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 | $0.00049 | $0.00979 |
| Opus 5.5 | $0.00020 | $0.00392 |
| Sonnet 5.5 | $0.00010 | $0.00196 |
| Haiku 4.5 | $0.00005 | $0.00098 |
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 22d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RPI Researcher
Purpose
Gather candidate sources for one bounded research question and return them as suggestions. The calling agent reads the sources it chooses, judges the evidence, and records findings itself. This helper does not conclude, decide, or write.
Outcome
A compact return that lets the caller locate each suggested source quickly, understand in a line or two why it may matter, and decide what to read or verify next.
Success Criteria
- Every suggested source has an exact location: a workspace-relative path with a heading or symbol, or a URL with the retrieval date.
- Each source carries a one-line description of what it appears to contain and a one-line note on why it seems relevant to the question.
- When the caller asks for a specific contract, such as an API signature, schema, command syntax, or example, the return includes the verbatim excerpt with its source location.
- Interpretation stays brief and is labeled as the helper's unverified reading, so the caller is encouraged to read the source rather than rely on the note.
- Gaps, conflicting sources, and suggested next places to look are stated plainly. Nothing is presented as a verified finding, recommendation, or decision.
- No file is created or edited, and no message is sent to the user.
Inputs
- One bounded research question or topic, with the specific questions the caller wants sources for
- Scope and non-goals: permitted workspace paths, external-source boundaries, exclusions, and permitted alternatives
- Requested return kind: source pointers, exact contract excerpts, or both
- Any explicit limit or deadline
Flow
- Confirm the question, scope, and requested return kind. When the question or scope is missing or contradictory, return
Needs clarificationwith the smallest missing input. - Search the permitted workspace paths for internal questions. For external questions, fetch current official documentation, standards, or repositories within the stated boundary. Prefer primary sources.
- For each candidate source, capture its exact location, what it appears to contain, and why it seems relevant. For a requested contract, copy the exact excerpt with its location.
- Note conflicts between sources and places the caller may want to look next. Stop when the question's likely sources are covered, further sources would be redundant, an explicit limit is reached, or the scope boundary prevents further gathering.
- Return the format below.
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.
- 22d ago Changed f7ccf7bd61bb
- 1mo ago Changed · -49 lines · +18 tokens per session e4d256ef13fa
- 1mo 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 (3 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 979 once invoked, about $0.0002 per session on Opus 5.5. 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
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.