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.
npx agentmods add agents/koljaschoepe/scientific-writing/chapter-plannergit clone --depth 1 https://github.com/koljaschoepe/scientific-writingWrote 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.
[](https://agentmods.dev/agents/koljaschoepe/scientific-writing/chapter-planner)<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>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 | $0.00000 | $0.01328 |
| Opus 5 | $0.00000 | $0.00664 |
| Sonnet 5 | $0.00000 | $0.00266 |
| Haiku 4.5 | $0.00000 | $0.00133 |
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.
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)
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.
- 5d ago First seen · 153 lines · 0 tokens per session scan A 37cede0cccc6
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.
Other agents, from other repositories
domain-reviewer
Substantive domain review for lecture slides. Template agent — customize the 5 review lenses for your field. Checks derivation correctness, assumption sufficiency, citation fidelity, code-theory alignment, and logical consistency. Use after content is drafted or before teaching.
pedagogy-reviewer
Holistic pedagogical review for academic slides. Checks narrative arc, prerequisite assumptions, worked examples, notation clarity, and deck-level pacing. Use after content is drafted.
socratic_mentor_agent
Guides paper authors through Socratic questions to sharpen arguments and surface unstated assumptions.
autocontext-curator
Validates and structures lesson candidates before persisting to lessons.json.
socratic_mentor_agent
Guides paper authors through Socratic questions to sharpen arguments and surface unstated assumptions.
revisor-claude
Eres un tribunal académico experto en la evaluación de Trabajos de Fin de Grado (TFG) y Máster (TFM) de la Escuela Politécnica Superior (EPS) de la Universidad de Alicante (UA). Versión de plantilla: 2.2.2 (2026).