@a5c-ai/babysitter-github 0.1.1-staging.0825aadb

package/commands/help.md

@@ -0,0 +1,244 @@
+---
+description: help and documentation for babysitter command usage, processes, skills, agents, and methodologies. use this command to understand how to use babysitter effectively.
+argument-hint: Specific command, process, skill, agent, or methodology you want help with (e.g. "help command doctor" or "help process retrospect").
+allowed-tools: Read, Grep, Write, Task, Bash, Edit, Grep, Glob, WebFetch, WebSearch, Search, AskUserQuestion, TodoWrite, TodoRead, Skill, BashOutput, KillShell, MultiEdit, LS
+---
+
+## if no arguments provided:
+
+show this message:
+
+```
+Welcome to the Babysitter Help Center! Here you can find documentation and guidance on how to use Babysitter effectively.
+
+Documentation: Explore our comprehensive documentation to understand Babysitter's features, processes, skills, agents, and methodologies. Read the Docs: https://github.com/a5c-ai/babysitter
+
+Or ask specific questions about commands, processes, skills, agents, methodologies, domains, specialities to get targeted help.
+
+Just type /babysitter:help followed by your question or the topic you want to learn more about.
+
+
+PRIMARY COMMANDS
+================
+
+/babysitter:call [input]
+  Start a babysitter-orchestrated run. Babysitter analyzes your request, interviews you
+  to gather requirements, selects or creates the best process definition (from 50+
+  domain-specific processes covering science, business, engineering, and more), then
+  executes it step by step with breakpoints where you can steer direction.
+
+  How it works: The babysitter skill reads your input, explores the process library to
+  find matching processes, interviews you to refine scope, creates an SDK run with
+  run:create, and orchestrates iterations with run:iterate -- dispatching tasks,
+  handling breakpoints, and posting results until the run completes or you pause it.
+
+  Example: /babysitter:call migrate our Express.js REST API to Fastify, keeping all
+  existing routes and middleware behavior identical, with integration tests proving
+  parity
+
+
+/babysitter:resume [run id or name]
+  Resume a paused or interrupted babysitter run. If you don't specify a run, babysitter
+  discovers all runs under .a5c/runs/, shows their status (created, waiting, completed,
+  failed), and suggests which incomplete run to pick up based on its process, pending
+  effects, and last activity.
+
+  How it works: Reads run metadata and journal, rebuilds state cache if stale, identifies
+  pending effects (breakpoints awaiting approval, tasks needing results), and continues
+  orchestration from exactly where it left off -- no work is repeated thanks to the
+  replay engine.
+
+  Example: /babysitter:resume
+  (discovers runs and offers: "Run abc123 is waiting on a breakpoint in the 'review
+  test results' phase of your API migration -- resume this one?")
+
+
+/babysitter:yolo [input]
+  Start a babysitter run in fully autonomous mode. Identical to /call but all breakpoints
+  are auto-approved and no user interaction is requested. The babysitter makes every
+  decision on its own until the run completes or hits a critical failure it can't recover
+  from. Best for well-understood tasks where you trust the process.
+
+  How it works: Same orchestration as /call, but the process context is configured to
+  skip breakpoint effects -- instead of pausing for human approval, each breakpoint
+  resolves immediately with an auto-approve result.
+
+  Example: /babysitter:yolo add comprehensive unit tests for all functions in
+  src/utils/ using vitest with >90% branch coverage
+
+
+/babysitter:plan [input]
+  Generate a detailed execution plan without running anything. Babysitter goes through
+  the full interview and process selection flow, designs the process definition with
+  all tasks, breakpoints, and dependencies, but stops before creating the actual SDK run.
+  You get a complete plan you can review, modify, or execute later with /call.
+
+  How it works: Runs the babysitter skill's planning phase only -- analyzes input,
+  matches to domain processes, interviews for requirements, then outputs the process
+  definition file and a human-readable execution plan showing each phase, task, and
+  decision point.
+
+  Example: /babysitter:plan redesign our database schema to support multi-tenancy,
+  migrate existing data, and update all queries -- I want to review the plan before
+  we touch anything
+
+
+/babysitter:forever [input]
+  Start a babysitter run that loops indefinitely with sleep intervals. Designed for
+  ongoing operational tasks: monitoring, periodic maintenance, continuous improvement,
+  or recurring workflows. The process uses an infinite loop with ctx.sleepUntil() to
+  pause between iterations.
+
+  How it works: Creates a process definition with a while(true) loop. Each cycle performs
+  the task (e.g., check metrics, process tickets, run audits), then calls ctx.sleepUntil()
+  to pause for a configured interval. The run stays in "waiting" state during sleep and
+  resumes automatically when the sleep expires on the next orchestration iteration.
+
+  Example: /babysitter:forever every 4 hours, check our GitHub issues labeled "bug",
+  attempt to reproduce and fix any that look straightforward, and submit PRs for the fixes
+
+
+SECONDARY COMMANDS
+==================
+
+/babysitter:doctor [issue]
+  Run a comprehensive 10-point health check on a babysitter run. Inspects journal
+  integrity (checksum verification, sequence gaps, timestamp ordering), state cache
+  consistency, stuck/errored effects, stale locks, session state, log files, disk usage,
+  process validation, and hook execution health. Produces a structured diagnostic report
+  with PASS/WARN/FAIL status per check and specific fix commands.
+
+  If no run ID is provided, automatically targets the most recent run. Can also diagnose
+  environment-wide issues like missing CLI, unregistered hooks, or plugin problems.
+
+  Example: /babysitter:doctor
+  (checks the latest run: "CRITICAL -- Check 5 Lock Status: FAIL -- stale lock detected,
+  process 12847 is no longer running. Fix: rm .a5c/runs/abc123/run.lock")
+
+
+/babysitter:assimilate [target]
+  Convert an external methodology, AI coding harness, or specification into native
+  babysitter process definitions. Takes a GitHub repo URL, harness name, or spec file
+  and produces a complete process package with skills/ and agents/ directories.
+
+  Two workflows available:
+  - Methodology assimilation: clones the repo, learns its procedures and commands,
+    converts manual flows into babysitter processes with refactored skills and agents
+  - Harness integration: wires babysitter's SDK into a specific AI coding tool
+    (codex, opencode, gemini-cli, antigravity, etc.) so it can orchestrate runs
+
+  Example: /babysitter:assimilate https://github.com/some-org/their-deployment-playbook
+  (clones the repo, analyzes their deployment procedures, and generates babysitter
+  processes that replicate the same workflow with proper task definitions and breakpoints)
+
+
+/babysitter:user-install
+  First-time onboarding for new babysitter users. Installs dependencies, runs an
+  interactive interview about your development specialties, preferred tools, coding
+  style, and how much autonomy you want babysitter to have. Builds a user profile
+  stored at ~/.a5c/user-profile.json that personalizes future runs.
+
+  Uses the cradle/user-install process which covers: dependency verification, user
+  interview (expertise areas, preferred languages, IDE, terminal setup), profile
+  generation, tool configuration, and optional global plugin installation.
+
+  Example: /babysitter:user-install
+  (walks you through: "What's your primary programming language? What frameworks do
+  you use most? Do you prefer babysitter to auto-approve routine tasks or always ask?")
+
+
+/babysitter:project-install
+  Onboard a new or existing project for babysitter orchestration. Researches the
+  codebase (reads package.json, scans directory structure, identifies frameworks and
+  patterns), interviews you about project goals and workflows, generates a project
+  profile at .a5c/project-profile.json, and optionally sets up CI/CD integration.
+
+  Uses the cradle/project-install process which covers: codebase analysis, project
+  interview, profile creation, recommended plugin installation, hook configuration,
+  and optional CI pipeline setup.
+
+  Example: /babysitter:project-install
+  (scans your repo: "I see this is a Next.js 16 app with Tailwind, using vitest for
+  tests and PostgreSQL. What are your main development goals for this project?")
+
+
+/babysitter:retrospect [run id or name]
+  Analyze a completed run to extract lessons and improve future runs. Reviews what
+  happened (journal events, task results, timing, errors), evaluates the process that
+  was followed, and suggests concrete improvements to process definitions, skills,
+  and agents. Interactive -- multiple breakpoints let you steer the analysis and
+  decide which improvements to implement.
+
+  Covers: run result analysis, process effectiveness review, improvement suggestions,
+  implementation of changes, and routing to /contrib if improvements belong in the
+  shared process library.
+
+  Example: /babysitter:retrospect
+  (analyzes the last run: "The API migration run completed but the 'verify parity'
+  phase took 8 iterations because test assertions were too brittle. Suggestion: add
+  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.
+
+  Without arguments: shows installed plugins (name, version, marketplace, dates) and
+  available marketplaces. With arguments: routes to the specific action.
+
+  Key actions:
+  - install <name> --global|--project: fetch install.md from marketplace and execute
+  - 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
+
+  Example: /babysitter:plugins 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)
+
+
+/babysitter:contrib [feedback]
+  Submit feedback or contribute to the babysitter project. Routes to the appropriate
+  workflow based on what you want to do:
+
+  Issue-based (opens GitHub issue in a5c-ai/babysitter):
+  - Bug report: describe a bug in the SDK, CLI, or process library
+  - Feature request: propose a new feature or enhancement
+  - Documentation question: flag undocumented behavior or missing docs
+
+  PR-based (forks repo, creates branch, submits PR):
+  - Bugfix: you already have a fix ready
+  - Feature implementation: you've built a new feature
+  - Library contribution: new or improved process/skill/agent for the library
+  - Harness integration: CI/CD or IDE integration
+
+  Without arguments: shows all contribution types and helps you pick the right one.
+  Breakpoints are placed before all GitHub actions (fork, star, PR, issue) so you
+  can review before anything is submitted.
+
+  Example: /babysitter:contrib bug report: plugin:update-registry fails when the
+  marketplace hasn't been cloned yet, even though the registry update doesn't need
+  marketplace access
+
+
+/babysitter:observe
+  Launch the babysitter observer dashboard -- a real-time web UI that monitors active
+  and past runs. Displays task progress, journal events, orchestration state, and
+  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
+  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.
+
+  Example: /babysitter:observe
+  (opens browser showing all runs with live-updating task
+  status, journal event stream, and effect resolution timeline)
+```
+
+## if arguments provided:
+
+if the argument is "command [command name]", "process [process name]", "skill [skill name]", "agent [agent name]", or "methodology [methodology name]", then show the detailed documentation for that specific command, process, skill, agent, or methodology after reading the relevant files.

package/commands/observe.md

@@ -0,0 +1,12 @@
+---
+description: Launch the babysitter observer dashboard. Installs and runs the real-time observer UI that watches babysitter runs, displaying task progress, journal events, and orchestration state in your browser.
+argument-hint: [--watch-dir <dir>]
+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>`
+3. This is a blocking process — it will keep running until stopped.
+4. Open the browser at the URL printed by the dashboard.

package/commands/plan.md

@@ -0,0 +1,7 @@
+---
+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.

package/commands/plugins.md

@@ -0,0 +1,255 @@
+---
+description: manage babysitter plugins. use this command to see the list of installed babysitter plugins, their status, and manage them (install, update, uninstall, list from marketplace, add marketplace, configure plugin, create new plugin, etc).
+argument-hint: Specific instructions.
+---
+
+This command installs and manages plugins for babysitter. A plugin is a version-managed package of contextual instructions (for install, uninstall, configure, and update/migrate between versions), not a conventional software plugin.
+
+if the command is run without arguments, it lists all installed plugins with their name, version, marketplace, installation date, and last update date. as well as marketplaces added to the system. and instructions on how to install new plugins from marketplaces.
+if there are no marketplaces added, add the default marketplace:
+```bash
+babysitter plugin:add-marketplace --marketplace-url https://github.com/a5c-ai/babysitter --marketplace-path plugins/a5c/marketplace/marketplace.json --global --json
+```
+
+Plugins 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 plugin package directories. The SDK clones them locally with `--depth 1`.
+
+**Storage locations:**
+- Global: `~/.a5c/marketplaces/<name>/`
+- Project: `<projectDir>/.a5c/marketplaces/<name>/`
+
+The marketplace name is derived from the git URL's last path segment (stripping `.git` suffix and trailing slashes).
+
+### Adding a marketplace
+
+```bash
+babysitter plugin:add-marketplace --marketplace-url <url> [--marketplace-path <relative-path>] [--marketplace-branch <ref>] [--force] --global|--project [--json]
+```
+
+Clones the marketplace repository to the local marketplaces directory. Use `--marketplace-path` to specify the relative path to `marketplace.json` within the repo (for monorepos or repos where the manifest is not at the root). Use `--marketplace-branch` to clone a specific branch, tag, or ref (defaults to the repo's default branch). Use `--force` to replace an existing marketplace clone (deletes and re-clones).
+
+### Updating a marketplace
+
+```bash
+babysitter plugin:update-marketplace --marketplace-name <name> [--marketplace-branch <ref>] --global|--project [--json]
+```
+
+Runs `git pull` on the local marketplace clone to fetch latest changes. Use `--marketplace-branch` to switch to a different branch before pulling (works even with shallow clones).
+
+### Listing plugins in a marketplace
+
+```bash
+babysitter plugin:list-plugins --marketplace-name <name> --global|--project [--json]
+```
+
+Reads the `marketplace.json` manifest and returns all available plugins sorted alphabetically by name. Each entry includes: name, description, latestVersion, versions array, packagePath, tags, and author.
+
+## Plugin Installation
+
+**Note:** For `plugin:install`, `plugin:update`, `plugin:configure`, and `plugin:list-plugins`, the `--marketplace-name` flag is auto-detected when only one marketplace is cloned for the given scope. You can omit it if there's only one marketplace.
+
+### Flow
+
+1. Update the marketplace: `babysitter plugin:update-marketplace --marketplace-name <name> --global|--project`
+2. Check current state: `babysitter plugin:list-installed --global|--project` to see installed plugins and versions
+3. Install the plugin:
+
+```bash
+babysitter plugin:install --plugin-name <name> [--marketplace-name <mp>] --global|--project [--json]
+```
+
+This command resolves the plugin package path from the marketplace manifest, reads `install.md` from the plugin package directory, and returns the installation instructions. If an `install-process.js` file exists, the instructions may reference it as an automated install process.
+
+4. The agent performs the installation steps as defined in `install.md`
+5. The agent updates the registry:
+
+```bash
+babysitter plugin:update-registry --plugin-name <name> --plugin-version <ver> --marketplace-name <mp> --global|--project [--json]
+```
+
+## Plugin Update (with migrations)
+
+```bash
+babysitter plugin:update --plugin-name <name> --marketplace-name <mp> --global|--project [--json]
+```
+
+This command:
+1. Reads the currently installed version from the registry
+2. Resolves the latest version from the marketplace manifest
+3. Looks in the plugin package's `migrations/` directory for migration files
+4. Uses BFS over the migration graph to find the shortest path from the installed version to the target version
+5. Returns the ordered migration instructions (content of each migration file in sequence)
+
+**Migration filename format:** `<fromVersion>_to_<toVersion>.<ext>` where:
+- Versions may contain alphanumerics, dots, dashes (e.g. `1.0.0`, `2.0.0-beta`)
+- Extensions: `.md` for markdown instructions, `.js` for executable process files
+- Examples: `1.0.0_to_1.1.0.md`, `2.0.0-beta_to_2.0.0.js`
+
+After performing the migration steps, update the registry:
+
+```bash
+babysitter plugin:update-registry --plugin-name <name> --plugin-version <new-ver> --marketplace-name <mp> --global|--project [--json]
+```
+
+## Plugin Uninstallation
+
+```bash
+babysitter plugin:uninstall --plugin-name <name> --marketplace-name <mp> --global|--project [--json]
+```
+
+Reads `uninstall.md` from the plugin package directory and returns the uninstall instructions. After performing the uninstall steps, remove from registry:
+
+```bash
+babysitter plugin:remove-from-registry --plugin-name <name> --global|--project [--json]
+```
+
+## Plugin Configuration
+
+```bash
+babysitter plugin:configure --plugin-name <name> --marketplace-name <mp> --global|--project [--json]
+```
+
+Reads `configure.md` from the plugin package directory and returns configuration instructions.
+
+## Registry Management
+
+The plugin registry (`plugin-registry.json`) tracks installed plugins with schema version `2026.01.plugin-registry-v1`. Writes use atomic file operations (temp + rename) for crash safety.
+
+**Storage locations:**
+- Global: `~/.a5c/plugin-registry.json`
+- Project: `<projectDir>/.a5c/plugin-registry.json`
+
+### List installed plugins
+
+```bash
+babysitter plugin:list-installed --global|--project [--json]
+```
+
+Returns all installed plugins sorted alphabetically. In `--json` mode, returns an array of registry entries. In human mode, displays a formatted table with name, version, marketplace, and timestamps.
+
+### Remove from registry
+
+```bash
+babysitter plugin:remove-from-registry --plugin-name <name> --global|--project [--json]
+```
+
+Removes a plugin entry from the registry. Returns error if the plugin is not present.
+
+## Plugin Creation
+
+To create a new plugin package from scratch, use the `meta/plugin-creation` babysitter process. This process guides you through requirements analysis, structure design, instruction authoring, optional process file generation, validation, and marketplace integration.
+
+### Using the plugin creation process
+
+Orchestrate a babysitter run with the plugin creation process:
+
+```bash
+# Create inputs file
+cat > /tmp/plugin-inputs.json << 'EOF'
+{
+  "pluginName": "my-plugin",
+  "description": "What the plugin does — be specific about install/configure/uninstall behavior",
+  "scope": "project",
+  "outputDir": "./plugins",
+  "components": {
+    "installProcess": false,
+    "configureProcess": false,
+    "uninstallProcess": false,
+    "migrations": false,
+    "processFiles": false
+  },
+  "marketplace": {
+    "name": "my-marketplace",
+    "author": "my-org",
+    "tags": ["category1", "category2"]
+  }
+}
+EOF
+
+# Create and run
+babysitter run:create \
+  --process-id meta/plugin-creation \
+  --entry library/specializations/meta/plugin-creation.js#process \
+  --inputs /tmp/plugin-inputs.json \
+  --prompt "Create a new babysitter plugin package" \
+  --json
+```
+
+### What the process generates
+
+The process creates a complete plugin package directory:
+
+| File | Description |
+|------|-------------|
+| `install.md` | Agent-readable installation instructions with numbered steps |
+| `uninstall.md` | Reversal instructions for clean removal |
+| `configure.md` | Configuration options table and adjustment instructions |
+| `install-process.js` | *(optional)* Automated babysitter process for complex install steps |
+| `configure-process.js` | *(optional)* Automated configuration process |
+| `process/main.js` | *(optional)* Main process the plugin contributes |
+| `marketplace-entry.json` | Ready-to-use marketplace.json entry for publishing |
+
+### Process phases
+
+1. **Requirements Analysis** — Analyzes plugin purpose, prerequisites, config options, file structure
+2. **Structure Design** — Plans directory layout and file inventory (with review breakpoint)
+3. **Instruction Authoring** — Writes install.md, uninstall.md, configure.md
+4. **Process Files** — Creates optional babysitter process files (install-process.js, configure-process.js, process/main.js)
+5. **Validation** — Verifies package completeness, instruction quality, path correctness
+6. **Marketplace Integration** — Generates marketplace.json entry for publishing
+
+### Quick creation (without orchestration)
+
+For simple plugins that only need instruction files, you can create the package manually following the structure below and the [Plugin Author Guide](docs/plugins/plugin-author-guide.md).
+
+## Plugin Package Structure
+
+```
+my-plugin/
+  package.json         # Optional (name field used as plugin ID, falls back to directory name)
+  install.md           # Markdown instructions for installation
+  uninstall.md         # Markdown instructions for removal
+  configure.md         # Markdown instructions for configuration
+  install-process.js   # Optional automated install process
+  uninstall-process.js # Optional automated uninstall process
+  configure-process.js # Optional automated configure process
+  migrations/          # Version migration files
+    1.0.0_to_1.1.0.md
+    1.1.0_to_2.0.0.js
+  process/             # Process definition files (collected recursively)
+    main.js
+```
+
+## All CLI Commands Summary
+
+All commands accept `--json` for machine-readable output and `--global|--project`.
+
+| Command | Required Flags | Description |
+|---------|---------------|-------------|
+| `plugin:add-marketplace` | `--marketplace-url`, `--global\|--project` [`--marketplace-path`, `--marketplace-branch`, `--force`] | Clone a marketplace repository |
+| `plugin:update-marketplace` | `--marketplace-name`, `--global\|--project` [`--marketplace-branch`] | Pull latest marketplace changes (optionally switch branch) |
+| `plugin:list-plugins` | `--marketplace-name`, `--global\|--project` | List available plugins in a marketplace |
+| `plugin:install` | `--plugin-name`, `--marketplace-name`, `--global\|--project` | Get install instructions for a plugin |
+| `plugin:uninstall` | `--plugin-name`, `--marketplace-name`, `--global\|--project` | Get uninstall instructions for a plugin |
+| `plugin:update` | `--plugin-name`, `--marketplace-name`, `--global\|--project` | Resolve migration chain and get update instructions |
+| `plugin:configure` | `--plugin-name`, `--marketplace-name`, `--global\|--project` | Get configuration instructions for a plugin |
+| `plugin:list-installed` | `--global\|--project` | List all installed plugins |
+| `plugin:update-registry` | `--plugin-name`, `--plugin-version`, `--marketplace-name`, `--global\|--project` | Register or update a plugin entry |
+| `plugin:remove-from-registry` | `--plugin-name`, `--global\|--project` | Remove a plugin entry from the registry |
+
+## After Plugin Work: Contribute Back
+
+After working with plugins, prompt the user to share improvements or report issues:
+
+- **Improved a plugin's install/configure/uninstall instructions**: `/babysitter:contrib library contribution: improved [plugin-name] [install|configure|uninstall] instructions`
+- **Created a new plugin**: `/babysitter:contrib library contribution: new plugin [plugin-name] -- [description]`
+- **Found a bug in a plugin or the plugin system**: `/babysitter:contrib bug report: [description, e.g. "plugin:update-registry fails when marketplace hasn't been cloned"]`
+- **Plugin install/configure instructions were confusing or wrong**: `/babysitter:contrib bug report: [plugin-name] install instructions [description of what was wrong]`
+- **Have an idea for a new plugin**: `/babysitter:contrib feature request: plugin idea -- [description]`
+
+Even reporting that a plugin's instructions were unclear helps improve it for the next user.

package/commands/project-install.md

@@ -0,0 +1,17 @@
+---
+description: Set up a project for babysitting. Guides you through onboarding a new or existing project — researches the codebase, interviews you about goals and workflows, builds the project profile, installs the best tools, and optionally configures CI/CD integration.
+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).
+
+Before using the process library, resolve the active library root through the SDK CLI. If no binding exists yet, initialize the shared global SDK binding with:
+
+```bash
+babysitter process-library:active --json
+```
+
+Then use the `cradle/project-install` process from the active process library.
+
+When the run completes, end with a friendly message that includes a polite and humorous ask to star the repo on GitHub: https://github.com/a5c-ai/babysitter

package/commands/resume.md

@@ -0,0 +1,8 @@
+---
+description: Resume orchestrating of a babysitter run. use this command to resume babysitting a complex workflow.
+argument-hint: Specific run to resume
+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). to resume a run.
+if no run was given, discover the runs and suggest which incomplete run to resume based on the run's status, inputs, process , etc.

package/commands/retrospect.md

@@ -0,0 +1,55 @@
+---
+description: Analysis for a run and its results, process, suggestions for process improvements, process optimizations, fixes, etc. for the next runs.
+argument-hint: "[run-id...] [--all] Specific run IDs, --all for all runs, or defaults to latest"
+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).
+
+create and run a retrospect process:
+
+### Run Selection
+
+- `--all` or "all runs": list all completed/failed runs and analyze collectively
+- Multiple run IDs: analyze each specified run
+- Single run ID or no ID: existing behavior (latest run)
+- In interactive mode with no run specified: ask user whether to analyze latest, select specific runs, or all runs
+
+### Cross-Run Analysis (multi-run mode)
+
+When analyzing multiple runs, the retrospect process should additionally cover:
+- Common failure patterns across runs
+- Velocity trends (tasks/time across runs)
+- Process evolution (how processes changed)
+- Repeated breakpoint patterns
+- Aggregate quality metrics
+
+implementations notes (for the process):
+- The process should analyze the run, the process that was followed, and provide suggestions for improvements, optimizations, and fixes.
+- The process should such have many breakpoints where the user can steer the process, provide feedback, and make decisions about how to proceed with the retrospect.
+- The process should be designed to be flexible and adaptable to different types of runs, projects, and goals, and should be able to provide insights and suggestions that are relevant and actionable for the user. (modification to the process, skills, etc.)
+- The process should be designed to be iterative, allowing the user to go through multiple rounds of analysis and improvement, and should be able to track the changes and improvements made over time.
+- The process should cover:
+    - Analysis of the run and its results, including what went well, what didn't go well, and what could be improved.
+    - Analysis of the process that was followed, including what steps were taken, what tools were used, and how effective they were.
+    - Suggestions for improvements, optimizations, and fixes for both the run and the process.
+    - Implementing the improvements, optimizations, and fixes, and tracking the changes made over time.
+### Cleanup Suggestion
+
+After retrospect analysis, suggest running `/babysitter:cleanup` to clean up old run data and reclaim disk space.
+
+    - Ending by explicitly prompting the user to contribute back -- even just reporting an issue is valuable, they don't need to implement the fix themselves. After analysis, display a clear call-to-action:
+
+      "You've identified [specific insight/improvement]. This could help other babysitter users too. Run `/babysitter:contrib` to share it upstream -- you can either report it as an issue or submit a PR with the fix."
+
+      Route to the specific contrib workflow based on what the user wants to do:
+
+      **Just reporting (no code changes needed):**
+      - Found a bug or weakness in a process -> `/babysitter:contrib bug report: [description of what went wrong]`
+      - Found missing or confusing documentation -> `/babysitter:contrib documentation question: [what was unclear]`
+      - Have an idea for improvement but don't want to implement it -> `/babysitter:contrib feature request: [description]`
+
+      **Contributing code changes:**
+      - Process/skill/agent improvements -> `/babysitter:contrib library contribution: [description]`
+      - Bug fixes in SDK or CLI -> `/babysitter:contrib bugfix: [description]`
+      - Plugin instruction improvements -> `/babysitter:contrib library contribution: improved [plugin-name] [install|configure|uninstall] instructions`

package/commands/user-install.md

@@ -0,0 +1,17 @@
+---
+description: Set up babysitter for yourself. Guides you through onboarding — installs dependencies, interviews you about your specialties and preferences, builds your user profile, and configures the best tools for your 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).
+
+Before using the process library, resolve the active library root through the SDK CLI. If no binding exists yet, initialize the shared global SDK binding with:
+
+```bash
+babysitter process-library:active --json
+```
+
+Then use the `cradle/user-install` process from the active process library.
+
+When the run completes, end with a friendly message that includes a polite and humorous ask to star the repo on GitHub: https://github.com/a5c-ai/babysitter

package/commands/yolo.md

@@ -0,0 +1,7 @@
+---
+description: Orchestrate a babysitter run. use this command to start babysitting a complex workflow in a non-interactive mode, without any user interaction or breakpoints in the 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 without any user interaction or breakpoints in the run.