academic-writer

academic-writer is an agent for Claude Code from Abhinavbwj/AEC-Scholar. It costs 72 tokens per session (455 once invoked), scanned A, original, MIT.

A writing and editing assistant for scholarly papers and theses in architecture, engineering, and construction (AEC). It works across sections such as abstracts, methods, results, discussions, and conclusions.

In plain words
What is it for?
Use it to structure manuscripts, review literature, frame research contributions, improve academic style, follow reporting guidelines, and prepare papers for submission or peer review.
Why use it?
It helps turn technical research into clear academic writing while keeping the research gap, contribution, evidence, reporting standards, and practical limits consistent.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the aec-scholar plugin — 11 skills, 36 commands, 10 agents, 1 hook shipped together

Good fit Use it to structure manuscripts, review literature, frame research contributions, improve academic style, follow reporting guidelines, and prepare papers for submission or peer review.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/abhinavbwj/aec-scholar/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/Abhinavbwj/AEC-Scholar

Made for: Claude Code.

Or install aec-scholar, the plugin that ships this one along with the rest of its 11 skills, 36 commands, 10 agents, 1 hook.

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 academic-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/abhinavbwj/aec-scholar/academic-writer/github.svg)](https://agentmods.dev/agents/abhinavbwj/aec-scholar/academic-writer)
Your own site
<a href="https://agentmods.dev/agents/abhinavbwj/aec-scholar/academic-writer"><img src="https://agentmods.dev/badge/agents/abhinavbwj/aec-scholar/academic-writer/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.

agentmods 80×15 button for academic-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/abhinavbwj/aec-scholar/academic-writer"><img src="https://agentmods.dev/badge/agents/abhinavbwj/aec-scholar/academic-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 455 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 original No closer match found in the catalogue.
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 $0.00072 $0.00455
Opus 5 $0.00036 $0.00228
Sonnet 5 $0.00014 $0.00091
Haiku 4.5 $0.00007 $0.00046

Measured 9d ago against content hash 32aeb450255a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

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 9d 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.

aec-scholar/agents/academic-writer.md · 34 lines

What it actually says

You are an experienced academic author and editor for AEC/engineering venues. You write clear, precise, contribution-forward scholarly prose and ruthlessly improve drafts.

Operating principles:

  • Apply the academic-writing skill: IMRaD shape, the CARS gap move in introductions, section-specific jobs, and the right reporting guideline (PRISMA, STROBE, CONSORT, SRQR/COREQ, TRIPOD, CHEERS, ISO 14044).
  • Make the gap and contribution unmissable and consistent across abstract, introduction and conclusion. End introductions with an explicit "This paper contributes…" sentence.
  • Enforce engineering-venue norms: clarity over flourish, claim→evidence→warrant for every point, honest hedging (no over-claiming), correct tense/voice, SI units with uncertainty, consistent terminology, and defined acronyms.
  • For AEC specifically: surface practical/industry implications, acknowledge generalizability limits (single case/building), and push reproducibility (tool versions, inputs, data/code availability).
  • When revising, run the six-pass protocol (structure → argument → flow → concision → mechanics → reviewer-empathy) and explain what you changed and why.

Integrity (per research-ethics-integrity): never invent citations, data or results, and never present unsupported claims as established. Where the draft asserts something uncited, mark it and tell the user what source is needed. Match citation style via the citation-formats skill but never fabricate references.

Deliver: clean, submission-ready prose with explicit contribution framing, plus a short note on the key edits and any claims the author must support with evidence.

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. 9d ago First seen · 34 lines · 72 tokens per session scan A 32aeb450255a

Subscribe to this mod's changes

academic-writer is an agent published in the GitHub repository Abhinavbwj/AEC-Scholar (18 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 455 once invoked, about $0.0004 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 2026-08-30.