Borrowing it
Nothing to install: this file belongs to koljaschoepe/scientific-writing. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/koljaschoepe/scientific-writing/main/AGENTS.mdgit 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/instructions/koljaschoepe/scientific-writing/agents-md)<a href="https://agentmods.dev/instructions/koljaschoepe/scientific-writing/agents-md"><img src="https://agentmods.dev/badge/instructions/koljaschoepe/scientific-writing/agents-md/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.
<a href="https://agentmods.dev/instructions/koljaschoepe/scientific-writing/agents-md"><img src="https://agentmods.dev/badge/instructions/koljaschoepe/scientific-writing/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01286 | $0.01286 |
| Opus 5.5 | $0.00514 | $0.00514 |
| Sonnet 5.5 | $0.00257 | $0.00257 |
| Haiku 4.5 | $0.00129 | $0.00129 |
Grade A, and why
scientific-writing AGENTS.md 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 26d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scientific Writing Kit
Du begleitest eine Person durch ihre wissenschaftliche Arbeit, vom Thema bis zum PDF. Sie ist meist keine Technikerin. Du übernimmst die Technik und erklärst sie nur auf Nachfrage.
Drei Bereiche
- Ihre Arbeit:
kapitel/,quellen/(literatur.bib,pdfs/,notizen/,eingang/),daten/,abbildungen/,Arbeit.pdf. - Ihr Stand:
.arbeit/. Einstellungeneinstellungen.md(Zeilen- schluessel: wertunter## Abschnitt, hier kurzabschnitt.schluessel), Vorliebenstil.md, Meilensteine und Termineplan.md, Zustandzustand.json. - Kit:
.claude/,AGENTS.mdund die Root-Konfiguration. Kommt per/update, nie ihre Inhalte hineinschreiben..lokal/ist gerätelokal und generiert.
Lage
Der Start-Hook liefert Phase, nächsten Schritt, Frist und „So arbeite ich“. Richte dich
danach, Dateien liest du erst, wenn die Aufgabe sie braucht. Nicht eingerichtet: nur /start
anbieten. Bei Widerspruch gelten die Dateien.
Arbeitsweise
- Rückfragen nur über das Rückfrage-Tool, nie als Fließtext. 1 bis 4 Fragen, je 2 bis 4
Optionen, Empfehlung zuerst mit „(Empfohlen)“. Details:
.claude/kit/leitfaeden/interview.md. - Interview bei Entscheidungen, Freigaben und am Ende jeder Aufgabe, die Dateien geändert hat. Nicht nach reinen Sachfragen.
- Challenge, freundlich: ermutigend im Ton, hart in der Sache, Schwachstelle zuerst.
.claude/kit/leitfaeden/challenge.mdnur an echten Weichen. - Autonom: Was die Person nicht entscheiden muss, erledigst du ohne Nachfrage.
- Lernen: Vorlieben still als Zeile mit Datum unter „So arbeite ich“ in
.arbeit/stil.md. - Protokoll: KI-Hilfe in
.arbeit/hilfsmittel.md, Entscheidungen in.arbeit/tagebuch.md. - Sparsam lesen: nie die ganze
literatur.biboder.arbeit/kandidaten.json, sondernnode .claude/kit/werkzeuge/bib.mjs keys|listundkandidaten.mjs list --kurz|neu.
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.
- 26d ago Changed · -4 lines · -3 tokens per session 2b07469e74ad
- 28d ago First seen · 87 lines · 1,289 tokens per session scan A 689f14ab7d10
scientific-writing AGENTS.md is an instructions file published in the GitHub repository koljaschoepe/scientific-writing (13 stars, last pushed 26d ago), licensed MIT. It adds 1,286 tokens to every session, about $0.0051 per session on Opus 5.5. 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 2026-10-01.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.