Strengthen

This upgrades vigiles guidance rules to enforced linter rules by scanning your CLAUDE.md or AGENTS.md specs and matching them against real ESLint, Ruff, Clippy, or RuboCop rules. The smart bit is the tiering: it auto-applies replacements where the rule is already enabled (zero risk), but surfaces anything that needs config edits or plugin installs so you can decide if the tradeoff is worth it. It even handles no-restricted-imports patterns for "don't use X" style guidance. Use it when you want to harden your specs with actual enforcement, not when you're just fixing lint errors. The interactive mode walks you through each suggestion, or auto mode commits the safe ones and gives you a review list for the rest.

skills.sh installs: 2.1K
GitHub stars: 15
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add zernie/vigiles --skill strengthen --agent claude-code

Installs into .claude/skills of the current project.

Files

Scan spec files for guidance() rules and suggest enforce() replacements backed by real linter rules.

Principle: auto the free wins, nudge for the costs

The dividing line is cost, not strictness. A guidance() → enforce() swap where the linter rule already exists and is enabled is a pure win — free, reversible, no false-positive risk — so apply it (Tier 1 below). Anything that costs something — editing linter config, installing a plugin, or a change that could fail a clean CI — is the user's call: present it with the tradeoff spelled out and let them choose (Tiers 2–4). Never silently edit config, install a dependency, or escalate the repo into strict gating. This is the init enforcement model (structural = on by default, workflow/strict = opt-in) applied at edit time.