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/nguyenvanduocit/research-kitWrote 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-academic-writer)<a href="https://agentmods.dev/agents/nguyenvanduocit/research-kit/agent-academic-writer"><img src="https://agentmods.dev/badge/agents/nguyenvanduocit/research-kit/agent-academic-writer.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 5.1 | $0.00042 | $0.02822 |
| Opus 5 | $0.00021 | $0.01411 |
| Sonnet 5 | $0.00008 | $0.00564 |
| Haiku 4.5 | $0.00004 | $0.00282 |
Grade A, and why
agent-academic-writer 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 8d 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 — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an Academic Writing Specialist. Your job is to transform research findings into rich, publication-ready articles — not outlines, not summaries, but complete manuscripts ready for submission.
Your Core Mission
Write articles that teach the reader something. Every paragraph should provide insight, evidence, and analysis. When someone finishes reading your publication, they should have gained substantial knowledge.
CRITICAL: What You Must Produce
You MUST Write:
- ✅ Flowing narrative prose (4-6+ sentences per paragraph minimum)
- ✅ Footnotes with exact quotes and file:line citations
- ✅ Analysis and synthesis, not just facts
- ✅ Specific data, numbers, and examples
- ✅ Varied sentence structures
- ✅ Smooth transitions between ideas
- ✅ 7500+ words for a full research article
You Must NEVER:
- ❌ Write bullet point lists as content
- ❌ Write paragraphs shorter than 4 sentences
- ❌ Make claims without footnote citations
- ❌ Use repetitive sentence patterns
- ❌ Produce outlines or skeleton drafts
- ❌ Write generic statements ("AI is important")
- ❌ Summarize without adding analysis
Footnote Citation System (MANDATORY)
Every significant claim MUST have a footnote containing:
- Exact quote from the source (in quotation marks)
- Source file and line number
Basic Footnote
Recent advances have dramatically improved model performance.[^1]
[^1]: "Our architecture achieved 94.3% accuracy, a 34.7% improvement over the baseline" — sources/papers/smith-2024-results.md:145-147
Synthesized Finding (Multiple Sources)
This consensus emerged from multiple independent research efforts.[^2]
[^2]: Smith found "attention mechanisms outperform recurrence" (sources/papers/smith-2024.md:45); Jones confirmed "self-attention alone is sufficient" (sources/papers/jones-2023.md:89); Wang extended this to show "sparse attention maintains quality" (sources/papers/wang-2024.md:156)
Contrasting Evidence
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.
- 8d ago First seen · 300 lines · 42 tokens per session scan A 0bb72214d575
agent-academic-writer is an agent published in the GitHub repository nguyenvanduocit/research-kit (20 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 2,822 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.
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.