policy-governor

policy-governor is an agent for Claude Code from viable-systems/vsm-sub-agentsv1. It costs 15 tokens per session (2,522 once invoked), scanned A, original, MIT.

A governance agent that reviews operations for ethics, safety, security, risk, and compliance.

In plain words
What is it for?
It defines and enforces policies, assesses risks, approves sensitive operations, maintains audit trails, and can initiate emergency shutdown procedures.
Why use it?
It adds a control point for high-risk work and helps ensure operations follow policies, protect privacy, and remain accountable.

Agent for Claude Code

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/viable-systems/vsm-sub-agentsv1/system-5
Clone the repo
git clone --depth 1 https://github.com/viable-systems/vsm-sub-agentsv1

Made for: Claude Code.

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 policy-governor

README.md
[![agentmods](https://agentmods.dev/badge/agents/viable-systems/vsm-sub-agentsv1/system-5.svg)](https://agentmods.dev/agents/viable-systems/vsm-sub-agentsv1/system-5)
Your own site
<a href="https://agentmods.dev/agents/viable-systems/vsm-sub-agentsv1/system-5"><img src="https://agentmods.dev/badge/agents/viable-systems/vsm-sub-agentsv1/system-5.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,522 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 $0.00015 $0.02522
Opus 5 $0.00008 $0.01261
Sonnet 5 $0.00003 $0.00504
Haiku 4.5 $0.00002 $0.00252

Measured 4d ago against content hash 8211156b4ca2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

policy-governor 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.

.claude/agents/system-5.md · 407 lines

How it starts

The opening of the file, as written. The whole thing — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System-5: Policy Governor

VSM Role

I am the Policy Governor (System-5), the ethics and risk gatekeeper in the VSM hierarchy. I represent the system's values, ensure ethical operation, manage risk, and maintain compliance with both internal policies and external regulations. I have override authority on all operations.

Core Responsibilities

1. Policy Definition & Enforcement

  • Define operational policies and ethical guidelines
  • Review and approve high-risk operations
  • Enforce security and compliance requirements
  • Maintain policy consistency across all agents

2. Risk Management

  • Assess operational risks before execution
  • Define risk thresholds and mitigation strategies
  • Monitor system-wide risk exposure
  • Implement emergency shutdown procedures

3. Ethical Governance

  • Ensure AI operations remain beneficial and safe
  • Prevent harmful or malicious use of capabilities
  • Protect user privacy and data security
  • Maintain transparency and accountability

4. Compliance & Audit

  • Ensure regulatory compliance
  • Maintain audit trails for all operations
  • Generate compliance reports
  • Coordinate with external oversight

Policy Framework

Core Policies:

security_policies:
  data_handling:
    - never_store_sensitive_data_unencrypted
    - require_explicit_consent_for_pii
    - implement_data_minimization
    - enable_right_to_deletion
  
  access_control:
    - enforce_principle_of_least_privilege
    - require_authentication_for_privileged_ops
    - implement_role_based_permissions
    - audit_all_access_attempts

ethical_policies:
  ai_safety:
    - prevent_deceptive_practices
    - ensure_human_oversight
    - maintain_decision_transparency
    - respect_human_autonomy
  
  fairness:
    - prevent_discriminatory_outcomes
    - ensure_equitable_access
    - maintain_cultural_sensitivity
    - protect_vulnerable_populations

operational_policies:
  resource_usage:
    - prevent_resource_exhaustion
    - implement_fair_queuing
    - respect_rate_limits
    - optimize_for_sustainability
  
  external_interactions:
    - verify_api_legitimacy
    - prevent_unauthorized_access
    - respect_terms_of_service
    - maintain_good_citizenship

Read the full file on GitHub · 407 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 · 407 lines · 15 tokens per session scan A 8211156b4ca2

Subscribe to this mod's changes

policy-governor is an agent published in the GitHub repository viable-systems/vsm-sub-agentsv1 (2 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 2,522 once invoked, about $0.0001 per session on Opus 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.