Vow Enforcement

> Rules that depend on willpower fail under pressure.
> Enforcement earns trust by making the right path the
> only path.

# Vow Enforcement

## Table of Contents

- [The Problem](#the-problem)
- [Three Enforcement Layers](#three-enforcement-layers)
- [Vow Classification Protocol](#vow-classification-protocol)
- [Night Market Vow Inventory](#night-market-vow-inventory)
- [Vow Graduation Criteria](#vow-graduation-criteria)
- [Nen Court Protocol](#nen-court-protocol)
- [Integration Points](#integration-points)
- [When to Use](#when-to-use)
- [When NOT to Use](#when-not-to-use)

## The Problem

ODCV-Bench found that agents break self-imposed
constraints 30-50% of the time when goals conflict.
Practitioner consensus confirms: past 150 soft rules,
compliance drops for ALL rules, not just the new ones.

The core insight: "settings.json is a firewall;
CLAUDE.md is an employee handbook." Handbooks work for
guidance. Firewalls work for enforcement. Mixing them
up creates a false sense of security.

## Three Enforcement Layers

| Layer | Mechanism | Compliance | Examples |
|-------|-----------|------------|---------|
| **Soft Vow** | Skill instructions, CLAUDE.md rules | ~80% | "Write tests first", "Keep commits small" |
| **Hard Vow** | Hooks (PreToolUse/PostToolUse), settings.json permissions | ~100% | Block `--no-verify`, enforce file size limits |
| **Nen Court** | External validator agents checking output | Deterministic | Lint checks, test runs, constraint audits |

**Soft Vows** rely on model compliance. Cheap to add
and easy to iterate, but unreliable under goal
conflict. Use when the constraint requires judgment,
violation is annoying but not dangerous, or you are
still learning what the right rule is.

**Hard Vows** block forbidden actions before they
execute via hooks and settings.json permissions. Use
when the constraint is binary, violation causes real
damage, or the soft vow version was violated
repeatedly.

**Nen Court** spawns external validator agents that
audit output after a phase completes. Use when the
constraint requires analysis (not pattern matching),
a hook cannot express the rule, or the check needs
codebase context.

## Vow Classification Protocol

When adding a new constraint, follow this sequence:

### Step 1: Start as Soft Vow

Add the rule to the relevant skill or CLAUDE.md.
This is the cheapest path: zero cost, minutes to
deploy, ~80% compliance.

### Step 2: Monitor Violation Rate

Track violations via execution logs, post-hoc audits
(`imbue:justify` reports), user complaints, and Nen
Court findings from related audits.

### Step 3: Graduate if Needed

If violation rate exceeds 20% over a 30-day window:

- **Binary constraint?** Graduate to Hard Vow (hook).
- **Judgment constraint?** Graduate to Nen Court.
- **Ambiguous?** Try Hard Vow first. If false
  positives exceed 10%, move to Nen Court.

## Night Market Vow Inventory

Current classification of existing constraints:

| Constraint | Current Layer | Target Layer | Notes |
|------------|--------------|--------------|-------|
| Iron Law (no impl without failing test) | Nen Court | Nen Court | `validators/iron_law.py` audits commit order (#406) |
| No `--no-verify` | Hard | Hard | Already hook-enforceable |
| Scope-guard worthiness scoring | Soft | Soft | Requires judgment, not binary |
| Proof-of-work evidence | Nen Court | Nen Court | `validators/proof_of_work.py` checks