@wular/coder 0.1.24 → 0.1.25

package/README.md

@@ -21,52 +21,56 @@ Plugs into Claude Code or Codex to enable the harness with Coder instances.
 
 ## Get started
 
-Coder runs your tasks on an **engine CLI** - it needs at least one of the [codex CLI](https://github.com/openai/codex) (`npm install -g @openai/codex`, then `codex login`) or the [Claude Code CLI](https://github.com/anthropics/claude-code) (`npm install -g @anthropic-ai/claude-code`, then `claude auth login`) installed and logged in. `coder host-setup` reports which are ready; if none is, install one of them to run tasks.
+**1. Install a host plugin.**
 
-Follow the install host specific guides below, then you can ask like:
+Pick the host you use (or both):
 
-> Use Coder to explain the directory structure of the workspace.
-
-You can also add this to CLAUDE.md.
-
-> Always use Coder for all implementation and system exploring tasks.
-
-The work happens in the engine, and your session gets the result. Codex is the primary engine when available, with a Claude subagent as fallback.
-
-### Claude Code
+<table>
+<tr><th>Claude Code</th><th>Codex</th></tr>
+<tr valign="top">
+<td>
 
 ```
 /plugin marketplace add muzam1l/coder
-
 /plugin install coder@coder-plugins
-
 /reload-plugins
-
 /coder:setup
 ```
 
-Or from the shell:
-
-```
-npm install -g @wular/coder
-coder host-setup --claude
-```
-
-### Codex
+</td>
+<td>
 
 ```
 codex plugin marketplace add muzam1l/coder
 codex plugin add coder@coder-plugins
 ```
 
-Or from the npm directly:
+</td>
+</tr>
+</table>
 
-```
+Or do it from the shell instead of slash commands - this installs the same plugin:
+
+```bash
 npm install -g @wular/coder
-coder host-setup --codex
+coder host-setup --claude   # or --codex
 ```
 
-Note: Codex 'Approve for me' just disables invoking CLI agents, so just use 'Ask for approval'/'Full Access' when using Codex/ChatGPT app as host.
+**2. Install at least one engine CLI**, logged in: [codex](https://github.com/openai/codex) (`npm install -g @openai/codex && codex login`) or [Claude Code](https://github.com/anthropics/claude-code) (`npm install -g @anthropic-ai/claude-code && claude auth login`). Run `coder host-setup` any time to check which engines are ready.
+
+**3. Ask your host to use it:**
+
+> Use Coder to explain the directory structure of the workspace.
+
+Or make it the default in AGENTS.md/CLAUDE.md:
+
+> Always use Coder for all implementation and system exploring tasks.
+
+The work happens in the engine, and your session gets the result. Codex is the primary engine when available, with a Claude subagent as fallback.
+
+_Recommended setup: Claude Code as host (fable model preferably), Codex as engine - best for performance and cost distribution._
+
+Note: with Codex as host, use "Ask for approval"/"Full Access", not "Approve for me" - the latter disables invoking CLI agents.
 
 ## Staying up to date
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@wular/coder",
-  "version": "0.1.24",
+  "version": "0.1.25",
   "description": "Delegating coding-agent runtime",
   "type": "module",
   "bin": {

package/plugins/claude/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "coder",
-  "version": "0.1.24",
+  "version": "0.1.25",
   "description": "Delegate coding tasks to a Coder subagent. Your main context stays clean.",
   "author": {
     "name": "muzam1l"

package/plugins/claude/skills/handle/SKILL.md

@@ -39,6 +39,10 @@ If `coder` is not on PATH, install it yourself without asking (`npm install -g @
 
 When no coder engine can start (missing binaries, auth, quota across the whole chain), the runtime exits 3 with a JSON payload (`fallback.action: "run-native-subagent"`). Mention the failure to the user (including any limit-reset time), then run the task with your own subagent facility: spawn one `general-purpose` subagent via the Agent tool whose prompt is the payload's `task` verbatim, prefixed with: "NEVER run git write operations (commit, checkout, stash, reset, push, etc.); leave changes uncommitted." If the payload's `permissions` is not `auto`, append it: `read-only` means investigate and report without modifying anything; `workspace-write` means never touch anything outside the workspace. Relay its output when it completes.
 
+## Supervision loop
+
+With coders running in the background, don't fire-and-forget: schedule recurring check-ins (the `/loop` skill or ScheduleWakeup; interval by the work's pace, 10m default). Each tick: `coder task list`, fetch finished results, dispatch newly unblocked coders, steer stuck ones, stop off-track ones, surface pending approvals. Stop the loop when all tasks are done and relayed.
+
 ## Controlling tasks
 
 - Continue prior work ("keep going", "apply the top fix"): `coder task steer <task-id> "<follow-up>"`.

package/plugins/codex/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "coder",
-  "version": "0.1.24",
+  "version": "0.1.25",
   "interface": {
     "displayName": "Coder (plugin)"
   },

package/plugins/codex/skills/handle/SKILL.md

@@ -33,6 +33,10 @@ When you run setup, also check codex is new enough for the default GPT-5.6 model
 - Permissions default to auto mode. Pass `--permissions read-only` when the task is read-only; `--permissions workspace-write` to forbid any escalation beyond the project.
 - A background dispatch prints a task id plus its result/steer/stop commands. Relay them and fetch the result (above) rather than polling.
 
+## Supervision loop
+
+With coders running in the background, don't fire-and-forget: run a recurring monitoring loop in this task (interval by the work's pace, 10m default). Each tick: `coder task list`, fetch finished results, dispatch newly unblocked coders, steer stuck ones, stop off-track ones, surface pending approvals. Stop the loop when all tasks are done and relayed.
+
 ## Controlling tasks
 
 - Continue prior work ("keep going", "apply the top fix"): `coder task steer <task-id> "<follow-up>"`.

package/plugins/cursor/.cursor-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "coder",
   "displayName": "Coder",
-  "version": "0.1.24",
+  "version": "0.1.25",
   "description": "Delegate coding tasks to a Coder subagent. Your main context stays clean.",
   "author": {
     "name": "muzam1l"

package/plugins/cursor/skills/handle/SKILL.md

@@ -32,6 +32,10 @@ When you run setup, also check codex is new enough for the default GPT-5.6 model
 - Permissions default to auto mode. Pass `--permissions read-only` when the task is read-only; `--permissions workspace-write` to forbid any escalation beyond the project.
 - A background dispatch prints a task id plus its result/steer/stop commands. Relay them and fetch the result (above) rather than polling.
 
+## Supervision loop
+
+With coders running in the background, don't fire-and-forget: run a recurring monitoring loop in this session (interval by the work's pace, 10m default). Each tick: `coder task list`, fetch finished results, dispatch newly unblocked coders, steer stuck ones, stop off-track ones, surface pending approvals. Stop the loop when all tasks are done and relayed.
+
 ## Controlling tasks
 
 - Continue prior work ("keep going", "apply the top fix"): `coder task steer <task-id> "<follow-up>"`.