Skip to content
Back to skills

Init

ASecurity

Bootstrap a session by activating orchestrator mode, confirming governer calibration, and arming declare-scope — all in one command. Use at the start of any session instead of running /orchestrator, /governer, and /declare-scope separately.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 7, 2026
toolsgobash

Security analysis

A100/100

Scanned November 7, 2026

npx -y skills add Next-AI-Labs-Inc/alignment-harness --skill init --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Init?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Init
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/next-ai-labs-inc-init/badge)](https://www.skillsdirectory.com/skills/next-ai-labs-inc-init)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: init
description: Bootstrap a session by activating orchestrator mode, confirming governer calibration, and arming declare-scope — all in one command. Use at the start of any session instead of running /orchestrator, /governer, and /declare-scope separately.
triggers:
  - "/init"
  - "session init"
  - "bootstrap session"
  - "initialize session"
  - "start session protocol"
---

# Session Bootstrap — /init

One command. Three layers armed. Session ready.

## What this does

Chains the three mandatory session protocols in order:

1. **Orchestrator** — activates non-blocking dispatch mode, hard gates, background-only agent rules
2. **Governer** — confirms scoring pipeline calibration (all phases: score → meta → verification contract → best-fit skill → execute → speak-human → summary)
3. **Declare-scope** — arms intent decomposition, ready to fire on first real task

## How to run

Invoke each skill in sequence using the Skill tool. Do NOT read their full contents — just activate them. Then print the combined ready state.

### Step 1 — Orchestrator

Invoke the `orchestrator` skill with args `"say ready"`.

Print output verbatim. It will print:
```
🟢 Hard Gates Active
⚡ All dispatches run in background. I stay available to you.
```

### Step 2 — Governer

Invoke the `governer` skill with args `"confirm calibrated"`.

It will confirm all pipeline phases are loaded. Print confirmation.

### Step 3 — Declare-scope

Invoke the `declare-scope` skill with args `"confirm this system loaded"`.

It will confirm intent decomposition is armed.

### Step 4 — Print combined ready state

After all three confirm, print exactly:

```
🟢 Session armed — orchestrator + governer + declare-scope active
Ready. What do you need?
```

## Rules this session now enforces

- **NON-BLOCKING — ABSOLUTE, NO EXCEPTIONS**
  - NEVER use Bash, Edit, Write, or Read tools for implementation work
  - NEVER call the Agent tool without `run_in_background: true`
  - ALWAYS dispatch → immediately say "What else, the user?"
  - "It's a small task" is not an exception. There are no exceptions.

- **Governer scores every task** before any code is written
- **Declare-scope** fires on every non-trivial task to post decomposed intent to Intent DB
- **No foreground blocking** — the orchestrator stays available to the user at all times

## What NOT to do

- Do not re-read the full orchestrator, governer, or declare-scope skill files — token waste
- Do not run any implementation commands during init
- Do not ask clarifying questions — just arm the three layers and print ready

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.