paper-draft

paper-draft is a command for Claude Code from Abhinavbwj/AEC-Scholar. It costs 17 tokens per session (457 once invoked), scanned A, original, MIT.

A writing assistant for drafting or reorganising parts of a research manuscript, such as the introduction, methods, results, or discussion.

In plain words
What is it for?
Use it to draft or improve a paper section, thesis chapter, or conclusion from material and sources you provide.
Why use it?
It helps match each section to its intended purpose and keeps claims tied to evidence. Missing sources are marked for later citation instead of being made up.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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

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.

agentmods
npx agentmods add commands/abhinavbwj/aec-scholar/paper-draft
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 paper-draft

README.md
[![agentmods](https://agentmods.dev/badge/commands/abhinavbwj/aec-scholar/paper-draft.svg)](https://agentmods.dev/commands/abhinavbwj/aec-scholar/paper-draft)
Your own site
<a href="https://agentmods.dev/commands/abhinavbwj/aec-scholar/paper-draft"><img src="https://agentmods.dev/badge/commands/abhinavbwj/aec-scholar/paper-draft.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 457 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00017 $0.00457
Opus 5 $0.00009 $0.00229
Sonnet 5 $0.00003 $0.00091
Haiku 4.5 $0.00002 $0.00046

Measured 6d ago against content hash e0a504823cdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

paper-draft 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 6d 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/commands/paper-draft.md · 35 lines

What it actually says

Draft or improve a manuscript section. Request: $ARGUMENTS

Use the academic-writer agent and the academic-writing skill (and aec-domains/research-methods for domain and method accuracy).

  1. Identify the section (Introduction, Background/Lit review, Methods, Results, Discussion, Conclusion, or a thesis chapter) and apply its specific job:

    • Introduction: CARS move — territory → niche/gap → occupy; end with an explicit "This paper contributes…".
    • Background: synthesize thematically, define the framework, build toward the gap.
    • Methods: reproducible detail + justification + validity/ethics.
    • Results: findings without interpretation; lead with the answer to each RQ; numbers + uncertainty.
    • Discussion: interpret, compare with prior work, theoretical + practical/industry implications, honest limitations → future work.
    • Conclusion: restate contribution & key findings, no new data.
  2. Draft from the user's material. Use only the facts, data and sources the user provides. Where a claim needs a citation the user hasn't supplied, insert [CITATION NEEDED: …] rather than inventing one.

  3. Enforce style. Clarity, claim→evidence→warrant, correct tense/voice, SI units with uncertainty, consistent terminology, defined acronyms, calibrated hedging (no over-claiming), and AEC reviewer expectations (explicit contribution, practical implications, generalizability limits, reproducibility).

  4. Return the drafted section plus a brief note of (a) the key edits/choices and (b) every place the author must supply evidence, data, or a citation.

Integrity: never fabricate data, results, or references. You are drafting the author's argument from the author's material — flag every gap that only they can fill.

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. 6d ago First seen · 35 lines · 17 tokens per session scan A e0a504823cdc

Subscribe to this mod's changes

paper-draft is a command published in the GitHub repository Abhinavbwj/AEC-Scholar (18 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 457 once invoked, about $0.0001 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.