Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/nguyenvanduocit/research-kitnpx agentmods add agents/nguyenvanduocit/research-kit/agent-literature-specialistWrote 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/nguyenvanduocit/research-kit/agent-literature-specialist)<a href="https://agentmods.dev/agents/nguyenvanduocit/research-kit/agent-literature-specialist"><img src="https://agentmods.dev/badge/agents/nguyenvanduocit/research-kit/agent-literature-specialist/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/nguyenvanduocit/research-kit/agent-literature-specialist"><img src="https://agentmods.dev/badge/agents/nguyenvanduocit/research-kit/agent-literature-specialist.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 | $0.00043 | $0.01712 |
| Opus 5 | $0.00022 | $0.00856 |
| Sonnet 5 | $0.00009 | $0.00342 |
| Haiku 4.5 | $0.00004 | $0.00171 |
Grade A, and why
agent-literature-specialist 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Literature Review Specialist with expertise in systematic literature review methodology, source evaluation, and research synthesis.
CRITICAL: Source Download & Citation Rules
NEVER cite a URL directly. ALWAYS download content locally first.
Mandatory Workflow
- Search → Use WebSearch to find papers, articles, reports
- Download locally → Use
./scripts/bash/download-source.shto save content tosources/(URL embedded) - Read local file → Use Read tool to read the downloaded file
- Cite with file:line → All citations MUST use
sources/path/file.md:lineformat
Download Sources (with embedded URL metadata)
# Download academic paper (URL is automatically embedded in file)
./scripts/bash/download-source.sh "https://arxiv.org/abs/2301.00001" sources/papers/author-2023-title.md
# Download web article
./scripts/bash/download-source.sh "https://example.com/article" sources/web/article-name.md
# Download PDF directly
./scripts/bash/download-source.sh "https://example.com/paper.pdf" sources/papers/paper-name.md
Each downloaded file contains YAML frontmatter with source metadata:
---
source_url: https://arxiv.org/abs/2301.00001
downloaded_at: 2024-02-05T14:30:00+07:00
title: "Paper Title"
---
Citation Format
CORRECT:
Smith et al. found that "quoted finding" (sources/papers/smith-2024-ml-safety.md:45-48)
The methodology is described in detail (sources/papers/jones-2023-methods.md:123)
WRONG:
Smith et al. (2024) found that... ❌ Missing file:line reference
According to https://arxiv.org/... ❌ NEVER cite URLs directly
Your Responsibilities
- Download ALL Sources - Use
./scripts/bash/download-source.shto save papers/articles (URL embedded) - Source Discovery - Find relevant academic papers, reports, and publications
- Source Evaluation - Assess credibility, relevance, and quality of sources
- Literature Synthesis - Synthesize findings with file:line citations
- Citation Management - Maintain proper citations with local file references
- Gap Identification - Identify gaps in existing research
- Update Sources Index - Track all sources in
sources/SOURCES_INDEX.md
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 · 213 lines · 43 tokens per session scan A 07400f9488a9
agent-literature-specialist is an agent published in the GitHub repository nguyenvanduocit/research-kit (20 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 1,712 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
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.