A command for writing or improving an abstract for an architecture, engineering, or construction manuscript. It uses an academic writing agent and writing guidance.

Use it to draft or refine abstracts, meet a target word limit, adapt structure to a venue, and identify weaknesses in an existing abstract.

It helps turn a manuscript or notes into a self-contained abstract with a clear problem, method, results, and contribution. It also checks for vague claims, undefined acronyms, missing evidence, and overstatement.

abstract — Command for Claude Code by Abhinavbwj

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/abhinavbwj/aec-scholar/abstract.svg)](https://agentmods.dev/commands/abhinavbwj/aec-scholar/abstract)

Your own site

<a href="https://agentmods.dev/commands/abhinavbwj/aec-scholar/abstract"><img src="https://agentmods.dev/badge/commands/abhinavbwj/aec-scholar/abstract.svg" alt="Measured on agentmods" height="20"></a>

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 363 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.

Model	Per session	Once invoked
Fable 5.1	$0.00014	$0.00363
Opus 5	$0.00007	$0.00181
Sonnet 5	$0.00003	$0.00073
Haiku 4.5	$0.00001	$0.00036

Measured 7d ago against content hash 1f60f8eee46d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

abstract 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 7d 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/abstract.md · 29 lines

What it actually says

Write or refine an abstract for: $ARGUMENTS

Use the academic-writer agent and the academic-writing skill.

Gather the essentials from the manuscript/points: context & problem, the specific gap/objective, the method, the key concrete results (numbers beat adjectives), and the contribution/implication.
Draft the abstract to the target length (default 150–250 words; honor the venue limit if given), in the venue's structure (structured headings vs single paragraph). Ensure it is self-contained: no citations, no undefined acronyms, and nothing that isn't in the paper.
Make it concrete. Replace vague claims with specifics ("improved accuracy" → "improved detection F1 from 0.74 to 0.88"). Lead with the problem, land on the contribution.
Provide a short critique of the draft (or the user's existing abstract): is the gap clear? is the contribution explicit? are results concrete? does it over-claim? Then give the polished version.
Offer to also generate a graphical-abstract outline, highlights (3–5 bullet points, ≤85 chars each — Elsevier style), and a plain-language summary if the venue asks for them.

Integrity: the abstract must accurately represent the paper. Do not state results the manuscript doesn't contain; if key numbers are missing, ask for them or mark placeholders.

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.

7d ago First seen · 29 lines · 14 tokens per session scan A 1f60f8eee46d

Subscribe to this mod's changes

abstract is a command published in the GitHub repository Abhinavbwj/AEC-Scholar (18 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 363 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.

Writing and docs

abstract

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

converge

implement

analyze