verify-governancelisted

Adjudicate a flagged governance concern with evidence, then issue a JUSTIFIED or REVERT verdict. Use when a Forge governance hook logs "GOVERNANCE: N violation(s)" or "Code governance", when a test-vs-implementation mismatch is suspected, when a change might be out of directive scope, or when the user asks to verify/justify a code or test change. Reads the real implementation before ruling — it never guesses.
nxtg-ai/forge-plugin · ★ 5 · AI & Automation · score 76

Install: claude install-skill nxtg-ai/forge-plugin

# Verify Governance Skill Adjudicates a governance concern by reading the **actual** source, comparing it to what was flagged, and returning an evidence-backed verdict: **JUSTIFIED** (proceed) or **REVERT**. This is the manual/adjudication front end for the same concern class the `governance-verifier` agent handles automatically. Use this skill for a quick in-session ruling; delegate to the agent when the concern needs its own isolated context. ## When to Use - A Forge advisory hook printed a warning during an Edit/Write (`GOVERNANCE: N violation(s)`). - You changed a test assertion and need to prove it matches the implementation. - You suspect a change drifted outside the current directive scope. - The user asks "is this justified?" / "should I revert this?". ## What the hooks actually emit (ground truth) `hooks/scripts/governance-check.sh` is a **PostToolUse (Edit/Write) advisory** hook — it **always exits 0 and never blocks**. It only runs on source paths (`*/src/*`, `.ts/.tsx/.js/.jsx/.py/.rs/.go`), **skips test files** (`*.test.*`, `*.spec.*`, `*__tests__*`), and flags four categories: | Tag | Rule | Message fragment | |-----|------|------------------| | `[ANY]` | `as any` cast in production code | `N 'as any' cast(s) at line(s): ...` | | `[API]` | `unwrapErr()` call | `use .error property` | | `[LOG]` | uncommented `console.log` | `use structured logger` | | `[URL]` | hardcoded `localhost:PORT` | `use env config` | It also appends a `WARN` entry (`category: code