diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json
deleted file mode 100644
index 013d1e3..0000000
--- a/.claude-plugin/plugin.json
+++ /dev/null
@@ -1,18 +0,0 @@
-{
-  "name": "claude-code-docs",
-  "version": "1.0.0",
-  "description": "Fetch Claude Code docs as markdown - rewrites code.claude.com/docs page URLs to their .md source before WebFetch runs",
-  "author": {
-    "name": "PleaseAI",
-    "url": "https://github.com/pleaseai"
-  },
-  "homepage": "https://github.com/pleaseai/claude-code-docs",
-  "license": "MIT",
-  "keywords": [
-    "claude-code",
-    "docs",
-    "markdown",
-    "webfetch",
-    "hooks"
-  ]
-}
diff --git a/README.md b/README.md
index c097612..b8088af 100644
--- a/README.md
+++ b/README.md
@@ -54,12 +54,14 @@ csp is optional: without it on `PATH`, `ask search` prints the resolved checkout
 
 ## Claude Code plugin: fetch docs as markdown
 
-This repo is also a Claude Code plugin. A `PreToolUse` hook rewrites `code.claude.com/docs` page URLs to their `.md` source before WebFetch runs, so Claude reads the clean markdown twin instead of the HTML app shell:
+The `claude-code-docs` Claude Code plugin now lives in [`pleaseai/claude-code-plugins`](https://github.com/pleaseai/claude-code-plugins/tree/main/plugins/claude-code-docs) (`plugins/claude-code-docs`). This repo is the docs mirror only. Moving the plugin out means installing it no longer clones this repo, which is large because of `docs/` and `llms-full.txt`. The install command is unchanged:
 
 ```bash
 /plugin install claude-code-docs@pleaseai
 ```
 
+A `PreToolUse` hook rewrites `code.claude.com/docs` page URLs to their `.md` source before WebFetch runs, so Claude reads the clean markdown twin instead of the HTML app shell:
+
 | WebFetch input | Rewritten to |
 |---|---|
 | `https://code.claude.com/docs/en/agents` | `https://code.claude.com/docs/en/agents.md` |
@@ -67,7 +69,7 @@ This repo is also a Claude Code plugin. A `PreToolUse` hook rewrites `code.claud
 
 Left untouched: URLs already ending in a file extension (`.md`, `llms.txt`, images), the docs root, and everything outside `code.claude.com/docs`. The hook returns [`updatedInput` with `permissionDecision: "allow"`](https://code.claude.com/docs/en/hooks#pretooluse-decision-control), so the rewritten fetch runs without an extra prompt.
 
-Hook tests: `bash hooks/rewrite-docs-url.test.sh`
+Source and hook tests: [`plugins/claude-code-docs`](https://github.com/pleaseai/claude-code-plugins/tree/main/plugins/claude-code-docs) in `pleaseai/claude-code-plugins`.
 
 ### Skill: `/claude-code-docs:claude-code-docs [question]`
 
diff --git a/hooks/hooks.json b/hooks/hooks.json
deleted file mode 100644
index fc0a342..0000000
--- a/hooks/hooks.json
+++ /dev/null
@@ -1,17 +0,0 @@
-{
-  "description": "Rewrites code.claude.com/docs page URLs to their .md source so WebFetch gets clean markdown instead of the HTML app shell",
-  "hooks": {
-    "PreToolUse": [
-      {
-        "matcher": "WebFetch",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/rewrite-docs-url.sh",
-            "timeout": 5
-          }
-        ]
-      }
-    ]
-  }
-}
diff --git a/hooks/rewrite-docs-url.sh b/hooks/rewrite-docs-url.sh
deleted file mode 100755
index 1f6e895..0000000
--- a/hooks/rewrite-docs-url.sh
+++ /dev/null
@@ -1,42 +0,0 @@
-#!/bin/bash
-# PreToolUse hook for WebFetch: rewrite Claude Code docs page URLs to their
-# markdown source (https://code.claude.com/docs/en/agents -> .../agents.md).
-# Every docs page serves a clean markdown twin at <page>.md; fetching it skips
-# the HTML app shell entirely. Silent exit 0 = no opinion, normal flow.
-
-input=$(cat)
-url=$(jq -r '.tool_input.url // empty' <<<"$input")
-[ -z "$url" ] && exit 0
-
-case "$url" in
-  https://code.claude.com/docs/*) ;;
-  *) exit 0 ;;
-esac
-
-# Drop fragment and query: hooks#pretooluse-decision-control -> hooks
-path="${url%%#*}"
-path="${path%%\?*}"
-path="${path%/}"
-
-# Already a raw file (page .md, llms.txt, images, ...) - leave untouched.
-# Check the last path segment only; the domain always contains dots.
-case "${path##*/}" in
-  *.*) exit 0 ;;
-esac
-
-# Only rewrite real pages under a locale segment (/docs/<locale>/<page...>),
-# not the docs root itself
-rest="${path#https://code.claude.com/docs/}"
-case "$rest" in
-  */*) ;;
-  *) exit 0 ;;
-esac
-
-jq --arg url "${path}.md" '{
-  hookSpecificOutput: {
-    hookEventName: "PreToolUse",
-    permissionDecision: "allow",
-    permissionDecisionReason: ("Rewrote Claude Code docs URL to markdown source: " + $url),
-    updatedInput: (.tool_input | .url = $url)
-  }
-}' <<<"$input"
diff --git a/hooks/rewrite-docs-url.test.sh b/hooks/rewrite-docs-url.test.sh
deleted file mode 100755
index 3f78d41..0000000
--- a/hooks/rewrite-docs-url.test.sh
+++ /dev/null
@@ -1,42 +0,0 @@
-#!/bin/bash
-# Tests for rewrite-docs-url.sh. Run: bash hooks/rewrite-docs-url.test.sh
-set -u
-cd "$(dirname "$0")"
-pass=0 fail=0
-
-run() {
-  echo "$1" | bash ./rewrite-docs-url.sh
-}
-
-expect_rewrite() { # input-url expected-url
-  out=$(run "{\"tool_name\":\"WebFetch\",\"tool_input\":{\"url\":\"$1\",\"prompt\":\"p\"}}")
-  got=$(jq -r '.hookSpecificOutput.updatedInput.url // empty' <<<"$out")
-  if [ "$got" = "$2" ]; then pass=$((pass+1)); else fail=$((fail+1)); echo "FAIL: $1 -> '$got' (expected $2)"; fi
-}
-
-expect_silent() { # input-url
-  out=$(run "{\"tool_name\":\"WebFetch\",\"tool_input\":{\"url\":\"$1\",\"prompt\":\"p\"}}")
-  if [ -z "$out" ]; then pass=$((pass+1)); else fail=$((fail+1)); echo "FAIL: $1 should pass through, got: $out"; fi
-}
-
-expect_rewrite "https://code.claude.com/docs/en/agents" "https://code.claude.com/docs/en/agents.md"
-expect_rewrite "https://code.claude.com/docs/en/agents/" "https://code.claude.com/docs/en/agents.md"
-expect_rewrite "https://code.claude.com/docs/en/hooks#pretooluse-decision-control" "https://code.claude.com/docs/en/hooks.md"
-expect_rewrite "https://code.claude.com/docs/en/agent-sdk/python" "https://code.claude.com/docs/en/agent-sdk/python.md"
-expect_rewrite "https://code.claude.com/docs/en/hooks?foo=bar" "https://code.claude.com/docs/en/hooks.md"
-
-expect_silent "https://code.claude.com/docs/en/agents.md"
-expect_silent "https://code.claude.com/docs/llms.txt"
-expect_silent "https://code.claude.com/docs/llms-full.txt"
-expect_silent "https://code.claude.com/docs/en"
-expect_silent "https://code.claude.com/docs"
-expect_silent "https://example.com/docs/en/agents"
-expect_silent "https://docs.claude.com/en/api/overview"
-
-# prompt must survive updatedInput (it replaces the whole input object)
-out=$(run '{"tool_name":"WebFetch","tool_input":{"url":"https://code.claude.com/docs/en/agents","prompt":"summarize"}}')
-got=$(jq -r '.hookSpecificOutput.updatedInput.prompt' <<<"$out")
-if [ "$got" = "summarize" ]; then pass=$((pass+1)); else fail=$((fail+1)); echo "FAIL: prompt lost: $got"; fi
-
-echo "passed: $pass, failed: $fail"
-[ "$fail" -eq 0 ]
diff --git a/skills/claude-code-docs/SKILL.md b/skills/claude-code-docs/SKILL.md
deleted file mode 100644
index a5b33f1..0000000
--- a/skills/claude-code-docs/SKILL.md
+++ /dev/null
@@ -1,69 +0,0 @@
----
-name: claude-code-docs
-description: Answer questions about Claude Code (features, hooks, plugins, skills, MCP, Agent SDK, settings, CLI) from the official docs. Uses the ask CLI to resolve a version-pinned local mirror and csp for semantic search, falling back to grep and WebFetch. Use when the user asks how Claude Code works, what a configuration field does, or whether Claude Code supports something.
-argument-hint: [question]
-arguments: [question]
----
-
-Answer this question about Claude Code using the official documentation:
-
-**$question**
-
-## How to find the answer
-
-Work through these steps, falling back gracefully when a tool is missing.
-
-### 1. Resolve the docs mirror
-
-```bash
-DOCS="$(ask src github:pleaseai/claude-code-docs)/docs"
-```
-
-`ask src` prints the root of a cached checkout of the docs mirror (clones on first use). If the `ask` CLI is not on PATH, run it via npx/bunx instead:
-
-```bash
-DOCS="$(npx -y @pleaseai/ask src github:pleaseai/claude-code-docs)/docs"
-```
-
-Only fall back to step 4 (WebFetch) when neither works, such as offline sandboxes without npm registry access.
-
-### 2. Search for relevant pages
-
-Prefer semantic search with csp, scoped to the per-page markdown:
-
-```bash
-csp search "$question" "$DOCS" --content docs --top-k 8
-```
-
-Or equivalently via ask (requires csp on PATH):
-
-```bash
-ask search github:pleaseai/claude-code-docs "$question" --content docs --top-k 8
-```
-
-If csp is not on PATH, run it via npx/bunx:
-
-```bash
-npx -y @pleaseai/csp search "$question" "$DOCS" --content docs --top-k 8
-```
-
-If that fails too, fall back to grep over the mirror — search for 2-3 distinct keyword variants, not one long phrase:
-
-```bash
-grep -ril "<keyword>" "$DOCS"
-```
-
-The manifest at `$DOCS/../llms.txt` lists every page with a one-line summary; reading it is a fast way to shortlist pages when keyword search is noisy.
-
-### 3. Read and answer
-
-Read the top matching pages (whole pages — they are small). Ground every claim in what the pages actually say:
-
-- Answer in the user's language; keep code identifiers, field names, and flags verbatim.
-- Cite each source page with its canonical URL: a mirror file `$DOCS/hooks.md` corresponds to `https://code.claude.com/docs/en/hooks`.
-- Quote exact field names, JSON shapes, and version requirements (`min-version` markers) when they matter.
-- If the docs do not answer the question, say so explicitly — do not fill gaps from memory.
-
-### 4. Fallback: WebFetch
-
-If the `ask` CLI is unavailable, fetch `https://code.claude.com/docs/llms.txt`, pick the relevant page URLs from the manifest, and fetch each as `<page-url>.md` (this plugin's hook rewrites page URLs to `.md` automatically). Then answer as in step 3.