Lamina Evolutionary Rules
Evolving product rules safely — reversible decisions, invariant checks as features change, deferring commitment. Use when the domain will grow or requirements are uncertain.
Install
$ agentstack add skill-aryaniyaps-lamina-lamina-evolutionary-rules ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-aryaniyaps-lamina-lamina-evolutionary-rules) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Evolutionary Rules
Products change. Design rules and invariants so they can evolve without silent breakage — prefer reversible choices until the cost of waiting exceeds the cost of committing.
Decision frameworks
- Reversible decision: Can be undone without corrupting domain state (toggle feature flag, add optional field).
- When to use: Uncertain requirements, early iterations.
- How: Document in
implement.mdas low-risk; verify after each change.
- Irreversible decision: Hard to undo (merge two entity types, remove invariant).
- When to use: Only when delay cost is high and trade-offs are explicit.
- How: Record in
decisions.md; full scenario coverage before ship.
- Invariant regression check: New feature must not violate existing
domainrules — re-run verify after external build. - When to use: Every
/lamina-verifyafter changes touching shared entities.
- Defer commitment: Wait until you need the rule — but do not defer documenting invariants you already know.
Checklists
- Tag design decisions reversible vs irreversible in run or
decisions.md. - When adding workflows, re-check all existing invariants for the touched entities.
- After external implementation, run verify — not one-time at handoff.
- Prefer additive rule changes over breaking changes to actor permissions.
Anti-patterns
- Big-bang rule change: New payment rule breaks all issued tickets without migration scenario.
- Forgotten invariants: Feature ships without updating scenarios.
- Permanent "temporary": Overrides that bypass invariants become architecture.
Examples
- Adding waitlist: Reversible — new workflow branch. Must preserve invariant: one valid ticket per student per exam. Scenarios for waitlist → ticket promotion and edge cases.
Related capabilities
- [Tradeoffs](../lamina-tradeoffs/SKILL.md)
- [Invariants](../lamina-invariants/SKILL.md)
- [Verify](../lamina-verify/SKILL.md)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: aryaniyaps
- Source: aryaniyaps/lamina
- License: MIT
- Homepage: https://lamina.dev
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.