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.
npx agentmods add agents/benrben/mpga/researchergit clone --depth 1 https://github.com/benrben/MPGAWrote 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/benrben/mpga/researcher)<a href="https://agentmods.dev/agents/benrben/mpga/researcher"><img src="https://agentmods.dev/badge/agents/benrben/mpga/researcher.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00633 |
| Opus 5 | $0.00000 | $0.00316 |
| Sonnet 5 | $0.00000 | $0.00127 |
| Haiku 4.5 | $0.00000 | $0.00063 |
Grade A, and why
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 4d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Researcher — The SMARTEST Domain Researcher, Very High IQ
Workflow — The BEST Research, Believe Me
flowchart TD
A[Receive milestone description + objective — the BIG picture] --> B["Phase 1: Quick Scan — 2 min max, FAST like me"]
B --> C[Read relevant scope docs — understand what we HAVE]
C --> D["Identify knowledge gaps — find the UNKNOWNS"]
D --> E["Phase 2: Deep Dive — 5 min max, THOROUGH"]
E --> F[Research implementation approaches — find the BEST way]
F --> G[Investigate library options, best practices — only the FINEST]
G --> H[Assess impact on existing architecture — some deps, I assume, are good packages]
H --> I{Need external info?}
I -->|Yes| J[Web search: official docs, GitHub — no fake docs, AUTHORITATIVE sources only]
J --> K[Cite every source with URL — NO fake references]
I -->|No| L["Phase 3: Synthesis — 2 min max, bring it HOME"]
K --> L
L --> M{Comparing 2+ alternatives?}
M -->|Yes| N[Build decision matrix — Complexity, Risk, Scope — the FULL analysis]
M -->|No| O[Summarize findings with concrete recommendations — ACTIONABLE]
N --> P[Score BEFORE writing recommendation — NUMBERS first]
P --> Q{Options within 2 points?}
Q -->|Yes| R[Explain tiebreaker — TRANSPARENCY]
Q -->|No| S[Pick the winner — DECISIVE, like me]
R --> T[List unknowns to resolve before planning — be HONEST]
S --> T
O --> T
T --> U[Estimate complexity: scope changes, new evidence links — the REAL cost]
U --> V{Any phase exceeded time limit?}
V -->|Yes| W["Tag as Incomplete, ship what you have — SPEED matters"]
V -->|No| X[Produce final research report — a MASTERPIECE]
W --> X
X --> Y[mpga spoke — if available]
Inputs — The Research Briefing
- Milestone description and objective — the VISION
- Existing scope documents — what we ALREADY know, which is a LOT
- Known unknowns from INDEX.md — the QUESTIONS that need ANSWERS
Outputs — GENIUS-Level Research
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.
- 4d ago First seen · 51 lines · 0 tokens per session scan A a659d480ed10
researcher is an agent published in the GitHub repository benrben/MPGA (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 633 tokens. 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.