# Core Install

> Install and register Agentic Life OS for the current runtime.

- **Type:** Skill
- **Install:** `agentstack add skill-djangonavarro220-agentic-life-os-core-install`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [djangonavarro220](https://agentstack.voostack.com/s/djangonavarro220)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [djangonavarro220](https://github.com/djangonavarro220)
- **Source:** https://github.com/djangonavarro220/agentic-life-os/tree/main/skills/life-os/skills/core-install

## Install

```sh
agentstack add skill-djangonavarro220-agentic-life-os-core-install
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# core-install

Install Agentic Life OS private state and make the umbrella skill visible to the current runtime. Install is a conversation and inspection workflow, not a blind script. Life OS is a helper over the runtime: it records where things live and how to access them, rather than becoming the owner of calendars, tasks, memory, crons, vaults, or delivery.

## Trigger

Use when the user asks to install, set up, register, enable, connect, or try Agentic Life OS in Hermes, OpenClaw, or another agent runtime.

## Principle

The helper may create private Life OS state files. The LLM owns the install decision flow:

- detect the active runtime
- check whether the skill is already visible
- discover existing runtime-owned systems
- explain bridge/import/migration choices
- ask before changing runtime-owned config, crons, delivery, skills, or memory

Do not add helper-script heuristics for runtime discovery. Runtime installations differ too much, and a script guessing paths is how you build a brittle little monster.

## Procedure

1. Detect the current runtime from command availability, session context, repo docs, and user request.
2. Load only the matching runtime adapter for the active runtime:
   - shared runtime adapter: `../../runtimes/.md`
   - core-install adapter: `runtimes/.md`
3. Do not load both Hermes and OpenClaw adapters for a single install. Keep runtime-specific instructions in those Markdown files, not inline here.
4. Check whether the umbrella `life-os` skill is already visible to that runtime.
5. If it is visible, do not re-register it. Run only private state install/doctor from the repo checkout.
6. If it is not visible, ask the user which registration scope and install mode they want using the runtime adapter:
   - symlink for live development
   - copy for a static snapshot
   - profile/workspace/agent/shared scope depending on runtime
7. Before proposing any integration, investigate runtime-owned systems with native runtime commands or docs:
   - tasks or background-task ledger
   - crons, schedules, heartbeat, reminders, hooks, standing orders
   - memory and vault/secrets systems
   - delivery routes and messaging channels
   - tools, sandboxing, model/provider config
   - profiles, agents, workspaces, or channel bindings
8. Present options before changing anything:
   - leave the runtime system alone and only read it when relevant
   - record a pointer/reference and bridge through runtime-native tools
   - import selected pointers, access notes, or Life-OS-specific state into config
   - migrate/reconnect references when moving between runtimes, using runtime-native stores for real data where possible
9. Ask approval before creating any bridge, import, migration, cron, delivery route, global skill registration, config edit, or destructive change.
10. Run private state install and doctor.
11. If `doctor.semantic_health.complete` is false, ask the next pending setup question from `python3 scripts/lifeos.py next-question`. The install must ask for the autonomy mode in plain human language, not just technical names; recommend `safe-internal` if the user is unsure.
12. Save each approved answer with `python3 scripts/lifeos.py answer  '' --kind `.
13. Autonomy modes are install-wide policy:
   - `approval-first`: ask before every write or external/runtime change.
   - `safe-internal`: default; allow read-only inspection and Life OS private tracking writes, ask before external/runtime/destructive/public changes.
   - `trusted-local`: allow clearly scoped reversible local maintenance, still ask before external/destructive/public/account changes.
   - `allow-all`: proceed only within the explicit saved policy and runtime safety layer; still escalate dangerous, credential, legal, destructive, or external-contact actions.
14. Review meeting crons are part of setup completion. Either create/reuse the approved runtime cron jobs for review meetings, or save the user's explicit manual-only/disabled opt-out. Do not claim setup complete while this is undecided.
15. Repeat doctor -> next-question -> ask -> answer until semantic health is complete, or until the user explicitly stops setup.
16. Use `python3 scripts/lifeos.py plan` to show runtime cron templates and remaining steps without creating jobs.
17. Verify with runtime-native skill visibility commands and `lifeos.py doctor`.

## Private state install

From the repo checkout:

```bash
python3 scripts/lifeos.py install --runtime 
python3 scripts/lifeos.py doctor
python3 scripts/lifeos.py next-question
python3 scripts/lifeos.py answer  '' --kind 
python3 scripts/lifeos.py plan
```

Use `--data-dir ` only when the user explicitly wants a non-default private data directory. Default private state is `$HOME/.life-os`; `LIFEOS_DATA_DIR` is an explicit override.

`doctor` includes `semantic_health`. Treat `semantic_health.complete: false` as “installed, but setup is not semantically complete”. Ask the next pending question through `next-question`, save the answer, and check again. Do not claim a total install while required semantic decisions are missing.

`plan` returns no-side-effect cron templates for daily briefing, quiet heartbeat, weekly review, monthly reset, and quarterly reset. These are examples for the runtime adapter to turn into real jobs only after the user has approved cadence and delivery. Larger reviews should run as guided meetings over due review items, not as giant one-shot reports.

## Runtime-owned system discovery

Discovery is read-only by default. Use it to inform the user, not to auto-migrate. After the LLM decides where a domain should live, record that source decision in the owning skill's `data.json` so later runs do not rediscover from scratch.

Examples:

- task source decisions -> `$LIFEOS_DATA_DIR/tasks-todo/data.json`
- contact source decisions -> `$LIFEOS_DATA_DIR/people-contacts/data.json`
- cron run record source decisions -> `$LIFEOS_DATA_DIR/integrations-runtime/data.json`

Skill data may store source records such as:

```json
{
  "source_decisions": {
    "records_source": {
      "owner": "runtime",
      "runtime": "",
      "source": "calendar-or-cron-or-task-system",
      "access": "use the active runtime adapter; do not duplicate the real records here"
    }
  }
}
```

Do not store the actual full birthday/contact/task list just to remember where it is.

### Runtime-specific discovery checklists

Do not inline Hermes and OpenClaw discovery instructions in this generic skill. That forces unrelated runtime context into the same prompt, which is exactly the mess this skill pack is trying to avoid.

Load only the adapter for the active runtime:

- Hermes install flow: `runtimes/hermes.md`, plus shared adapter `../../runtimes/hermes.md`
- OpenClaw install flow: `runtimes/openclaw.md`, plus shared adapter `../../runtimes/openclaw.md`

Those Markdown files own the runtime-specific commands, storage pointers, and caveats. This file owns only the generic install contract.

## Installer response contract

Report compactly:

```text
Install:
- Runtime: 
- Skill visibility: 
- Private state: 
- Runtime-owned systems found: 
- Safe next action: 
- Needs approval: 
```

If runtime detection is ambiguous, ask one concrete question: which runtime, profile, workspace, or agent should own this install?

## What the helper creates

- `$LIFEOS_DATA_DIR/installed.json`
- `$LIFEOS_DATA_DIR/runtime.json`
- `$LIFEOS_DATA_DIR/config.json` with install-wide metadata, skill enablement, and `semantic_setup` pointers
- `$LIFEOS_DATA_DIR//data.json` for every indexed subskill, including that skill's source decisions, state, caches, and preferences

## Boundaries

Install does not create runtime crons, delivery routes, credentials, memory entries, vault entries, mail config, calendar config, skill registrations, or migrations. Those are runtime-owned and require explicit user approval.

Skill registration is runtime-specific. Runtime-wide scheduling, delivery, and global registration policy remain explicit follow-up steps, not hidden installer side effects.

## Data

Private state belongs in:

```text
$LIFEOS_DATA_DIR/core-install/data.json
```

Do not commit personal data, credentials, private runtime config, raw logs, transcripts, screenshots, audio, or real delivery targets.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [djangonavarro220](https://github.com/djangonavarro220)
- **Source:** [djangonavarro220/agentic-life-os](https://github.com/djangonavarro220/agentic-life-os)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-djangonavarro220-agentic-life-os-core-install
- Seller: https://agentstack.voostack.com/s/djangonavarro220
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.