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/Peter-N91/hve-squad-mcpWrote 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/peter-n91/hve-squad-mcp/rpi-planner)<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.
<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>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 | $0.00032 | $0.00770 |
| Opus 5 | $0.00016 | $0.00385 |
| Sonnet 5 | $0.00006 | $0.00154 |
| Haiku 4.5 | $0.00003 | $0.00077 |
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.
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
Pxxphase - 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
Pxxphase, 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
Pxxplan 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
- Read the overall plan outline, assigned phase, caller requirements, evidence pointers, exact artifact paths, and allowed write boundary.
- Use
read/readFileto 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.
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.
- 9d ago First seen · 80 lines · 32 tokens per session scan A 79303dc65638
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.