title-keywords

title-keywords is a command for Claude Code from Abhinavbwj/AEC-Scholar. It costs 15 tokens per session (314 once invoked), scanned A, original, MIT.

A command for improving an academic paper’s title and keyword list. It uses subject-area terminology and journal indexing guidance to suggest options and a final recommendation.

In plain words
What is it for?
Creating candidate titles, selecting keywords, and checking their fit for the paper’s likely audience and publication venue.
Why use it?
It helps make a paper easier to find while keeping its title accurate and avoiding unsupported claims.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

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

Good fit Creating candidate titles, selecting keywords, and checking their fit for the paper’s likely audience and publication venue.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/abhinavbwj/aec-scholar/title-keywords
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 title-keywords

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/abhinavbwj/aec-scholar/title-keywords"><img src="https://agentmods.dev/badge/commands/abhinavbwj/aec-scholar/title-keywords.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 314 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 $0.00015 $0.00314
Opus 5 $0.00008 $0.00157
Sonnet 5 $0.00003 $0.00063
Haiku 4.5 $0.00002 $0.00031

Measured 9d ago against content hash e802f61eb2a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

title-keywords 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/commands/title-keywords.md · 26 lines

What it actually says

Optimize the title and keywords for: $ARGUMENTS

Use the academic-writer and aec-domain-expert agents, with aec-domains (terminology) and aec-journals (indexing/SEO conventions).

  1. Titles. Propose 4–6 candidate titles spanning styles (descriptive, method-forward, finding-forward, and a question form). Each should be specific, accurate, keyword-rich at the front, free of undefined acronyms, and non-over-claiming. Briefly note the trade-off of each, then recommend one.

  2. Keywords. Propose 5–8 keywords for discoverability:

    • mix exact-topic terms with broader indexing terms,
    • include canonical AEC terminology and common synonyms searchers actually use (from aec-domains),
    • avoid words already in the title where the venue discourages repetition (check the venue's rule),
    • prefer terms that match database thesauri/indexing.
  3. Discoverability check. Note how the title+keywords position the paper for the target audience and search behavior, and whether they align with the likely venue's norms.

Keep everything truthful to the actual contribution — a catchy title that over-promises will be punished in review and erode trust. Recommend the final title + keyword set explicitly.

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 · 26 lines · 15 tokens per session scan A e802f61eb2a8

Subscribe to this mod's changes

title-keywords is a command published in the GitHub repository Abhinavbwj/AEC-Scholar (18 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 314 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.