@a5c-ai/babysitter-codex 5.0.1-staging.686c8b317 → 5.0.1-staging.69cb593ea536

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "babysitter",
3
- "version": "5.0.1-staging.686c8b317",
3
+ "version": "5.0.1-staging.69cb593ea536",
4
4
  "description": "Orchestrate complex, multi-step workflows with event-sourced state management, hook-based extensibility, and human-in-the-loop approval",
5
5
  "author": {
6
6
  "name": "a5c.ai",
@@ -104,7 +104,7 @@ function ensureMarketplaceEntry(marketplacePath, pluginRoot) {
104
104
  name: PLUGIN_NAME,
105
105
  source: relSource,
106
106
  description: "Orchestrate complex, multi-step workflows with event-sourced state management, hook-based extensibility, and human-in-the-loop approval",
107
- version: "5.0.1-staging.686c8b317",
107
+ version: "5.0.1-staging.69cb593ea536",
108
108
  author: { name: "a5c.ai" },
109
109
  };
110
110
  if (idx >= 0) marketplace.plugins[idx] = entry;
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@a5c-ai/babysitter-codex",
3
- "version": "5.0.1-staging.686c8b317",
3
+ "version": "5.0.1-staging.69cb593ea536",
4
4
  "description": "Orchestrate complex, multi-step workflows with event-sourced state management, hook-based extensibility, and human-in-the-loop approval",
5
5
  "scripts": {
6
6
  "test": "npm run validate:ci",
@@ -5,4 +5,8 @@ description: Orchestrate a babysitter run. use this command to start babysitting
5
5
 
6
6
  # call
7
7
 
8
- Invoke the babysitter:babysit skill (using the Skill tool) and follow its instructions (SKILL.md).
8
+ Invoke the babysitter:babysit skill (using the Skill tool) and follow its instructions (SKILL.md). Then continue executing the returned instructions in this same turn. Do not stop after the Skill tool returns; carry the requested run through to completion proof.
9
+
10
+ User arguments for this command:
11
+
12
+ $ARGUMENTS
@@ -5,4 +5,8 @@ description: Orchestrate a babysitter run. use this command to start babysitting
5
5
 
6
6
  # yolo
7
7
 
8
- Invoke the babysitter:babysit skill (using the Skill tool) and follow its instructions (SKILL.md). but without any user interaction or breakpoints in the run.
8
+ 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.
9
+
10
+ User arguments for this command:
11
+
12
+ $ARGUMENTS