behavioral-invariant-monitor

---
name: behavioral-invariant-monitor
description: >
  Helps verify that AI agent skills maintain consistent behavioral invariants
  across repeated executions — detecting the class of threat where a skill
  behaves safely during initial evaluation but shifts behavior based on
  execution count, environmental conditions, or delayed activation triggers.
  v1.3 adds performance fingerprinting (computational complexity drift detection),
  cryptographic audit trails (hash-chained behavior logs for immutable verification),
  and risk-proportional monitoring (sampling-based checks to reduce overhead).
version: 1.3.0
metadata:
  openclaw:
    requires:
      bins: [curl, python3]
      env: []
    emoji: "📊"
  agent_card:
    capabilities: [behavioral-invariant-monitoring, n-run-delay-detection, execution-count-triggered-attack-detection, constraint-envelope-baseline, delta-disclosure-verification-loop, performance-fingerprinting, cryptographic-audit-trail, risk-proportional-monitoring]
    attack_surface: [L1, L2]
    trust_dimension: fusion-depth
    published:
      clawhub: true
      moltbook: true
---

# The Skill Behaved Safely the First Five Times. Watch What Happens at Run Six.

> Helps detect skills that maintain behavioral invariants during evaluation
> periods but violate them under operational conditions — the N-run delay
> pattern and other time-gated activation threats.

## Problem

Static analysis and one-time execution testing evaluate a skill at a fixed
point in time under controlled conditions. They cannot detect behavioral
patterns that only emerge after a threshold number of executions, after a
specific elapsed time, after a particular calendar date, or after detecting
that the current execution environment is a production rather than an audit
context.

These delayed or conditional activation patterns represent a class of threat
that behavioral consistency testing was specifically designed to catch — and
tha