@a5c-ai/babysitter-opencode 5.0.1-staging.702617b8 → 5.0.1-staging.70c61e4c7b4d

package/README.md

@@ -9,7 +9,7 @@ complex multi-step workflows -- powered by the Babysitter SDK.
 ## Plugin Structure
 
 ```
-plugins/babysitter-opencode/
+artifacts/generated-plugins/opencode/
   bin/
     cli.cjs              CLI entry point (babysitter-opencode command)
     install.cjs          Installation script
@@ -36,31 +36,29 @@ plugins/babysitter-opencode/
 
 ### Prerequisites
 
-Install the Babysitter SDK CLI:
+Install the Babysitter CLI once:
 
 ```bash
-npm install -g @a5c-ai/babysitter-sdk
+npm install -g @a5c-ai/babysitter
 ```
 
-### Method 1: npm global install (recommended)
+### Method 1: Babysitter harness install (recommended)
 
-```bash
-npm install -g @a5c-ai/babysitter-opencode
-```
-
-The `postinstall` script automatically copies the plugin into your current
-workspace's `.opencode/plugins/babysitter/` directory.
-
-To install into a specific workspace:
+Use the SDK helper for scriptable global or workspace installs. This is the canonical path used by the installer tests and resolves to `npx --yes @a5c-ai/babysitter-opencode install ...` under the hood:
 
 ```bash
-babysitter-opencode install --workspace /path/to/project
+# Global install
+babysitter harness:install-plugin opencode
+
+# Workspace install
+babysitter harness:install-plugin opencode --workspace /path/to/project
 ```
 
-### Method 2: Babysitter harness install
+### Method 2: Published package installer
 
 ```bash
-babysitter harness:install-plugin opencode
+npx --yes @a5c-ai/babysitter-opencode install --global
+npx --yes @a5c-ai/babysitter-opencode install --workspace /path/to/project
 ```
 
 ### Method 3: Manual copy
@@ -94,13 +92,13 @@ OpenCode config directory (`<userDataPath>/opencode/plugins/babysitter/`).
 
 ```bash
 # Auto-detects Accomplish during standard install
-npm install -g @a5c-ai/babysitter-opencode
+npx --yes @a5c-ai/babysitter-opencode install --global
 
 # Or target Accomplish explicitly
-babysitter-opencode install --accomplish
+npx --yes @a5c-ai/babysitter-opencode install --accomplish
 
 # Install to both standalone OpenCode and Accomplish
-babysitter-opencode install --global --accomplish
+npx --yes @a5c-ai/babysitter-opencode install --global --accomplish
 ```
 
 Accomplish stores OpenCode config at platform-specific locations:
@@ -206,7 +204,7 @@ babysitter process-library:active --json
 ## Running Tests
 
 ```bash
-cd plugins/babysitter-opencode
+cd artifacts/generated-plugins/opencode
 npm test
 ```
 

package/bin/install-shared.js

@@ -29,7 +29,7 @@ function writeFileIfChanged(filePath, contents) {
   try {
     const existing = fs.readFileSync(filePath, 'utf8');
     if (existing === contents) return false;
-  } catch {}
+  } catch (e) { process.stderr.write('[extension-mux] file read failed for ' + filePath + ', overwriting: ' + (e instanceof Error ? e.message : String(e)) + '\n'); }
   fs.mkdirSync(path.dirname(filePath), { recursive: true });
   fs.writeFileSync(filePath, contents);
   return true;
@@ -82,7 +82,7 @@ function writeJson(filePath, value) {
 function ensureExecutable(filePath) {
   try {
     fs.chmodSync(filePath, 0o755);
-  } catch {}
+  } catch (e) { process.stderr.write('[extension-mux] chmod failed for ' + filePath + ': ' + (e instanceof Error ? e.message : String(e)) + '\n'); }
 }
 
 function normalizeMarketplaceSourcePath(source, marketplacePath) {
@@ -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: "5.0.0",
+    version: "5.0.1-staging.70c61e4c7b4d",
     author: { name: "a5c.ai" },
   };
   if (idx >= 0) marketplace.plugins[idx] = entry;
@@ -147,7 +147,7 @@ function resolveCliCommand(packageRoot) {
   const versionsPath = path.join(packageRoot, 'versions.json');
   const versions = readJson(versionsPath) || {};
   const ver = versions.sdkVersion || 'latest';
-  return `npx -y @a5c-ai/babysitter-sdk@${ver}`;
+  return `npm exec --yes --package @a5c-ai/babysitter-sdk@${ver} -- babysitter`;
 }
 
 function runCli(packageRoot, cliArgs, options = {}) {

package/commands/blueprints.md

@@ -0,0 +1,64 @@
+---
+description: manage Babysitter blueprints. Use this command to list installed blueprints, browse marketplaces, install, update, uninstall, configure, or create a new blueprint.
+argument-hint: Blueprint action and options.
+---
+
+This command installs and manages Babysitter blueprints. A blueprint is a version-managed package of contextual instructions or deterministic Babysitter processes, not a conventional software plugin.
+
+If the command is run without arguments, list installed blueprints with their name, version, marketplace, installation date, and last update date. Also list configured marketplaces and show how to add the default marketplace when none exist.
+
+Blueprints can be installed at two scopes:
+
+- **global** (`--global`): stored under `~/.a5c/`, available for all projects
+- **project** (`--project`): stored under `<projectDir>/.a5c/`, project-specific
+
+## Marketplace Management
+
+Marketplaces are git repositories containing a `marketplace.json` manifest and blueprint package directories. The SDK clones new marketplaces to `.a5c/blueprints/marketplaces/` for the selected scope and reads legacy `.a5c/marketplaces/` clones for compatibility.
+
+### Add a marketplace
+
+```bash
+babysitter blueprint:add-marketplace --marketplace-url <url> [--marketplace-path <relative-path>] [--marketplace-branch <ref>] [--force] --global|--project [--json]
+```
+
+### Update a marketplace
+
+```bash
+babysitter blueprint:update-marketplace --marketplace-name <name> [--marketplace-branch <ref>] --global|--project [--json]
+```
+
+### List blueprints in a marketplace
+
+```bash
+babysitter blueprint:list-plugins --marketplace-name <name> --global|--project [--json]
+```
+
+## Blueprint Lifecycle
+
+For `blueprint:install`, `blueprint:update`, `blueprint:configure`, and `blueprint:list-plugins`, the `--marketplace-name` flag is auto-detected when only one marketplace is cloned for the selected scope.
+
+```bash
+babysitter blueprint:install --plugin-name <name> [--marketplace-name <mp>] --global|--project [--json]
+babysitter blueprint:update --plugin-name <name> --marketplace-name <mp> --global|--project [--json]
+babysitter blueprint:configure --plugin-name <name> --marketplace-name <mp> --global|--project [--json]
+babysitter blueprint:uninstall --plugin-name <name> --marketplace-name <mp> --global|--project [--json]
+```
+
+The `--plugin-name` flag is preserved for CLI compatibility with existing marketplace manifests. User-facing docs should call the installable a blueprint.
+
+## Registry Management
+
+```bash
+babysitter blueprint:list-installed --global|--project [--json]
+babysitter blueprint:update-registry --plugin-name <name> --plugin-version <ver> --marketplace-name <mp> --global|--project [--json]
+babysitter blueprint:remove-from-registry --plugin-name <name> --global|--project [--json]
+```
+
+## Deprecated Aliases
+
+The old `plugin:*` commands remain available as deprecated aliases for one release. Prefer `blueprint:*` in new docs, skills, and process instructions.
+
+## Agent Plugins Are Separate
+
+Do not rename or reinterpret agent harness plugins while handling blueprints. `CLAUDE_PLUGIN_ROOT`, `PI_PLUGIN_ROOT`, `.claude/plugins/`, hooks-mux, extension-mux, and agent plugin manifests stay plugin-specific.

package/commands/call.md

@@ -1,7 +1,11 @@
----
-description: Orchestrate a babysitter run. use this command to start babysitting a complex workflow.
-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
----
-
-Invoke the babysitter:babysit skill (using the Skill tool) and follow its instructions (SKILL.md).
+---
+description: Orchestrate a babysitter run. use this command to start babysitting a complex workflow.
+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
+---
+
+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/commands/check-forbidden-markers.md

@@ -0,0 +1,68 @@
+---
+description: Pre-deploy gate that scans built JS chunks for forbidden substring markers (saga-era / obsolete code paths) listed in a project-local forbidden-markers.txt
+argument-hint: "[--markers-file <path>] [--chunks-dir <path>] [--json] Optional overrides; defaults are project-relative."
+allowed-tools: Read, Grep, Write, Task, Bash, Edit, Grep, Glob, WebFetch, WebSearch, Search, AskUserQuestion, TodoWrite, TodoRead, Skill, BashOutput, KillShell, MultiEdit, LS
+---
+
+Invoke the babysitter:babysit skill (using the Skill tool) and follow its instructions (SKILL.md). Compose the gate from the shared helper at `library/processes/shared/forbidden-markers-scanner.js` (issue #477).
+
+## What this gate does
+
+Reads a list of literal substring markers from `scripts/forbidden-markers.txt` (blank lines and `#`-prefixed comments stripped) and greps every `.js` chunk under `.vercel/output/static/_next/static/chunks/` (Next.js / Vercel default; configurable) for any occurrence. Reports structured hits per `(marker, chunk)` pair with occurrence counts. Designed to chain between `vercel build --prod` and `vercel deploy --prod`.
+
+Use this gate when a refactor or restart-from-baseline replaced load-bearing code paths and you need a structural guarantee the obsolete symbols never re-ship. Burned-in evidence: cookbook VI-9 / VI-12 near-miss revivals during the 2026-05 iOS-Safari saga; the prototype lives at `cookbook/scripts/check-no-forbidden.mjs` and shipped two upstream contributions before being generalized as this gate.
+
+## When to use
+
+- **Pre-deploy.** Insert after build, before deploy. Block the deploy when `ok: false`.
+- **Post-restart.** After a baseline rollback + step-by-step re-add, snapshot the saga-era markers in `forbidden-markers.txt` and let CI hold the line.
+- **Post-refactor.** When old helper / handler / module names must not coexist with the new ones in the same bundle.
+
+## Expected config locations
+
+- `scripts/forbidden-markers.txt` — one marker per line, `#` for comments. The list is the contract; the gate is mechanical. Commit this file to source control.
+- `.vercel/output/static/_next/static/chunks/` — default scan target. Override for non-Vercel frameworks via the `--chunks-dir` flag or the `chunksDir` task input.
+
+A missing markers file is a no-op (`ok: true`, `reason: 'missing-markers-file'`) — misconfiguration is never a deploy block. A missing chunks directory is likewise a no-op (`reason: 'missing-chunks-dir'`) so the gate is safe to chain into `check:all` before the build runs.
+
+## Exit semantics
+
+| Reason                  | `ok`   | Deploy decision                |
+|-------------------------|--------|--------------------------------|
+| `missing-markers-file`  | true   | Pass (no gate active)          |
+| `missing-chunks-dir`    | true   | Pass (run before build)        |
+| `empty-markers`         | true   | Pass (list is empty)           |
+| `no-chunks`             | true   | Pass (nothing to scan)         |
+| `clean`                 | true   | Pass — proceed to deploy       |
+| `hits`                  | false  | **BLOCK** — surface hits, ask for triage |
+
+For each hit, the gate emits `{ marker, chunk, count }` so the operator sees the exact marker string, the absolute chunk path, and the number of occurrences in that chunk. Multiple hits across chunks for the same marker are reported separately.
+
+## Programmatic surface
+
+```js
+import { scanForbiddenMarkers, checkForbiddenMarkersTask } from '@a5c-ai/babysitter-library/processes/shared';
+
+// Direct call:
+const result = await scanForbiddenMarkers({
+  markersFile: 'scripts/forbidden-markers.txt',
+  chunksDir:   '.vercel/output/static/_next/static/chunks',
+});
+if (!result.ok) {
+  // result.hits: Array<{ marker, chunk, count }>
+  // result.reason === 'hits'
+  process.exit(1);
+}
+
+// Or dispatched as a babysitter task:
+const gate = await ctx.task(checkForbiddenMarkersTask, {
+  projectDir: '.',
+  // markersFile / chunksDir are inferred from projectDir if omitted
+});
+```
+
+## Reference
+
+- Issue: https://github.com/a5c-ai/babysitter/issues/477
+- Helper module: `library/processes/shared/forbidden-markers-scanner.js`
+- Origin (cookbook prototype): `cookbook/scripts/check-no-forbidden.mjs` (81 lines)

package/commands/cleanup.md

@@ -6,15 +6,43 @@ allowed-tools: Read, Grep, Write, Task, Bash, Edit, Grep, Glob, WebFetch, WebSea
 
 Invoke the babysitter:babysit skill (using the Skill tool) and follow its instructions (SKILL.md).
 
-Create and run a cleanup process using the process at `skills\babysit\process\cradle\cleanup-runs.js/processes/cleanup-runs.js`.
+Resolve the active process library with:
+
+```bash
+babysitter process-library:active --json
+```
+
+Read `binding.dir` from that JSON and create/run the cleanup process from `cradle/cleanup-runs.js#process` relative to that active library root. Do not use plugin-cache-relative cradle paths.
 
 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/commands/contrib.md

@@ -1,33 +1,33 @@
----
-description: Submit feedback or contribute to babysitter project
-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
----
-
-Invoke the babysitter:babysit skill (using the Skill tool) and follow its instructions (SKILL.md).
-
-## Process Routing
-
+---
+description: Submit feedback or contribute to babysitter project
+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
+---
+
+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/commands/doctor.md

@@ -156,7 +156,6 @@ 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:
@@ -260,7 +259,7 @@ 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`.
@@ -315,7 +314,7 @@ 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`.

package/commands/forever.md

@@ -1,7 +1,7 @@
----
-description: Use this command to start babysitting a never-ending babysitter run.
-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
----
-
+---
+description: Use this command to start babysitting a never-ending babysitter run.
+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
+---
+
 Invoke the babysitter:babysit skill (using the Skill tool) and follow its instructions (SKILL.md). but create a process that uses an infinte loop and a ctx.sleep to create a never-ending babysitter loop. an example of such process is a daily process that reads new support ticket every day and tries to resolve them, then sleeps for 4 hours and repeats the process. 

package/commands/help.md

@@ -179,13 +179,13 @@ SECONDARY COMMANDS
   a fuzzy comparison step before strict assertion. Implement this fix?")
 
 
-/babysitter:plugins [action]
-  Manage babysitter plugins: list installed plugins, browse marketplaces, install,
-  update, configure, uninstall, or create new plugins. Plugins are version-managed
-  instruction packages (not executable code) that guide the agent through install,
-  configure, and uninstall steps via markdown files.
+/babysitter:blueprints [action]
+  Manage Babysitter blueprints: list installed blueprints, browse marketplaces,
+  install, update, configure, uninstall, or create new blueprints. Blueprints are
+  version-managed instruction packages or process bundles that guide the agent
+  through install, configure, and uninstall steps.
 
-  Without arguments: shows installed plugins (name, version, marketplace, dates) and
+  Without arguments: shows installed blueprints (name, version, marketplace, dates) and
   available marketplaces. With arguments: routes to the specific action.
 
   Key actions:
@@ -193,11 +193,11 @@ SECONDARY COMMANDS
   - configure <name> --global|--project: fetch configure.md and walk through options
   - update <name> --global|--project: resolve migration chain via BFS and apply steps
   - uninstall <name> --global|--project: fetch uninstall.md and execute removal
-  - create: scaffold a new plugin package with the meta/plugin-creation process
+  - create: scaffold a new blueprint package
 
-  Example: /babysitter:plugins install sound-hooks --project
+  Example: /babysitter:blueprints install sound-hooks --project
   (fetches sound-hooks from marketplace, reads install.md, walks you through player
-  detection, sound selection, hook configuration, and registers in plugin-registry.json)
+  detection, sound selection, hook configuration, and registers the blueprint)
 
 
 /babysitter:contrib [feedback]
@@ -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
+`agent-platform observe` surface, but this skill uses the verified standalone
+dashboard package.

package/commands/plan.md

@@ -1,7 +1,17 @@
----
-description: Plan a babysitter run. use this command to plan a complex workflow, without actually running it.
-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
----
-
-Invoke the babysitter:babysit skill (using the Skill tool) and follow its instructions (SKILL.md). focus on creating the best process possible, but without creating and running the actual run.
+---
+description: Plan a babysitter run. use this command to plan a complex workflow, without actually running it.
+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
+---
+
+Invoke the babysitter:babysit skill (using the Skill tool) and follow its instructions (SKILL.md). Focus on creating the best process possible, but without creating and running the actual run.
+
+Before drafting the process, run Phase 0 -- REUSE-AUDIT: extract keyword nouns and verbs from the request, scan for matching existing migrations, API routes, environment variables, SDK dependencies, and imports, honor `.a5c/reuse-audit.json` when present, and put a `Reuse-audit findings (REVIEW BEFORE PROCEEDING)` block before Phase 1 of the plan.
+
+## Process Shape Selection
+
+Choose the process shape before authoring `process.js`:
+
+- Use a flat phase list when the spec is well-defined, the work is wiring or composition, the bug class is already known if this is a fix, and execution should proceed sequentially through clear phases.
+- Use a HYPOTHESES tree when the bug class is unknown, forensics are required, multiple causal models compete, and each hypothesis needs its own observations, falsifying observations, and follow-up phases.
+- Rule of thumb: if the first phase is "investigate", use HYPOTHESES-tree mode. If the first phase is "implement X", use flat-phase-list mode.