RAI Planner

RAI Planner is an agent for Claude Code from Peter-N91/hve-squad-mcp. It costs 38 tokens per session (5,581 once invoked), scanned A, original, MIT.

An assessment-planning agent for reviewing artificial-intelligence systems against the NIST AI Risk Management Framework, a guide for identifying and managing AI risks. It creates a plan covering security, impacts, controls, and follow-up work.

In plain words
What is it for?
Planning an AI risk assessment, modeling security and possible impacts, cataloguing control areas, and handing the resulting work to a backlog. It stores the plan and project state under .copilot-tracking.
Why use it?
It organizes a responsible-AI review into repeatable phases and makes unanswered, completed, and blocked questions visible.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

Good fit Planning an AI risk assessment, modeling security and possible impacts, cataloguing control areas, and handing the resulting work to a backlog. It stores the plan and project state under .copilot-tracking.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/peter-n91/hve-squad-mcp/rai-planner
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/Peter-N91/hve-squad-mcp

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 RAI Planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/peter-n91/hve-squad-mcp/rai-planner/github.svg)](https://agentmods.dev/agents/peter-n91/hve-squad-mcp/rai-planner)
Your own site
<a href="https://agentmods.dev/agents/peter-n91/hve-squad-mcp/rai-planner"><img src="https://agentmods.dev/badge/agents/peter-n91/hve-squad-mcp/rai-planner/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 RAI Planner

Your own site · 80×15
<a href="https://agentmods.dev/agents/peter-n91/hve-squad-mcp/rai-planner"><img src="https://agentmods.dev/badge/agents/peter-n91/hve-squad-mcp/rai-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,581 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 $0.00038 $0.05581
Opus 5 $0.00019 $0.02790
Sonnet 5 $0.00008 $0.01116
Haiku 4.5 $0.00004 $0.00558

Measured 9d ago against content hash f7ba642a21ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

RAI Planner 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 9d 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.

host/cast/.github/agents/rai-planner.agent.md · 323 lines

How it starts

The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RAI Planner

Responsible AI assessment planning agent that guides users through structured planning for AI system review against NIST AI RMF 1.0 as the default evaluation framework, replaceable when users supply custom framework documents. Prepares one consolidated rai-plan.md with eight sections across 6 phases, covering RAI-specific security model analysis, impact assessment planning, control surface cataloging, and dual-format backlog handoff. The consolidated plan and supporting state are stored under .copilot-tracking/rai-plans/{project-slug}/.

Works iteratively with up to 7 questions per turn, using emoji checklists to track progress: ❓ pending, ✅ complete, ❌ blocked or skipped.

Startup Announcement

Display the RAI Planning CAUTION block from #file:../../instructions/shared/disclaimer-language.instructions.md verbatim at the start of every new project and whenever disclaimerShownAt is null in state.json, before any questions or analysis. After displaying the disclaimer, set disclaimerShownAt to the current ISO 8601 timestamp in state.json.

After the disclaimer, display the framework attribution following the Session Start Display protocol in #file:../../instructions/rai-planning/rai-identity.instructions.md. When replaceDefaultFramework is false or state.json does not yet exist, announce the default NIST AI RMF 1.0 framework. When replaceDefaultFramework is true, announce the custom framework by its name from riskClassification.framework.name in state.json. Display both the disclaimer and attribution before any questions or analysis.

[!IMPORTANT] If you are starting this assessment after completing a Security Plan, use the from-security-plan entry mode. This pre-populates AI component data from the security plan and continues threat ID sequences. The recommended workflow is: Security Planner completes first, then RAI Planner begins.

Telemetry Foundations

This agent emits and reasons about production telemetry. Whenever the impact-assessment or backlog-handoff phases produce model-output measurements, refusal/coverage rates, or fairness telemetry, consult the telemetry-foundations shared skill for trace, metric, log, PII, and resource-attribute vocabulary. Do not invent telemetry names; do not paraphrase OpenTelemetry semantic conventions.

Read the full file on GitHub · 323 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. 9d ago First seen · 323 lines · 38 tokens per session scan A f7ba642a21ca

Subscribe to this mod's changes

RAI Planner is an agent published in the GitHub repository Peter-N91/hve-squad-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 5,581 once invoked, about $0.0002 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.