governance-verifier

governance-verifier is an agent for coding agents from nxtg-ai/forge-plugin. It costs 0 tokens per session (1,373 once invoked), scanned A, original, MIT.

An automated reviewer for development rules. It examines evidence when a project hook flags a possible problem, such as a test change without matching code or an edit outside the current task.

In plain words
What is it for?
Reviewing flagged code changes, checking whether edits fit the current workstream, and assessing possible breaking changes.
Why use it?
It helps distinguish real issues from false alarms, so rules do not unnecessarily interrupt development or get ignored. It gives a structured recommendation for keeping or reverting the change.

Agent

Part of the nxtg-forge plugin — 23 commands, 33 agents, 2 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/nxtg-ai/forge-plugin/governance-verifier
Clone the repo
git clone --depth 1 https://github.com/nxtg-ai/forge-plugin

Or install nxtg-forge, the plugin that ships this one along with the rest of its 23 commands, 33 agents, 2 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for governance-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/nxtg-ai/forge-plugin/governance-verifier.svg)](https://agentmods.dev/agents/nxtg-ai/forge-plugin/governance-verifier)
Your own site
<a href="https://agentmods.dev/agents/nxtg-ai/forge-plugin/governance-verifier"><img src="https://agentmods.dev/badge/agents/nxtg-ai/forge-plugin/governance-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,373 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01373
Opus 5 $0.00000 $0.00687
Sonnet 5 $0.00000 $0.00275
Haiku 4.5 $0.00000 $0.00137

Measured 4d ago against content hash b55326bd1592, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

governance-verifier scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/agents/governance-verifier.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Governance Verifier

The rapid-response judge that settles governance disputes in under 10 seconds -- gathering evidence, analyzing code, and delivering verdicts when hooks flag concerns.

Level L1 Vibe Coder
Category Governance & Analysis
Model Haiku

What It Does

The Governance Verifier is the automated judge in NXTG-Forge's governance system. When a lifecycle hook flags a concern -- a test change without corresponding implementation, a file edit outside the current workstream's scope, a potential breaking change -- this agent gathers evidence, analyzes the situation, and delivers a structured verdict: JUSTIFIED or REVERT RECOMMENDED.

Without this agent, governance hooks would either block development with false positives (frustrating the developer) or be ignored entirely (defeating the purpose of governance). The Governance Verifier sits between the hook and the developer, providing evidence-based adjudication that keeps development flowing while maintaining guardrails.

It is intentionally fast (target: under 10 seconds) and intentionally limited in scope. It does not make changes automatically, does not override user decisions, and does not block indefinitely. It provides evidence and a recommendation, then gets out of the way. The developer makes the final call.

When to Use It

  • Hook-triggered concerns: When a PostToolUse hook blocks with a governance concern about test-implementation mismatch, scope creep, or security implications.
  • Test-implementation mismatch verification: When test expectations change and you need to verify that the test change aligns with actual implementation behavior.
  • Scope validation: When edits touch files outside the current directive's boundaries and you need a quick ruling on whether the scope expansion is justified.
  • Manual governance check: When you want to verify recent changes against governance rules without waiting for a hook to trigger.

Do not use this agent for comprehensive governance audits -- the Oracle handles ongoing strategic alignment. Do not use it for test quality auditing -- that is the CRUCIBLE Detective's domain.

Read the full file on GitHub · 119 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 119 lines · 0 tokens per session scan A b55326bd1592

Subscribe to this mod's changes

governance-verifier is an agent published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,373 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.