claude-warden 1.8.3 → 2.0.1

package/.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "plugins": [
     {
-      "name": "claude-warden",
+      "name": "warden",
       "description": "Auto-approves safe commands, blocks dangerous ones, prompts for the rest",
       "version": "1.0.1",
       "author": {

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
-  "name": "claude-warden",
-  "version": "1.8.3",
+  "name": "warden",
+  "version": "2.0.1",
   "description": "Smart command safety filter for Claude Code — parses shell pipelines and evaluates per-command safety rules to auto-approve safe commands and block dangerous ones",
   "author": {
     "name": "banyudu"

package/README.md

@@ -48,7 +48,7 @@ Two commands inside Claude Code:
 
 ```
 /plugin marketplace add banyudu/claude-warden
-/plugin install claude-warden@claude-warden
+/plugin install warden@claude-warden
 ```
 
 That's it. Restart Claude Code and Warden is active.
@@ -68,6 +68,27 @@ cd claude-warden && npm install && npm run build
 claude --plugin-dir ./claude-warden
 ```
 
+## Codex CLI (experimental)
+
+Codex currently uses `execpolicy` (`.rules` files) for command approvals. Warden can export your effective command-level decisions to a Codex rules file:
+
+```bash
+pnpm run build
+pnpm run codex:export-rules
+```
+
+This writes `.codex/rules/warden.rules` in the current project by default.
+
+- Use `--cwd <dir>` to choose which workspace config to load.
+- Use `--out <path>` to choose an output path.
+- Use `--stdout` to print the generated rules.
+
+Example:
+
+```bash
+node dist/codex-export.cjs --cwd . --out .codex/rules/warden.rules
+```
+
 ## Configure
 
 Warden works out of the box with sensible defaults. To customize, create a config file:
@@ -133,14 +154,37 @@ rules:
         description: Read-only docker commands
 ```
 
-## Feedback and `/claude-warden:warden-allow`
+## YOLO mode
+
+Need to temporarily bypass all permission prompts? YOLO mode auto-allows all commands for a limited time or the full session — while still blocking always-deny commands (like `sudo`, `shutdown`) for safety.
+
+### Activate via slash command
+
+```
+/warden:yolo session    # Full session, no expiry
+/warden:yolo 5m         # 5 minutes
+/warden:yolo 15m        # 15 minutes
+/warden:yolo off        # Turn off immediately
+```
+
+Running `/warden:yolo` with no arguments shows a menu of duration options.
+
+### How it works
+
+YOLO mode is **session-scoped** — it only affects the current Claude Code session. The hook intercepts special activation commands and stores state in a temp file keyed by session ID. When a command is evaluated during YOLO mode, the hook skips normal rule evaluation and auto-allows (except always-deny commands). Expired YOLO states are cleaned up automatically.
+
+### Discovery
+
+When Warden prompts you for permission (`ask` decision), the system message includes a tip about YOLO mode so you can discover it when you need it most.
+
+## Feedback and `/warden:allow`
 
 When Warden blocks or flags a command, it includes a system message explaining:
 
 1. **Why** the command was blocked/flagged (per-command reasons)
 2. **How to allow it** — a ready-to-use YAML snippet for your config
 
-Use the `/claude-warden:warden-allow` slash command to apply the suggested config change. It will ask which scope (project or user) to use.
+Use the `/warden:allow` slash command to apply the suggested config change. It will ask which scope (project or user) to use.
 
 ## Built-in defaults
 

package/config/warden.default.yaml

@@ -86,9 +86,36 @@ notifyOnDeny: true
 
 # Command-specific rules (override built-in rules by command name).
 # The first scope (project > user > default) with a rule for a given command wins.
+#
+# IMPORTANT: Rules are matched by the command being executed, not by arguments.
+# For example, when Claude runs `python -c "import foo"`, warden looks up rules
+# for command: "python" — NOT "bash" or "sh". A common mistake is writing rules
+# for "bash" with argPatterns matching "python"; this won't work because warden
+# sees the command as "python".
+#
 # rules:
+#   # Allow all python commands
+#   - command: python
+#     default: allow
+#
+#   # Allow python -c but ask for other python usage
+#   - command: python
+#     default: ask
+#     argPatterns:
+#       - match:
+#           anyArgMatches: ['^-c$']
+#         decision: allow
+#         description: Allow python -c inline scripts
+#
+#   # Allow all node.js execution
+#   - command: node
+#     default: allow
+#
+#   # Trust all npx in this project
 #   - command: npx
-#     default: allow          # Trust all npx in this project
+#     default: allow
+#
+#   # Docker with selective allow
 #   - command: docker
 #     default: ask
 #     argPatterns: