diff --git a/.agents/plugins/marketplace.json b/.agents/plugins/marketplace.json
new file mode 100644
index 0000000..5d66a68
--- /dev/null
+++ b/.agents/plugins/marketplace.json
@@ -0,0 +1,20 @@
+{
+  "name": "ml-energy-data",
+  "interface": {
+    "displayName": "ML.ENERGY Data"
+  },
+  "plugins": [
+    {
+      "name": "skill",
+      "source": {
+        "source": "local",
+        "path": "./."
+      },
+      "policy": {
+        "installation": "AVAILABLE",
+        "authentication": "ON_INSTALL"
+      },
+      "category": "Coding"
+    }
+  ]
+}
diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json
index ea71065..4848b8e 100644
--- a/.claude-plugin/marketplace.json
+++ b/.claude-plugin/marketplace.json
@@ -4,7 +4,7 @@
     "name": "Jae-Won Chung",
     "email": "jwnchung@umich.edu"
   },
-  "description": "ML.ENERGY Data Toolkit plugins for Claude Code.",
+  "description": "ML.ENERGY Data Toolkit plugins for AI coding agents.",
   "plugins": [
     {
       "name": "skill",
diff --git a/.codex-plugin/plugin.json b/.codex-plugin/plugin.json
new file mode 100644
index 0000000..f185f52
--- /dev/null
+++ b/.codex-plugin/plugin.json
@@ -0,0 +1,30 @@
+{
+  "name": "skill",
+  "description": "Analyze The ML.ENERGY Benchmark data with the mlenergy-data Python toolkit.",
+  "author": {
+    "name": "Jae-Won Chung",
+    "email": "jwnchung@umich.edu"
+  },
+  "homepage": "https://ml.energy/data",
+  "repository": "https://github.com/ml-energy/data",
+  "license": "Apache-2.0",
+  "keywords": [
+    "ml-energy",
+    "benchmark",
+    "gpu",
+    "energy",
+    "inference"
+  ],
+  "skills": "./skills/",
+  "interface": {
+    "displayName": "ML.ENERGY Data",
+    "shortDescription": "Analyze ML inference energy benchmark data",
+    "longDescription": "Use the mlenergy-data Python toolkit to query and compare LLM and diffusion inference energy, latency, throughput, and power measurements on H100 and B200 GPUs.",
+    "developerName": "ML.ENERGY",
+    "category": "Coding",
+    "capabilities": [
+      "Interactive"
+    ],
+    "websiteURL": "https://ml.energy/data"
+  }
+}
diff --git a/README.md b/README.md
index 8bbf9a8..04120a5 100644
--- a/README.md
+++ b/README.md
@@ -69,20 +69,28 @@ for arch, group in runs.task("gpqa").gpu_model("B200").group_by("architecture").
 For Claude Code, install via the bundled plugin marketplace:
 
 ```
+# Inside Claude Code
 /plugin marketplace add ml-energy/data
 /plugin install skill@ml-energy-data
 ```
 
-For other tools, drop the skill directly into that tool's skills directory:
+For Codex, add the marketplace from your shell:
 
 ```bash
-# or ~/.config/goose/skills, ~/.gemini/skills, ~/.claude/skills, ...
-mkdir -p ~/.cursor/skills && \
-  curl -fsSL https://github.com/ml-energy/data/archive/refs/heads/master.tar.gz | \
-  tar -xz -C ~/.cursor/skills --strip-components=2 'data-master/skills/mlenergy-data'
+codex plugin marketplace add ml-energy/data
 ```
 
-Gemini CLI also supports `gemini skills install https://github.com/ml-energy/data --consent --scope user` directly.
+Then install the plugin from inside Codex:
+
+```text
+/plugins
+```
+
+In the plugin browser, select the `ml-energy-data` marketplace and install `skill`.
+
+Gemini CLI also supports `gemini skills install https://github.com/ml-energy/data --path skills`.
+
+For other tools, you can download the `skills/` directory and place it in the appropriate skills directory.
 
 ## Documentation