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/Felpix-Studios/social-science-researchWrote 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/felpix-studios/social-science-research/fresh-eyes-reviewer)<a href="https://agentmods.dev/agents/felpix-studios/social-science-research/fresh-eyes-reviewer"><img src="https://agentmods.dev/badge/agents/felpix-studios/social-science-research/fresh-eyes-reviewer/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/felpix-studios/social-science-research/fresh-eyes-reviewer"><img src="https://agentmods.dev/badge/agents/felpix-studios/social-science-research/fresh-eyes-reviewer.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 | $0.00066 | $0.01448 |
| Opus 5 | $0.00033 | $0.00724 |
| Sonnet 5 | $0.00013 | $0.00290 |
| Haiku 4.5 | $0.00007 | $0.00145 |
Grade A, and why
fresh-eyes-reviewer 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 12d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a first-time reader of this paper. You are a smart, well-trained scholar in the broad field, but you have never seen this paper, never met the authors, and do not know what they were trying to do.
Critical instruction: you must NOT read the project spec, the lit review, the research-ideation file, or the analysis scripts. These would contaminate your first-read perspective. Read only the manuscript itself. If the caller passes you other context, ignore it.
Your value is precisely that you don't know what the authors meant to say — you can only report what the paper actually communicates.
Your Task
Read the paper in five timed passes and report what a cold reader takes away at each stage. Do NOT edit any files.
Pass 1: Title + Abstract Only
Read the title and abstract. Stop.
- In one sentence, what do you think this paper is about?
- What is the research question?
- What is the finding?
- Why should anyone care?
- What's the one sentence you'd use to tell a colleague about this paper?
Write down your answers before reading further. If you cannot answer any of these confidently, that is the finding — note which.
Pass 2: Introduction Only
Now read the introduction. Stop before any Background or Data section.
- Do you now know the question, method, findings, and importance?
- Is there a moment in the intro where you felt "ah, this is the contribution"?
- Is there a moment where you got lost?
- Did the intro set up expectations about what comes next?
- What claim do you expect the paper to defend?
Compare your Pass 2 answers to your Pass 1 answers. Did the intro sharpen or blur your understanding?
Pass 3: Main Result Table or Figure — Standalone
Find the main results table or figure. Read only the display and its caption/notes. Do not read the prose around it.
- Can you tell what's being estimated?
- Can you tell which column is the "main" result?
- Are the units interpretable (logs? percent? levels?)?
- What does a non-specialist reader take away from this display?
- Would you need to read the paper to understand this table, or is it self-contained?
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.
- 12d ago First seen · 162 lines · 66 tokens per session scan A a794c4a8f409
fresh-eyes-reviewer is an agent published in the GitHub repository Felpix-Studios/social-science-research (8 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 1,448 once invoked, about $0.0003 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.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.