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.
git clone --depth 1 https://github.com/nxtg-ai/forge-pluginWrote 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.
[](https://agentmods.dev/agents/nxtg-ai/forge-plugin/governance-verifier)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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:
- Gathers Evidence - Reads the relevant implementation code
- Analyzes the Concern - Determines if the concern is valid
- Provides Verdict - Either justifies the change with evidence or recommends reverting
- 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-governanceinvocation - 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"
}
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.
- 1mo ago Changed · +67 lines · +187 tokens per session e4948aba7b1b
- 1mo ago First seen · 119 lines · 0 tokens per session scan A b55326bd1592
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.
Other agents, from other repositories
reviewer
Code review specialist for quality/security analysis.
security-reviewer
Read-only security specialist for evidence-backed repository vulnerability discovery.
panel-adviser
DAE review-panel adviser. Constructive senior review of a checkpoint artifact (acs.md at CP2, plan.md at CP4): what is missing, underspecified, or would bite later. Read-only, bounded one-shot. Dispatched by /engineer.discover-acs and /engineer.plan alongside panel-advocate.
panel-advocate
DAE review-panel advocate. Adversarial review of a checkpoint artifact (acs.md at CP2, plan.md at CP4). Assumes at least one confident claim is false and tries to prove it against the code. Read-only. Dispatched by /engineer.discover-acs and /engineer.plan alongside panel-adviser.
reviewer
DAE refine reviewer. Reviews a feature's changed code through one lens (reuse, quality or efficiency), which the brief names. Read-only; returns ranked proposals. Dispatched three at a time by /engineer.refine at CP6.
verifier
DAE independent verifier for CP7 Light Verify. Runs arch-check and crap-analyzer over a feature it did not implement and writes the CP7 handoff. Must not modify code. Dispatched by /engineer.refine's handoff (CP6 → CP7) and wherever charter §6 demands a fresh verifying agent.