settings.json shared with a repo, checked in · .claude/settings.local.json just you, just this repo . Quick one-off without editing a file — hooks inherit the launching shell: CLAUDISH MODEL=llama3.2:3b claude To confirm the hook is firing, set CLAUDISH DEBUG=1 and watch "$TMPDIR"/claudish-to-english/debug.log . Claude Code fires the MessageDisplay event once per streamed chunk , not once per message. Each fire is a separate process carrying message id , index , a final flag, and this chunk's delta a text fragment, not the whole message . So the hook buffers every delta to a temp file keyed by message id and only calls the model on the final chunk, once the whole message is known: chunk 0 final:false ─┐ chunk 1 final:false ─┤ append each delta to $TMPDIR/claudish-to-english/<session /<message /<index .part chunk 2 final:false ─┘ → emit nothing append or "" replace chunk 3 final:true ──► reconstruct full message → call ollama once → show the rewrite → delete the buffer On that final chunk it also reads the original user question from the transcript and passes it to the model as context only — to keep the rewrite on-topic. The model is told never to answer or repeat the question; it only rewrites the assistant's message. CLAUDISH MODE | On screen | Notes | |---|---|---| append default | Original streams normally, then a 💬 In plain English: block is appended. | Safest. No streaming loss; if the LLM fails you just don't get the extra block. | replace | Only the simplified version original chunks suppressed while streaming . | Experimental. Appears all at once after LLM latency; on failure it re-shows the full original. | A PostToolUse hook rewrite-md.sh rewrites Markdown files into plain English when they are written or edited. Unlike the display hook, this changes bytes on disk. Opt-in by directory. It does nothing unless CLAUDISH MD DIR is set, and it only touches .md files whose resolved path is inside that directory. Every other README , CLAUDE.md , or doc you edit is left alone. CLAUDISH MD MODE | Result | Notes | |---|---|---| sibling default | Writes NAME.plain.md next to NAME.md . | Non-destructive; the original is never touched. | overwrite | Replaces NAME.md in place. | Adds a < -- claudish-to-english:rewritten -- marker so a re-write is skipped idempotent . A weak model can degrade real docs — use with care. | In both modes: YAML frontmatter is split off and re-attached verbatim , fenced code is left to the model instruction, short files are skipped, and the write is atomic. Fail-open here means the file is left exactly as the agent wrote it . Large files are slow. gemma4:26b-mlx the default rewrites at roughly 60 tokens/s, so a long plan or spec can take 30–120s. This hook allows up to CLAUDISH MD TIMEOUT 150s inside a 180s PostToolUse hook budget; if a rewrite still times out you get the one-time notice above — raise those limits, or set CLAUDISH MODEL to a smaller model. Enable it for one directory, in sibling mode the safe default , the same way as every other setting — the env block of your settings.json : { "env": { "CLAUDISH MD DIR": "/ABS/PATH/docs/plain", "CLAUDISH MD MODE": "sibling" } } In overwrite mode the marker comment is written after any YAML frontmatter, so the frontmatter stays on line 1 where parsers expect it. | Var | Default | Meaning | |---|---|---| CLAUDISH ENABLED | 1 | Master switch. 0 = pass everything through. Read once at session start. | CLAUDISH OFF FILE | ~/.claude/claudish-off | Runtime kill switch. While this file exists, rewrites pause — re-checked every message, so unlike env vars it works mid-session. See | CLAUDISH MODE append append or replace display hook . CLAUDISH MODEL gemma4:26b-mlx CLAUDISH OLLAMA http://localhost:11434 CLAUDISH MIN CHARS 200 CLAUDISH STUB 0 1 = deterministic stub instead of the model for testing display mechanics . CLAUDISH TIMEOUT 45 display hook seconds . Keep it below that hook's timeout 60s . CLAUDISH MD TIMEOUT 150 Markdown file hook seconds . Higher on purpose — a large model rewriting a long doc is slow. Keep it below the PostToolUse hook timeout 180s . CLAUDISH DEBUG 0 1 = write a debug log to $TMPDIR/claudish-to-english/ . CLAUDISH NOTICE 1 1 = show a one-time, once-per-session notice when a rewrite is skipped because ollama is unreachable, the call timed out, or the model isn't pulled display hook appends it on screen; Markdown hook uses a systemMessage . 0 = stay fully silent pure fail-open . CLAUDISH MD DIR unset Markdown hook opt-in. Only .md under this directory is rewritten. Unset = the Markdown hook does nothing. CLAUDISH MD MODE sibling sibling NAME.plain.md or overwrite in place . CLAUDISH MD SUFFIX plain NAME.<suffix .md .In hooks/hooks.json the display hook MessageDisplay has a 60s timeout and the Markdown hook PostToolUse has a 180s timeout — the file hook is higher because a large model rewriting a long document can take a couple of minutes. CLAUDISH TIMEOUT and CLAUDISH MD TIMEOUT keep the LLM call itself bounded below those ceilings, so it fails open cleanly instead of being killed mid-write. Quick kill switch: set CLAUDISH ENABLED=0 or disable the plugin both apply only from the next session start , or touch ~/.claude/claudish-off to pause a session that's already running — see Toggling mid-session toggling-mid-session below. CLAUDISH ENABLED and the other env vars are read once, when a session launches, so they can't pause rewrites in a session that's already running. For that, both hooks also check a flag file on every invocation — each fire is a fresh process, so the check is always live: touch ~/.claude/claudish-off pause rewrites, effective on the next message rm ~/.claude/claudish-off resume You create and remove this file yourself; nothing creates it on install, and its absence is the normal "on" state. While it exists, ENABLED is forced to 0 and the fail-open path leaves Claude's original text untouched. Point a hotkey at a two-line toggle script to flip rewrites from the keyboard across all running sessions at once. Override the path with CLAUDISH OFF FILE . The request sends "think": false . Models with a hidden reasoning phase otherwise spend most of their time generating reasoning tokens you never see — much slower for identical output quality on this simple task. Keep it off. The rewriter runs entirely locally against ollama, so no conversation content leaves your machine . If you ever point CLAUDISH OLLAMA at a remote/hosted endpoint, that context which can include file contents from tool results would be sent off-box — don't do that unless you understand and accept it. claudish-to-english/ ├── .claude-plugin/ │ ├── plugin.json plugin manifest │ └── marketplace.json so the repo can be added as a marketplace directly ├── hooks/ │ └── hooks.json MessageDisplay - rewrite.sh ; PostToolUse - rewrite-md.sh ├── rewrite.sh display-rewrite hook ├── rewrite-md.sh markdown-file rewrite hook opt-in ├── LICENSE └── README.md MIT — see LICENSE /gvzdv/claudish-to-english/blob/main/LICENSE .