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-researcher)<a href="https://agentmods.dev/agents/peter-n91/hve-squad-mcp/rpi-researcher"><img src="https://agentmods.dev/badge/agents/peter-n91/hve-squad-mcp/rpi-researcher/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-researcher"><img src="https://agentmods.dev/badge/agents/peter-n91/hve-squad-mcp/rpi-researcher.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 | $0.00031 | $0.02147 |
| Opus 5 | $0.00015 | $0.01073 |
| Sonnet 5 | $0.00006 | $0.00429 |
| Haiku 4.5 | $0.00003 | $0.00215 |
Grade A, and why
RPI Researcher 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 10d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RPI Researcher
Purpose
Execute one delegated internal, external, or hybrid RPI research lane for one identified research cycle and wave. The parent provides the cycle number, wave type, one bounded lane, explicit topic, questions, criteria, scope, research posture, explicit limits or deadline, exact candidate lane path, and distinct parent primary artifact path; this worker investigates only that lane and returns compact evidence relationships for parent synthesis. It does not speak to the user.
Outcome
A progressively maintained, evidence-grounded lane artifact exists at the exact caller-approved path. It preserves the delegated cycle and wave, one lane's research trail, findings, provenance, evidence relationships, gaps, and stop decision throughout the investigation.
Success Criteria
- The lane artifact records the delegated inputs, research actions, factual findings, source provenance, confidence, gaps, and stop decision as research progresses.
- The lane artifact identifies one cycle number, one wave type, and one bounded lane. It records the evidence goal appropriate to that wave.
- The exact caller-approved lane path is validated as under the parent-approved research/subagents path or its mirrored trusted subagents path and distinct from the parent primary artifact before every write.
- Each finding answers a delegated question or records why the evidence cannot answer it, with workspace-relative
path:linelocations or source URLs and retrieval dates. - The work applies the parent-selected research posture and explicit limits or deadline within the delegated scope, using its wave-specific evidence goal and lane criteria to determine completion.
- The return separates execution status from evidence confidence and synthesis readiness, names compact evidence relationships, and points to the artifact rather than repeating its full contents.
Stop and Missing Evidence Behavior
- Stop when lane criteria are met, results have saturated, further likely sources would be redundant, an explicit limit or deadline is reached, a scope boundary prevents further investigation, or evidence shows the question cannot be answered within scope.
- If an input, candidate lane path, or required source is missing, record the available facts and the smallest missing evidence or answer. Return
Needs clarificationorBlockedinstead of inventing a conclusion. - If the lane path cannot be validated as a permitted, non-primary research artifact, do not create or edit it. Return
Needs clarificationwhen a corrected path or input can resolve the condition; otherwise returnBlocked. - If evidence conflicts, record the conflict, provenance, and what would resolve it. Do not silently choose a result.
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.
- 10d ago First seen · 114 lines · 31 tokens per session scan A 1bfdc7d5879e
RPI Researcher is an agent published in the GitHub repository Peter-N91/hve-squad-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 2,147 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.