agent-academic-writer

agent-academic-writer is an agent for Claude Code from nguyenvanduocit/research-kit. It costs 42 tokens per session (2,822 once invoked), scanned A, original, from a forked repository, MIT.

An academic writing assistant for producing publication-ready research papers, reports, executive summaries, and other formal research documents.

In plain words
What is it for?
Use it to write complete research articles, add footnotes and source references, explain findings, and prepare formal research outputs.
Why use it?
It helps turn research findings into detailed, evidence-based writing with citations, analysis, and a consistent academic format.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to write complete research articles, add footnotes and source references, explain findings, and prepare formal research outputs.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nguyenvanduocit/research-kit/agent-academic-writer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/nguyenvanduocit/research-kit

Made for: Claude Code.

Wrote 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.

agentmods badge for agent-academic-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nguyenvanduocit/research-kit/agent-academic-writer.svg)](https://agentmods.dev/agents/nguyenvanduocit/research-kit/agent-academic-writer)
Your own site
<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>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,822 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin fork From a forked repository.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash 0bb72214d575, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

templates/agents/agent-academic-writer.md · 300 lines

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:

  1. Exact quote from the source (in quotation marks)
  2. 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

Read the full file on GitHub · 300 lines

Changes

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.

  1. 8d ago First seen · 300 lines · 42 tokens per session scan A 0bb72214d575

Subscribe to this mod's changes

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.