rai_policy

rai_policy is an agent for coding agents from sabbour/agentweaver. It costs 0 tokens per session (321 once invoked), scanned A, original, MIT.

A responsible-AI policy that checks projects for credential leaks, personal-data exposure, injection vulnerabilities, harmful content, bias, deceptive patterns, privacy risks, and unsupported claims.

In plain words
What is it for?
Use it to guide automated or manual checks of code, prompts, content, and AI-generated results.
Why use it?
It helps identify security, privacy, safety, and fairness problems before they reach users.

Agent

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/sabbour/agentweaver/rai_policy
Clone the repo
git clone --depth 1 https://github.com/sabbour/agentweaver

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 rai_policy

README.md
[![agentmods](https://agentmods.dev/badge/agents/sabbour/agentweaver/rai_policy.svg)](https://agentmods.dev/agents/sabbour/agentweaver/rai_policy)
Your own site
<a href="https://agentmods.dev/agents/sabbour/agentweaver/rai_policy"><img src="https://agentmods.dev/badge/agents/sabbour/agentweaver/rai_policy.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 321 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 $0.00321
Opus 5 $0.00000 $0.00161
Sonnet 5 $0.00000 $0.00064
Haiku 4.5 $0.00000 $0.00032

Measured yesterday against content hash 90d45a6b841e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rai_policy 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 yesterday.

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.

packages/Agentweaver.Squad/Catalog/Resources/agents/rai_policy.md · 31 lines

What it actually says

RAI Policy

This policy defines the Responsible AI checks performed by the Rai agent on this project.

Check Categories

Critical (always enabled — cannot be disabled)

  • Credential leaks — API keys, tokens, passwords, connection strings in code or content
  • PII exposure — personal data (names, emails, phone numbers, IDs) without justification
  • Injection vulnerabilities — prompt injection, SQL injection, command injection
  • Harmful content — content that could cause physical or emotional harm

Advisory (enabled by default — can be disabled with justification)

  • Exclusionary language — terms that exclude or demean groups of people
  • Deceptive patterns — UI/UX patterns designed to mislead users
  • Bias indicators — algorithmic or content bias in models or outputs
  • Insufficient grounding — AI outputs presented as facts without citations
  • Privacy risks — unnecessary data collection or retention in prompts

Terminology Standards

Use inclusive, precise language. Avoid: blacklist/whitelist (use allowlist/denylist), master/slave (use primary/replica), and gendered defaults.

Opt-Out

Advisory checks may be disabled temporarily with justification logged to .squad/rai/audit-trail.md. Critical checks cannot be disabled. Temporary opt-outs auto-expire after 30 days.

Audit Trail

All RAI review findings are recorded to .squad/rai/audit-trail.md. This file is append-only and is never edited after write.

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. yesterday First seen · 31 lines · 0 tokens per session scan A 90d45a6b841e

Subscribe to this mod's changes

rai_policy is an agent published in the GitHub repository sabbour/agentweaver (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 321 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 2026-09-03.

Related

Other agents, from other repositories

policy-enforcer

Blocking policy judge. Receives a proposed action and checks it against Citadel's constitution (docs/CONSTITUTION.md). Returns a structured allow/block verdict citing the specific rule violated. Never modifies files — read-only judge. Spawned by Archon and Fleet before Red-reversibility operations.

SethGammon/Citadel · 63 tokens

infrastructure-architect

Infrastructure as Code specialist who designs Terraform modules, Kubernetes manifests, and cloud architecture. Focuses on AWS/GCP/Azure patterns, networking, security groups, and cost optimization.

yonatangross/orchestkit · 40 tokens

NOTICE

Source: https://github.com/msitarzewski/agency-agents Pinned commit: 64eee9f8e04f69b04e78e150d771a443c64720be License verified: MIT, confirmed at the pinned commit on 2026-07-28 (GitHub license API, spdxid: MIT). Because the import was commit-pinned, a later upstream relicense does not affect the grant that applied at…

clawboo/clawboo · 0 tokens

legal

Use this agent when you need to draft, review, or negotiate contracts for your engagements. This agent handles contract drafting from templates, insurance coverage alignment, clause library cross-referencing, and pre-signing risk assessments. Triggering conditions: User says "draft contract", "new agreement", "create…

Zeekeey-jpeg/LeRoy-HQ · 469 tokens

god-pci-auditor

PCI-DSS 4.0 auditor. Maps the 12 requirements to code/process evidence. For systems handling cardholder data (CHD). Spawned by: /god-pci-audit Extension: @godpowers/security-pack.

hannsxpeter/godpowers · 55 tokens

god-soc2-auditor

SOC 2 Common Criteria auditor. Maps controls to code/process evidence. Produces auditor-ready findings document. Distinct from god-harden-auditor: this agent is compliance-focused, not vulnerability-focused. Spawned by: /god-soc2-audit Extension: @godpowers/security-pack.

hannsxpeter/godpowers · 68 tokens