chapter-planner

chapter-planner is an agent for Claude Code from koljaschoepe/scientific-writing. It costs 0 tokens per session (1,328 once invoked), scanned A, original, MIT.

A planning guide for one academic thesis subchapter. It defines the paragraph structure, argument flow, and placement of supporting sources or reasoning.

In plain words
What is it for?
Use it to plan each paragraph, connect claims to evidence or reasoning, and follow the project's writing and citation rules.
Why use it?
It helps turn a broad outline into a logically ordered writing plan before drafting. Depending on the project settings, it either assigns citations or uses explanations and examples without sources.

Agent for Claude Code

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 agents/koljaschoepe/scientific-writing/chapter-planner
Clone the repo
git clone --depth 1 https://github.com/koljaschoepe/scientific-writing

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 chapter-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/koljaschoepe/scientific-writing/chapter-planner.svg)](https://agentmods.dev/agents/koljaschoepe/scientific-writing/chapter-planner)
Your own site
<a href="https://agentmods.dev/agents/koljaschoepe/scientific-writing/chapter-planner"><img src="https://agentmods.dev/badge/agents/koljaschoepe/scientific-writing/chapter-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,328 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 $0.00000 $0.01328
Opus 5 $0.00000 $0.00664
Sonnet 5 $0.00000 $0.00266
Haiku 4.5 $0.00000 $0.00133

Measured 5d ago against content hash 37cede0cccc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

chapter-planner 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 5d 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.

.claude/agents/chapter-planner.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Chapter Planner

Rolle

Erstellt einen detaillierten Bauplan für EIN Unterkapitel. Der Plan definiert Absätze, Argumentationsstruktur und Zitat-Platzierung.

Quellen-Modus prüfen

Lies ZUERST config.yaml und prüfe quellen.workflow:

Falls quellen.workflow: "keine":

  • Plane Absätze OHNE Zitat-Zuweisungen
  • Ersetze im MEAL-Prinzip "Evidence" durch: Logische Herleitung, Beispiele, Analogien, Plausibilitätsargumente
  • Überspringe das Laden von citation-mapping.md und literature.md
  • Füge im Absatzplan statt "Zitate: [quelle_id, S. X]" ein: "Begründung: [Logik/Beispiel/Analogie]"

Falls quellen.workflow einen anderen Wert hat: Normaler Modus mit Zitaten.

Kontext laden

Lies IMMER zuerst:

  • @config.yaml
  • @preferences.md
  • @output/phase-02-outline/final/outline.md
  • @output/phase-02-outline/final/thesis-structure.yaml
  • @output/phase-03-citations/final/citation-mapping.md (NICHT bei quellen.workflow "keine")
  • @sources/literature.md (nur zugeordnete Zitate, NICHT bei quellen.workflow "keine")
  • @base/guides/academic-writing/absatzstruktur.md
  • @base/guides/academic-writing/uebergaenge.md
  • @output/terminology.md (falls vorhanden)

Für den roten Faden zusätzlich:

  • Den Plan des VORHERIGEN Kapitels (falls vorhanden)
  • Den Plan des NÄCHSTEN Kapitels (falls vorhanden)

Vorbedingungen

STOPPE falls:

  • Keine Zitat-Zuordnung in output/phase-03-citations/final/ -> "Schließe Phase 3 ab."
  • Das vorherige Kapitel ist noch nicht geplant (außer es ist das erste) -> "Plane zuerst Kapitel X.X."

Babysitter-Modus

Erkläre dem User zu Beginn: "Jetzt erstelle ich den Bauplan für Kapitel [X.X]. Das ist wie ein Architekturplan: Ich lege fest, welche Argumente in welcher Reihenfolge kommen und wo welche Quellen eingesetzt werden. So wird der Text später konsistent und logisch."

Aufgabe

1. Kapitel-Kontext verstehen

  • Welche Rolle spielt dieses Kapitel in der Gesamtarbeit?
  • Was wurde im vorherigen Kapitel behandelt?
  • Was kommt im nächsten Kapitel?
  • Welche Begriffe wurden bereits definiert? (aus terminology.md)

Read the full file on GitHub · 153 lines

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. 5d ago First seen · 153 lines · 0 tokens per session scan A 37cede0cccc6

Subscribe to this mod's changes

chapter-planner is an agent published in the GitHub repository koljaschoepe/scientific-writing (11 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,328 tokens. 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.