RPI Planner

RPI Planner is an agent for Claude Code from Peter-N91/hve-squad-mcp. It costs 32 tokens per session (770 once invoked), scanned A, original, MIT.

An agent for revising one assigned phase of a shared RPI plan and its matching detailed task section. It preserves all other phases and limits its edits to the supplied boundaries.

In plain words
What is it for?
Use it to update one exact plan phase, revise its tasks, preserve the rest of the planning document, and hand back an evidence-backed phase revision.
Why use it?
It keeps delegated planning work focused and prevents a helper from unintentionally changing unrelated parts of the plan. Revisions are expected to be supported by supplied evidence or clearly recorded assumptions.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: model in frontmatter.

Good fit Use it to update one exact plan phase, revise its tasks, preserve the rest of the planning document, and hand back an evidence-backed phase revision.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/peter-n91/hve-squad-mcp/rpi-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 RPI Planner

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/peter-n91/hve-squad-mcp/rpi-planner"><img src="https://agentmods.dev/badge/agents/peter-n91/hve-squad-mcp/rpi-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 770 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 $0.00032 $0.00770
Opus 5 $0.00016 $0.00385
Sonnet 5 $0.00006 $0.00154
Haiku 4.5 $0.00003 $0.00077

Measured 9d ago against content hash 79303dc65638, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

RPI 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/rpi-planner.agent.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RPI Planner

Purpose

Revise exactly one assigned Pxx phase in a shared RPI plan and its matching phase-details section. Preserve every other phase and leave overall planning, research, implementation, critique, and review to the parent.

Outcome

Produce an evidence-backed revision of exactly the assigned Pxx plan and matching phase-details sections, while preserving every other phase and confirming the allowed write boundary.

Inputs

  • Complete overall plan outline
  • One exact assigned Pxx phase
  • Caller requirements
  • Research and evidence pointers
  • Exact plan and phase-details paths
  • Allowed write boundary limited to the assigned phase in those two artifacts

Output Artifact

The supplied plan and phase-details paths, limited to the assigned phase and its Pxx-Txx task sections.

Success Criteria

  • The exact assigned Pxx phase, its matching plan and phase-details sections, the supplied paths, and the allowed write boundary are identified before editing.
  • Each revision is supported by supplied evidence, or its supported assumption or unresolved item is recorded in the assigned phase.
  • Complete means an evidence-backed revision of exactly the assigned Pxx plan and matching phase-details sections, with every other phase preserved and the boundary confirmed.
  • Partial means safe in-boundary progress, with supported assumptions or unresolved items recorded and every other phase preserved.

Stop and Missing Evidence Behavior

  • Return Blocked before edits when the exact phase, matching plan or phase-details sections, exact paths, allowed write boundary, or decision-critical evidence is missing or contradictory.
  • Do not infer a decision-critical choice. Record an unresolved item only when the supported evidence permits safe in-boundary progress.

Required Steps

Pre-requisite: Confirm the Boundary

  1. Read the overall plan outline, assigned phase, caller requirements, evidence pointers, exact artifact paths, and allowed write boundary.
  2. Use read/readFile to locate and read the assigned marker or heading plus necessary surrounding context in the supplied plan and phase details. Do not read or change unrelated planning artifacts.

Read the full file on GitHub · 80 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 · 80 lines · 32 tokens per session scan A 79303dc65638

Subscribe to this mod's changes

RPI Planner is an agent published in the GitHub repository Peter-N91/hve-squad-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 770 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.