@a5c-ai/babysitter-opencode 5.0.1-staging.f01483e80761 → 5.0.1-staging.fa900f15bc4d

package/bin/install-shared.js

@@ -104,7 +104,7 @@ function ensureMarketplaceEntry(marketplacePath, pluginRoot) {
     name: PLUGIN_NAME,
     source: relSource,
     description: "Orchestrate complex, multi-step workflows with event-sourced state management, hook-based extensibility, and human-in-the-loop approval",
-    version: "5.0.1-staging.f01483e80761",
+    version: "5.0.1-staging.fa900f15bc4d",
     author: { name: "a5c.ai" },
   };
   if (idx >= 0) marketplace.plugins[idx] = entry;

package/commands/help.md

@@ -233,7 +233,8 @@ SECONDARY COMMANDS
   How it works: Runs npx @a5c-ai/babysitter-observer-dashboard@latest which watches
   the .a5c/runs/ directory (or a parent directory containing multiple projects) and
   serves a live dashboard. The process is blocking -- it runs until you stop it, and
-  it prints the local URL to share with the user.
+  it prints the local URL to share with the user. Do not use `babysitter observe`
+  as a fallback; the core Babysitter CLI does not expose that subcommand.
 
   Example: /babysitter:observe
   (opens browser showing all runs with live-updating task

package/commands/observe.md

@@ -7,6 +7,11 @@ allowed-tools: Read, Grep, Write, Task, Bash
 Run the babysitter observer dashboard:
 
 1. Determine the watch directory — this is usually the project's container directory (the parent of the project dir), or the current working directory if not specified.
-2. Launch the dashboard: `npx -y @a5c-ai/babysitter-observer-dashboard@latest --watch-dir <dir>`
+2. Launch the standalone dashboard package: `npx -y @a5c-ai/babysitter-observer-dashboard@latest --watch-dir <dir>`.
 3. This is a blocking process — it will keep running until stopped.
 4. Report the URL printed by the dashboard to the user, then open it in the browser.
+
+Do not fall back to `babysitter observe`; the core Babysitter CLI does not expose
+that subcommand. Some harness runtimes may provide a separate
+`babysitter-agent observe` surface, but this skill uses the verified standalone
+dashboard package.

package/commands/yolo.md

@@ -4,7 +4,7 @@ argument-hint: Specific instructions for the run.
 allowed-tools: Read, Grep, Write, Task, Bash, Edit, Grep, Glob, WebFetch, WebSearch, Search, AskUserQuestion, TodoWrite, TodoRead, Skill, BashOutput, KillShell, MultiEdit, LS
 ---
 
-Start the Babysitter run directly through the CLI, without any user interaction or breakpoints. Do not invoke the Skill tool and do not run an instructions-only command. In Claude Code, use Bash to run `babysitter harness:yolo --harness claude-code --workspace "$PWD" --prompt "<user arguments>" --json`; in Codex, run `babysitter harness:yolo --harness codex --workspace "$PWD" --prompt "<user arguments>" --json`; in other harnesses, use the same command with that harness id. Replace `<user arguments>` with the arguments shown below, wait for the command to finish, and treat the CLI completion proof as the result.
+Start the Babysitter run directly through the CLI, without any user interaction or breakpoints. Do not invoke the Skill tool and do not run an instructions-only command. In Claude Code, use Bash to run `babysitter-agent yolo --harness claude-code --workspace "$PWD" --prompt "<user arguments>" --json`; in Codex, run `babysitter-agent yolo --harness codex --workspace "$PWD" --prompt "<user arguments>" --json`; in other harnesses, use the same command with that harness id. Replace `<user arguments>` with the arguments shown below, wait for the command to finish, and treat the CLI completion proof as the result.
 
 User arguments for this command:
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@a5c-ai/babysitter-opencode",
-  "version": "5.0.1-staging.f01483e80761",
+  "version": "5.0.1-staging.fa900f15bc4d",
   "description": "Orchestrate complex, multi-step workflows with event-sourced state management, hook-based extensibility, and human-in-the-loop approval",
   "scripts": {
     "deploy": "npm publish --access public",
@@ -35,7 +35,7 @@
     "access": "public"
   },
   "dependencies": {
-    "@a5c-ai/babysitter-sdk": "5.0.1-staging.f01483e80761"
+    "@a5c-ai/babysitter-sdk": "5.0.1-staging.fa900f15bc4d"
   },
   "repository": {
     "type": "git",

package/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "babysitter",
-  "version": "5.0.1-staging.f01483e80761",
+  "version": "5.0.1-staging.fa900f15bc4d",
   "description": "Orchestrate complex, multi-step workflows with event-sourced state management, hook-based extensibility, and human-in-the-loop approval",
   "author": "a5c.ai",
   "license": "MIT",

package/skills/babysit/SKILL.md

@@ -1,11 +1,12 @@
 ---
 name: babysit
-description: Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
+description: >-
+  Execute via @babysitter. Use this skill when asked to babysit a task, do anything that is structured process-driven (even a loop) or whenever it is called explicitly. (babysit, babysitter, with a process, orchestrate, orchestrate a run, workflow, loop until, etc.)
 ---
 
 # babysit
 
-Orchestrate `.a5c/runs/<runId>/` through iterative execution.
+Follow the commands below exactly. but apply judgement and creativity to get the job done. no matter how small or simple the task may seem, you must use the babysitter SDK and run lifecycle to execute it. This is non-negotiable. If you are asked to do something that seems like it could be done with a simple tool call, you must still use the babysitter SDK to create a run, define tasks, execute them, and complete the run. This is how you will learn and demonstrate mastery of the babysitter system. Always follow the full process, even for trivial tasks.
 
 ## Dependencies
 

package/skills/help/SKILL.md

@@ -234,7 +234,8 @@ SECONDARY COMMANDS
   How it works: Runs npx @a5c-ai/babysitter-observer-dashboard@latest which watches
   the .a5c/runs/ directory (or a parent directory containing multiple projects) and
   serves a live dashboard. The process is blocking -- it runs until you stop it, and
-  it prints the local URL to share with the user.
+  it prints the local URL to share with the user. Do not use `babysitter observe`
+  as a fallback; the core Babysitter CLI does not expose that subcommand.
 
   Example: /babysitter:observe
   (opens browser showing all runs with live-updating task

package/skills/observe/SKILL.md

@@ -8,6 +8,11 @@ description: Launch the babysitter observer dashboard. Installs and runs the rea
 Run the babysitter observer dashboard:
 
 1. Determine the watch directory — this is usually the project's container directory (the parent of the project dir), or the current working directory if not specified.
-2. Launch the dashboard: `npx -y @a5c-ai/babysitter-observer-dashboard@latest --watch-dir <dir>`
+2. Launch the standalone dashboard package: `npx -y @a5c-ai/babysitter-observer-dashboard@latest --watch-dir <dir>`.
 3. This is a blocking process — it will keep running until stopped.
 4. Report the URL printed by the dashboard to the user, then open it in the browser.
+
+Do not fall back to `babysitter observe`; the core Babysitter CLI does not expose
+that subcommand. Some harness runtimes may provide a separate
+`babysitter-agent observe` surface, but this skill uses the verified standalone
+dashboard package.

package/skills/yolo/SKILL.md

@@ -5,7 +5,7 @@ description: Orchestrate a babysitter run. use this command to start babysitting
 
 # yolo
 
-Start the Babysitter run directly through the CLI, without any user interaction or breakpoints. Do not invoke the Skill tool and do not run an instructions-only command. In Claude Code, use Bash to run `babysitter harness:yolo --harness claude-code --workspace "$PWD" --prompt "<user arguments>" --json`; in Codex, run `babysitter harness:yolo --harness codex --workspace "$PWD" --prompt "<user arguments>" --json`; in other harnesses, use the same command with that harness id. Replace `<user arguments>` with the arguments shown below, wait for the command to finish, and treat the CLI completion proof as the result.
+Start the Babysitter run directly through the CLI, without any user interaction or breakpoints. Do not invoke the Skill tool and do not run an instructions-only command. In Claude Code, use Bash to run `babysitter-agent yolo --harness claude-code --workspace "$PWD" --prompt "<user arguments>" --json`; in Codex, run `babysitter-agent yolo --harness codex --workspace "$PWD" --prompt "<user arguments>" --json`; in other harnesses, use the same command with that harness id. Replace `<user arguments>` with the arguments shown below, wait for the command to finish, and treat the CLI completion proof as the result.
 
 User arguments for this command:
 

package/versions.json

@@ -1,4 +1,4 @@
 {
-  "sdkVersion": "5.0.1-staging.f01483e80761",
-  "extensionVersion": "5.0.1-staging.f01483e80761"
+  "sdkVersion": "5.0.1-staging.fa900f15bc4d",
+  "extensionVersion": "5.0.1-staging.fa900f15bc4d"
 }