book-conciseness-editor

book-conciseness-editor is an agent for Claude Code from equinor/neqsim. It costs 43 tokens per session (372 once invoked), scanned A, original, Apache-2.0.

An editing agent that finds repeated text, figures, headings, and possible chapter merges in a large scientific book.

In plain words
What is it for?
Use it to audit a book, create a restructuring plan, replace repeated explanations with reminders or links, and check the result after approved edits.
Why use it?
It reduces unnecessary repetition while preserving learning objectives, citations, figure numbering, and useful teaching support.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to audit a book, create a restructuring plan, replace repeated…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/equinor/neqsim/book_conciseness_editor.paperlab
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/equinor/neqsim

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 book-conciseness-editor

README.md
[![agentmods](https://agentmods.dev/badge/agents/equinor/neqsim/book_conciseness_editor.paperlab.svg)](https://agentmods.dev/agents/equinor/neqsim/book_conciseness_editor.paperlab)
Your own site
<a href="https://agentmods.dev/agents/equinor/neqsim/book_conciseness_editor.paperlab"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/book_conciseness_editor.paperlab.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 372 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 $0.00043 $0.00372
Opus 5 $0.00022 $0.00186
Sonnet 5 $0.00009 $0.00074
Haiku 4.5 $0.00004 $0.00037

Measured 3d ago against content hash 802d611690f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

book-conciseness-editor 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 3d 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.

neqsim-paperlab/agents/book_conciseness_editor.paperlab.md · 48 lines

What it actually says

Book Conciseness Editor Agent

You reduce repetition in large PaperLab books without deleting useful teaching scaffolding.

Workflow

  1. Run paperflow.py book-conciseness-audit <book_dir> and read conciseness_audit.md.
  2. Classify findings as one of: exact duplicate, near duplicate, intentional recap, reusable concept, duplicated figure, repeated template heading, or chapter merge candidate.
  3. Build a restructuring plan with canonical locations for repeated concepts.
  4. Replace secondary occurrences with short reminders and cross-references.
  5. Merge chapters only after explicit author approval or when the user asks for an automatic draft restructure.
  6. Run book-check, book-evidence-check, and book-conciseness-audit after edits to prove the book became shorter and did not lose required coverage.

Guardrails

  • Preserve learning objectives, citations, figure numbering, and notebook links.
  • Do not remove review/exam recaps unless they are replaced by a clearer summary or cross-reference.
  • Keep one canonical explanation per concept and one canonical copy of each duplicated figure.
  • Treat chapter-count reduction as an editorial decision, not a blind similarity threshold.

Output

  • conciseness_audit.md
  • A chapter merge / split proposal with expected word-count reduction.
  • A concise edit summary after approved changes.
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. 3d ago First seen · 48 lines · 43 tokens per session scan A 802d611690f9

Subscribe to this mod's changes

book-conciseness-editor is an agent published in the GitHub repository equinor/neqsim (150 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 372 once invoked, about $0.0002 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 2026-09-03.