reliability-worker

Enforce Tier 2 reliability and negative-path correctness with audited tests.

Updated Apr 8, 2026
One-click install
npx skills add https://github.com/LudwigAJ/swell --skill reliability-worker
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: reliability-worker
Source: https://github.com/LudwigAJ/swell/tree/main/.factory/skills/reliability-worker
Command: npx skills add https://github.com/LudwigAJ/swell --skill reliability-worker

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you make Tier 2 reliability and correctness changes without breaking a previously green Tier 1 system, especially when the work must be audited and proven with tests.

Core Features & Use Cases

  • Negative-path hardening: Add and validate tests for denied, paused, misordered, or corrupted states before changing runtime behavior.
  • Guarded implementation: Apply the smallest fix needed for permission enforcement, hooks, compaction, token accounting, cost limits, and session or config correctness.
  • Regression-safe validation: Run the required crate tests, checks, clippy, and integration assertions, then report machine-readable evidence for mission review.

Quick Start

Use this skill to assess the mission’s Tier 2 reliability feature, confirm Tier 1 is green, implement the smallest audited fix, and return validation evidence with the exact commands you ran.

Frequently Asked Questions about reliability-worker

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add negative-path validation in Rust without breaking existing tests?

Negative-path hardening for Rust permission enforcement requires writing adversarial tests for denied or corrupted states first, then applying the smallest audited fix while preserving existing Tier 1 test wiring to prevent regressions.

What is negative-path correctness for permission enforcement?

Negative-path correctness validates denied, paused, misordered, or corrupted states by requiring adversarial test-first changes before applying runtime behavior fixes, ensuring audited reliability without regressions.

How do I implement cost guards and token accounting safely?

To implement cost guards and token accounting safely, apply the smallest guarded fix needed for reliability, then run crate tests and clippy to validate the changes and report machine-readable gate evidence for review.

Does reliability-worker work for compaction and session state validation?

Reliability-worker applies to compaction, session state correctness, and config validation by enforcing Tier 2 reliability through regression-proof validation after Tier 1 is green.

What's the best way to audit reliability fixes with regression testing?

Auditing reliability fixes with regression testing requires confirming Tier 1 is green, implementing the smallest audited fix, running crate tests and clippy, then returning machine-readable validation evidence for mission review.

Why do I need adversarial test-first changes for Rust reliability?

Adversarial test-first changes are required for Rust reliability to validate negative-path correctness before runtime behavior changes, ensuring permission enforcement and token accounting modifications remain regression-proof.