@a5c-ai/babysitter-opencode 0.1.4-staging.fd3ab4c2 → 5.0.1-staging.04ca6ab00d21

package/hooks/babysitter-proxied-tool-execute-after.sh

@@ -0,0 +1,3 @@
+#!/bin/bash
+set -euo pipefail
+babysitter hook:run --harness unified --hook-type post-tool-use --json

package/hooks/babysitter-proxied-tool-execute-before.js

@@ -0,0 +1,24 @@
+#!/usr/bin/env node
+"use strict";
+var execSync = require("child_process").execSync;
+var path = require("path");
+var readFileSync = require("fs").readFileSync;
+
+var PLUGIN_ROOT = process.env.PLUGIN_ROOT || process.env.PLUGIN_ROOT || path.resolve(__dirname, "..");
+var stdin = "";
+try { stdin = readFileSync(0, "utf8"); } catch {}
+try {
+  var result = execSync("bash " + JSON.stringify(path.join(PLUGIN_ROOT, "hooks/pre-tool-use.sh")), {
+    input: stdin,
+    stdio: ["pipe", "pipe", "pipe"],
+    timeout: 30000,
+    env: Object.assign({}, process.env, {
+      HOOK_TYPE: process.env.HOOK_TYPE || "",
+      ADAPTER_NAME: process.env.ADAPTER_NAME || "opencode",
+      PLUGIN_ROOT: PLUGIN_ROOT
+    })
+  });
+  process.stdout.write(result);
+} catch (e) {
+  process.stdout.write("{}\n");
+}

package/hooks/babysitter-proxied-tool-execute-before.sh

@@ -0,0 +1,3 @@
+#!/bin/bash
+set -euo pipefail
+babysitter hook:run --harness unified --hook-type pre-tool-use --json

package/hooks/hooks.json

@@ -1,45 +1,37 @@
 {
   "version": 1,
-  "description": "Babysitter hook registration for OpenCode. Maps OpenCode plugin events to babysitter hook scripts.",
+  "description": "babysitter hook registration for OpenCode.",
   "hooks": {
     "session.created": [
       {
         "type": "command",
-        "script": "hooks/session-created.js",
-        "description": "Initialize babysitter session state and inject context",
+        "script": "./hooks/babysitter-proxied-session-created.js",
+        "description": "babysitter SessionStart hook",
         "timeoutMs": 30000
       }
     ],
-    "session.idle": [
+    "tool.execute.before": [
       {
         "type": "command",
-        "script": "hooks/session-idle.js",
-        "description": "Check for pending babysitter effects when agent goes idle",
+        "script": "./hooks/babysitter-proxied-tool-execute-before.js",
+        "description": "babysitter PreToolUse hook",
         "timeoutMs": 30000
       }
     ],
-    "shell.env": [
-      {
-        "type": "command",
-        "script": "hooks/shell-env.js",
-        "description": "Inject BABYSITTER_SESSION_ID and other env vars into shell",
-        "timeoutMs": 5000
-      }
-    ],
-    "tool.execute.before": [
+    "tool.execute.after": [
       {
         "type": "command",
-        "script": "hooks/tool-execute-before.js",
-        "description": "Pre-tool-use hook for babysitter awareness",
-        "timeoutMs": 10000
+        "script": "./hooks/babysitter-proxied-tool-execute-after.js",
+        "description": "babysitter PostToolUse hook",
+        "timeoutMs": 30000
       }
     ],
-    "tool.execute.after": [
+    "shell.env": [
       {
         "type": "command",
-        "script": "hooks/tool-execute-after.js",
-        "description": "Post-tool-use hook for babysitter awareness",
-        "timeoutMs": 10000
+        "script": "./hooks/babysitter-proxied-shell-env.js",
+        "description": "babysitter ShellEnv hook",
+        "timeoutMs": 5000
       }
     ]
   }

package/package.json

@@ -1,46 +1,48 @@
 {
   "name": "@a5c-ai/babysitter-opencode",
-  "version": "0.1.4-staging.fd3ab4c2",
-  "description": "Babysitter orchestration plugin for OpenCode with SDK-managed process-library bootstrapping and in-turn iteration model",
+  "version": "5.0.1-staging.04ca6ab00d21",
+  "description": "Orchestrate complex, multi-step workflows with event-sourced state management, hook-based extensibility, and human-in-the-loop approval",
   "scripts": {
-    "test": "node test/integration.test.js",
-    "test:integration": "node test/integration.test.js",
-    "sync:commands": "node scripts/sync-command-docs.cjs",
-    "postinstall": "node bin/install.cjs",
-    "preuninstall": "node bin/uninstall.cjs",
     "deploy": "npm publish --access public",
-    "deploy:staging": "npm publish --access public --tag staging"
+    "deploy:staging": "npm publish --access public --tag staging",
+    "postinstall": "node bin/install.js",
+    "preuninstall": "node bin/uninstall.js",
+    "team:install": "node scripts/team-install.js",
+    "test": "node test/integration.test.js"
   },
   "bin": {
-    "babysitter-opencode": "bin/cli.cjs"
+    "babysitter-opencode": "bin/cli.js"
   },
   "files": [
     "bin/",
-    "commands/",
     "hooks/",
-    "scripts/",
     "skills/",
+    "commands/",
+    "scripts/",
     "plugin.json",
-    "versions.json"
+    "README.md",
+    "versions.json",
+    "package.json"
   ],
   "keywords": [
     "babysitter",
     "opencode",
-    "orchestration",
-    "ai-agent",
-    "sdk-integration"
+    "orchestration"
   ],
   "author": "a5c.ai",
   "license": "MIT",
   "publishConfig": {
     "access": "public"
   },
+  "dependencies": {
+    "@a5c-ai/babysitter-sdk": "5.0.1-staging.04ca6ab00d21"
+  },
   "repository": {
     "type": "git",
-    "url": "https://github.com/a5c-ai/babysitter"
+    "url": "git+https://github.com/a5c-ai/babysitter-opencode.git"
   },
-  "homepage": "https://github.com/a5c-ai/babysitter/tree/main/plugins/babysitter-opencode#readme",
-  "dependencies": {
-    "@a5c-ai/babysitter-sdk": "0.0.188-staging.fd3ab4c2"
+  "homepage": "https://github.com/a5c-ai/babysitter-opencode#readme",
+  "bugs": {
+    "url": "https://github.com/a5c-ai/babysitter-opencode/issues"
   }
 }

package/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "babysitter",
-  "version": "0.1.0",
-  "description": "Orchestrate complex, multi-step workflows with event-sourced state management, hook-based extensibility, and human-in-the-loop approval -- powered by the Babysitter SDK",
+  "version": "5.0.1-staging.04ca6ab00d21",
+  "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",
   "harness": "opencode",
@@ -18,8 +18,10 @@
     "automation",
     "event-sourced",
     "hooks",
-    "opencode",
+    "TDD",
+    "quality-convergence",
     "agent",
-    "LLM"
+    "LLM",
+    "opencode"
   ]
 }

package/scripts/create-release-tag.mjs

@@ -0,0 +1,18 @@
+#!/usr/bin/env node
+import { spawnSync } from 'node:child_process';
+import { existsSync, readFileSync } from 'node:fs';
+
+function run(command, args) {
+  const result = spawnSync(command, args, { encoding: 'utf8', stdio: 'inherit' });
+  if (result.status !== 0) process.exit(result.status || 1);
+}
+
+const branch = process.env.GITHUB_REF_NAME || 'develop';
+const sha = (process.env.GITHUB_SHA || '').slice(0, 12);
+const version = existsSync('package.json') ? JSON.parse(readFileSync('package.json', 'utf8')).version : JSON.parse(readFileSync('versions.json', 'utf8')).sdkVersion;
+const normalized = String(version).replace(/[^0-9A-Za-z._-]/g, '-');
+const tag = 'release/' + branch + '/v' + normalized + '-' + sha;
+run('git', ['config', 'user.name', 'github-actions[bot]']);
+run('git', ['config', 'user.email', 'github-actions[bot]@users.noreply.github.com']);
+run('git', ['tag', tag]);
+run('git', ['push', 'origin', tag]);

package/scripts/publish-from-tag.mjs

@@ -0,0 +1,41 @@
+#!/usr/bin/env node
+import { spawnSync } from 'node:child_process';
+import { readFileSync } from 'node:fs';
+
+function run(command, args, options = {}) {
+  const result = spawnSync(command, args, { stdio: options.stdio || 'inherit', encoding: options.encoding });
+  if (result.status !== 0 && !options.allowFailure) process.exit(result.status || 1);
+  return result;
+}
+
+function npmView(packageSpec) {
+  return run('npm', ['view', packageSpec, 'version'], { allowFailure: true, stdio: 'pipe', encoding: 'utf8' }).status === 0;
+}
+
+const pkg = JSON.parse(readFileSync('package.json', 'utf8'));
+const ref = process.env.GITHUB_REF_NAME || '';
+const branch = ref.split('/')[1] || 'develop';
+const tag = branch === 'main' ? 'latest' : branch;
+
+if (!process.env.NODE_AUTH_TOKEN) {
+  console.log('NODE_AUTH_TOKEN is not configured; skipping npm publish.');
+  process.exit(0);
+}
+
+if (npmView(pkg.name + '@' + pkg.version)) {
+  console.log(pkg.name + '@' + pkg.version + ' already exists; ensuring dist-tag ' + tag + '.');
+  run('npm', ['dist-tag', 'add', pkg.name + '@' + pkg.version, tag], { allowFailure: true });
+  process.exit(0);
+}
+
+for (const field of ['dependencies', 'peerDependencies', 'optionalDependencies']) {
+  for (const [name, version] of Object.entries(pkg[field] || {})) {
+    if (!name.startsWith('@a5c-ai/') || version.startsWith('^') || version.startsWith('~') || version === '*' || version.startsWith('workspace:')) continue;
+    if (!npmView(name + '@' + version)) {
+      console.log('Required internal dependency ' + name + '@' + version + ' is not published yet; skipping npm publish.');
+      process.exit(0);
+    }
+  }
+}
+
+run('npm', ['publish', '--access', 'public', '--tag', tag]);

package/scripts/team-install.js

@@ -0,0 +1,23 @@
+#!/usr/bin/env node
+'use strict';
+
+var path = require('path');
+var shared = require('../bin/install-shared');
+
+var workspace = process.cwd();
+for (var i = 0; i < process.argv.length; i++) {
+  if (process.argv[i] === '--workspace' && process.argv[i + 1]) {
+    workspace = path.resolve(process.argv[i + 1]);
+  }
+}
+
+var src = process.env.PLUGIN_PACKAGE_ROOT || path.resolve(__dirname, '..');
+var dest = shared.getHomePluginRoot('workspace');
+console.log('[babysitter] Team install to ' + dest);
+
+shared.copyPluginBundle(src, dest);
+if (typeof shared.harnessTeamInstall === 'function') {
+  shared.harnessTeamInstall(src, dest, workspace);
+}
+shared.runPostInstall(dest);
+console.log('[babysitter] Team install complete.');

package/skills/accomplish-status/SKILL.md

@@ -29,7 +29,9 @@ Where `OPENCODE_CONFIG_DIR` is resolved from the `OPENCODE_CONFIG_DIR` environme
 Read the SDK version from `versions.json` to ensure version compatibility:
 
 ```bash
-SDK_VERSION=$(node -e "try{const fs=require('fs');const probes=['./plugins/babysitter-opencode/versions.json','./node_modules/@a5c-ai/babysitter-opencode/versions.json'];for(const probe of probes){if(fs.existsSync(probe)){console.log(JSON.parse(fs.readFileSync(probe,'utf8')).sdkVersion||'latest');process.exit(0)}}console.log('latest')}catch{console.log('latest')}")
+SDK_VERSION=$(node -e "try{const fs=require('fs');const probes=['./plugins/babysitter-unified/versions.json','./node_modules/@a5c-ai/babysitter-opencode/versions.json'];for(const probe of probes){if(fs.existsSync(probe)){console.log(JSON.parse(fs.readFileSync(probe,'utf8')).sdkVersion||'latest');process.exit(0)}}console.log('latest')}catch{console.log('latest')}")
+npm i -g @a5c-ai/babysitter-sdk@$SDK_VERSION
+
 CLI="npx -y @a5c-ai/babysitter-sdk@$SDK_VERSION"
 ```
 

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
 
@@ -14,7 +15,9 @@ Orchestrate `.a5c/runs/<runId>/` through iterative execution.
 Read the SDK version from `versions.json` to ensure version compatibility:
 
 ```bash
-SDK_VERSION=$(node -e "try{const fs=require('fs');const probes=['./plugins/babysitter-opencode/versions.json','./node_modules/@a5c-ai/babysitter-opencode/versions.json'];for(const probe of probes){if(fs.existsSync(probe)){console.log(JSON.parse(fs.readFileSync(probe,'utf8')).sdkVersion||'latest');process.exit(0)}}console.log('latest')}catch{console.log('latest')}")
+SDK_VERSION=$(node -e "try{const fs=require('fs');const probes=['./plugins/babysitter-unified/versions.json','./node_modules/@a5c-ai/babysitter-opencode/versions.json'];for(const probe of probes){if(fs.existsSync(probe)){console.log(JSON.parse(fs.readFileSync(probe,'utf8')).sdkVersion||'latest');process.exit(0)}}console.log('latest')}catch{console.log('latest')}")
+
+npm i -g @a5c-ai/babysitter-sdk@$SDK_VERSION
 CLI="npx -y @a5c-ai/babysitter-sdk@$SDK_VERSION"
 ```
 

package/skills/call/SKILL.md

@@ -5,4 +5,8 @@ description: Orchestrate a babysitter run. use this command to start babysitting
 
 # call
 
-Invoke the babysitter:babysit skill (using the Skill tool) and follow its instructions (SKILL.md).
+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.
+
+User arguments for this command:
+
+$ARGUMENTS

package/skills/cleanup/SKILL.md

@@ -11,11 +11,33 @@ Create and run a cleanup process using the process at `skills\babysit\process\cr
 
 Implementation notes (for the process):
 - Parse arguments for `--dry-run` flag (if present, set dryRun: true in inputs) and `--keep-days N` (default: 7)
-- The process scans .a5c/runs/ for completed/failed runs, aggregates insights, writes summaries, then removes old data
-- Always show the user what will be removed before removing (in interactive mode via breakpoints)
-- In non-interactive mode (yolo), proceed with cleanup using defaults
-- The insights file goes to docs/run-history-insights.md
-- Only remove terminal runs (completed/failed) older than the keep-days threshold
-- Never remove active/in-progress runs
-- Remove orphaned process files not referenced by remaining runs
-- After cleanup, show remaining run count and disk usage
+
+CRITICAL: The cleanup MUST follow this exact phase order. Do NOT delete any run before Phase 2 completes.
+
+Phase 1 — Scan:
+- Scan .a5c/runs/ for all runs
+- Classify each as terminal (completed/failed) or active (in-progress/created)
+- Identify terminal runs older than the keep-days threshold as removal candidates
+- Never mark active/in-progress runs for removal
+- Count and report: total runs, terminal, active, removal candidates, disk usage
+
+Phase 2 — Aggregate insights (BEFORE any deletion):
+- For EVERY removal candidate, read its run.json and journal/ events
+- Extract: processId, prompt, status, event count, created date, task summaries
+- Group by process type and extract patterns (retry counts, convergence behavior, failure modes)
+- Append a new dated section to docs/run-history-insights.md with:
+  - Summary statistics (runs removed, disk freed, runs retained)
+  - Run categories with counts and descriptions
+  - Key patterns observed (multi-batch convergence, retry behavior, etc.)
+  - What worked well / what didn't from the run data
+- This file MUST be written and verified before proceeding to Phase 3
+
+Phase 3 — Confirm removal:
+- In interactive mode, show the user what will be removed via a breakpoint
+- In non-interactive mode (yolo), proceed with defaults
+- In dry-run mode, stop here and show what would be removed
+
+Phase 4 — Remove:
+- Delete the terminal runs older than keep-days threshold
+- Identify and remove orphaned process files not referenced by remaining runs
+- Show remaining run count and disk usage after cleanup

package/skills/contrib/SKILL.md

@@ -5,30 +5,30 @@ description: Submit feedback or contribute to babysitter project
 
 # contrib
 
-Invoke the babysitter:babysit skill (using the Skill tool) and follow its instructions (SKILL.md).
-
-## Process Routing
-
+Invoke the babysitter:babysit skill (using the Skill tool) and follow its instructions (SKILL.md).
+
+## Process Routing
+
 Contribution processes live under the active process library's `cradle/` directory. Resolve the active library root with `babysitter process-library:active --json` and route based on arguments:
-
-### Issue-based (opens a GitHub issue in a5c-ai/babysitter)
- * **Bug report** → `cradle/bug-report.js#process` — Report a bug in the SDK, CLI, process library, etc.
- * **Feature request** → `cradle/feature-request.js#process` — Request a new feature or enhancement
- * **Documentation question** → `cradle/documentation-question.js#process` — Ask about undocumented behavior or missing docs
-
-### PR-based (forks repo, creates branch, submits PR to a5c-ai/babysitter)
- * **Bugfix** → `cradle/bugfix.js#process` — User already has the fix for a bug
- * **Feature implementation** → `cradle/feature-implementation-contribute.js#process` — User already has a feature implementation
- * **Harness integration** → `cradle/feature-harness-integration-contribute.js#process` — User has a harness (CI/CD, IDE, editor) integration
- * **Library contribution** → `cradle/library-contribution.js#process` — New or improved process/skill/subagent for the library
- * **Documentation answer** → `cradle/documentation-contribute-answer.js#process` — User has an answer for an unanswered docs question
-
-### Router (when arguments are empty or general)
- * **Contribute** → `cradle/contribute.js#process` — Explains contribution types and routes to the specific process
-
-## Contribution Rules
-
- * PR-based contributions: fork the babysitter repo (a5c-ai/babysitter) for the user, ask to star if not already starred, perform changes, submit PR
- * Issue-based contributions: gather details, search for duplicates, review, then open an issue in a5c-ai/babysitter
- * Add breakpoints (permissions) before ALL gh actions (fork, star, submit PR/issue) to allow user review and cancellation
+
+### Issue-based (opens a GitHub issue in a5c-ai/babysitter)
+ * **Bug report** → `cradle/bug-report.js#process` — Report a bug in the SDK, CLI, process library, etc.
+ * **Feature request** → `cradle/feature-request.js#process` — Request a new feature or enhancement
+ * **Documentation question** → `cradle/documentation-question.js#process` — Ask about undocumented behavior or missing docs
+
+### PR-based (forks repo, creates branch, submits PR to a5c-ai/babysitter)
+ * **Bugfix** → `cradle/bugfix.js#process` — User already has the fix for a bug
+ * **Feature implementation** → `cradle/feature-implementation-contribute.js#process` — User already has a feature implementation
+ * **Harness integration** → `cradle/feature-harness-integration-contribute.js#process` — User has a harness (CI/CD, IDE, editor) integration
+ * **Library contribution** → `cradle/library-contribution.js#process` — New or improved process/skill/subagent for the library
+ * **Documentation answer** → `cradle/documentation-contribute-answer.js#process` — User has an answer for an unanswered docs question
+
+### Router (when arguments are empty or general)
+ * **Contribute** → `cradle/contribute.js#process` — Explains contribution types and routes to the specific process
+
+## Contribution Rules
+
+ * PR-based contributions: fork the babysitter repo (a5c-ai/babysitter) for the user, ask to star if not already starred, perform changes, submit PR
+ * Issue-based contributions: gather details, search for duplicates, review, then open an issue in a5c-ai/babysitter
+ * Add breakpoints (permissions) before ALL gh actions (fork, star, submit PR/issue) to allow user review and cancellation
  * If arguments are empty: use the `contribute.js` router process to show options and route accordingly

package/skills/doctor/SKILL.md

@@ -157,7 +157,6 @@ If it exists:
 **Goal:** Inspect babysitter session files for health and detect runaway loops.
 
 - Search for session state files using Glob:
-  - `plugins/babysitter/skills/babysit/state/*.md`
   - `.a5c/state/*.md`
   - `.a5c/state/*.json`
 - For each session state file found:
@@ -261,7 +260,7 @@ Mark as PASS if total size < 500MB and no files > 10MB. Mark as WARN if total si
 
 ### 10a. Hook Registration
 
-- Locate the plugin root. Check for `CLAUDE_PLUGIN_ROOT` env var, or search for `plugins/babysitter/hooks/hooks.json` by walking up from the current directory.
+- Locate the plugin root. Check for `CLAUDE_PLUGIN_ROOT` env var first, or search for a babysitter `hooks.json` by walking up from the current directory.
 - If found, read `hooks.json` and verify:
   - A `Stop` hook entry exists with a command referencing `babysitter-stop-hook.sh`.
   - A `SessionStart` hook entry exists with a command referencing `babysitter-session-start-hook.sh`.
@@ -316,7 +315,7 @@ If the stop hook shows NO evidence of execution (no log entries, no journal even
 
 Perform these diagnostic steps in order and report the first failure found:
 
-1. **Plugin not installed**: Check if `plugins/babysitter/` exists relative to the project root and if `CLAUDE_PLUGIN_ROOT` is set. If the plugin directory doesn't exist, report: "Plugin not installed — the babysitter plugin directory is missing."
+1. **Plugin not installed**: Check if `CLAUDE_PLUGIN_ROOT` is set or if a babysitter plugin directory exists relative to the project root. If neither exists, report: "Plugin not installed — the babysitter plugin directory is missing."
 
 2. **Plugin not enabled**: Check for Claude settings files:
    - `~/.claude/settings.json` — look for `babysitter` in `enabledPlugins`.
@@ -363,13 +362,13 @@ Mark as FAIL if:
 - Parse the output and inspect the `resolvedFrom` field. Classify as follows:
   - `resolvedFrom: "pid-marker"` → mark as PASS ("Session ID derives from the live Claude Code ancestor process -- authoritative").
   - `resolvedFrom: "env-file"` → mark as PASS with a note ("CLAUDE_ENV_FILE was used; typically healthy").
-  - `resolvedFrom: "env-var"` → mark as WARN ("`BABYSITTER_SESSION_ID` is set without a corroborating PID marker. Likely stale from a prior Claude Code session -- see GitHub issue #130").
-    - Remediation: run `babysitter session:cleanup` and start a fresh Claude Code session, or `unset BABYSITTER_SESSION_ID` before invoking babysitter.
+  - `resolvedFrom: "env-var"` → mark as WARN ("`AGENT_SESSION_ID` is set without a corroborating PID marker. Likely stale from a prior Claude Code session -- see GitHub issue #130").
+    - Remediation: run `babysitter session:cleanup` and start a fresh Claude Code session, or `unset AGENT_SESSION_ID` before invoking babysitter.
   - `resolvedFrom: "none"` → mark as ERROR ("No session ID resolvable. Either no session-start hook fired, or the ancestor walk failed").
 
 **Env-var shadow check:**
 - Independently inspect `envVarPresent` and `envVarMatches` in the output.
-- If `envVarPresent && !envVarMatches`, mark as WARN ("`BABYSITTER_SESSION_ID` in env does not match the resolved session ID; a stale value is shadowing the authoritative one. Unset the env var").
+- If `envVarPresent && !envVarMatches`, mark as WARN ("`AGENT_SESSION_ID` in env does not match the resolved session ID; a stale value is shadowing the authoritative one. Unset the env var").
 
 ---
 
@@ -391,7 +390,7 @@ Mark as FAIL if:
 
 - Enumerate files in `~/.a5c/` matching the pattern `current-session-*-pid-*`.
 - Count markers per harness (derived from the filename).
-- If more than one live marker exists for the same harness, mark as INFO ("Multiple live Claude Code / harness sessions detected; ensure each shell scopes `BABYSITTER_SESSION_ID` appropriately -- the PID marker handles this automatically").
+- If more than one live marker exists for the same harness, mark as INFO ("Multiple live Claude Code / harness sessions detected; ensure each shell scopes `AGENT_SESSION_ID` appropriately -- the PID marker handles this automatically").
 - Otherwise mark as PASS.
 
 ---
@@ -502,7 +501,7 @@ babysitter session:cleanup --dry-run   # preview
 babysitter session:cleanup             # apply
 
 # 2. Unset a stale env var
-unset BABYSITTER_SESSION_ID
+unset AGENT_SESSION_ID
 
 # 3. Re-bind a run explicitly if needed
 babysitter session:resume --session-id <fresh-id> --state-dir ~/.a5c --run-id <runId> --runs-dir .a5c/runs

package/skills/help/SKILL.md

@@ -231,9 +231,11 @@ SECONDARY COMMANDS
   effect status in your browser. Useful when running /yolo or /forever to watch
   progress without interrupting the run.
 
-  How it works: Runs npx @yoavmayer/babysitter-observer-dashboard@latest which watches
+  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.
+  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. 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. Open the browser at the URL printed by the dashboard.
+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
+`agent-platform observe` surface, but this skill uses the verified standalone
+dashboard package.