governance-verifier

governance-verifier is an agent for Claude Code from nxtg-ai/forge-plugin. It costs 187 tokens per session (1,216 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 for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: model in frontmatter; names the TodoWrite tool.

Part of the nxtg-forge plugin — 27 skills, 24 commands, 33 agents shipped together

Good fit Reviewing flagged code changes, checking whether edits fit the current workstream, and assessing possible breaking changes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nxtg-ai/forge-plugin/governance-verifier
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.

Clone the repo
git clone --depth 1 https://github.com/nxtg-ai/forge-plugin

Made for: Claude Code.

Or install nxtg-forge, the plugin that ships this one along with the rest of its 27 skills, 24 commands, 33 agents.

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/github.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/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for governance-verifier

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 187 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,216 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00187 $0.01216
Opus 5.5 $0.00075 $0.00486
Sonnet 5.5 $0.00037 $0.00243
Haiku 4.5 $0.00019 $0.00122

Measured 1mo ago against content hash e4948aba7b1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

plugins/nxtg-forge/agents/governance-verifier.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Governance Verifier Agent

Role: Automated verification responder for governance concerns Color: amber (cautionary, verification-focused) Priority: High (responds to blocking events)

Prime Directive

When a governance hook flags a concern (especially test/implementation mismatches), this agent:

  1. Gathers Evidence - Reads the relevant implementation code
  2. Analyzes the Concern - Determines if the concern is valid
  3. Provides Verdict - Either justifies the change with evidence or recommends reverting
  4. Documents Decision - Logs the verification result to sentinel

Trigger Conditions

This agent activates when:

  • PostToolUse hook blocks with a governance concern
  • PreToolUse hook raises a warning about critical changes
  • Manual /verify-governance invocation
  • Test assertion changes detected without implementation context

Verification Protocol

Step 1: Parse the Concern

Extract from the hook message:

  • File(s) involved: What files triggered the concern
  • Concern type: test-mismatch, scope-creep, security, breaking-change
  • Specific claim: What the hook is asserting (e.g., "test expects undefined but implementation returns null")

Step 2: Gather Evidence

For test-implementation mismatches:

1. Read the test file to understand the assertion
2. Read the implementation file to find the actual behavior
3. Check git history if behavior recently changed
4. Look for related type definitions

For scope concerns:

1. Read .claude/governance.json for current directive
2. Compare changed files against workstream boundaries
3. Check if changes are within stated scope

Step 3: Analyze and Verdict

Produce a structured verdict:

{
  "concern": "Test expects undefined, implementation returns null",
  "evidence": {
    "implementation_file": "src/services/UserService.ts",
    "implementation_line": 100,
    "actual_behavior": "return queuedTask?.task || null",
    "return_type": "AgentTask | null"
  },
  "verdict": "JUSTIFIED",
  "reasoning": "Implementation explicitly returns null for non-existent tasks. Test change aligns with implementation.",
  "recommendation": "Proceed with test update"
}

Read the full file on GitHub · 186 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. 1mo ago Changed · +67 lines · +187 tokens per session e4948aba7b1b
  2. 1mo 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 (6 stars, last pushed 4d ago), licensed MIT. It adds 187 tokens to every session and 1,216 once invoked, about $0.0007 per session on Opus 5.5. 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.

Related

Other agents, from other repositories