What is full-page-pdf-snap AGENTS.md?

Repository instructions for a website and browser-extension project that publishes measured results and citation data. They require claims to be backed by methods, raw data, and checks.

Use them when changing the site, validating raw data, running checks, or adding measurements and citations.

They reduce unsupported numbers and make published results reproducible, meaning another person can check how they were obtained.

How Bubu89/full-page-pdf-snap configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Bubu89/full-page-pdf-snap. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Bubu89/full-page-pdf-snap/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Bubu89/full-page-pdf-snap

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/bubu89/full-page-pdf-snap/agents-md/github.svg)](https://agentmods.dev/instructions/bubu89/full-page-pdf-snap/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/bubu89/full-page-pdf-snap/agents-md"><img src="https://agentmods.dev/badge/instructions/bubu89/full-page-pdf-snap/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/bubu89/full-page-pdf-snap/agents-md"><img src="https://agentmods.dev/badge/instructions/bubu89/full-page-pdf-snap/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,543 This file is loaded in full into every session.

When invoked 3,543 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.03543	$0.03543
Opus 5	$0.01772	$0.01772
Sonnet 5	$0.00709	$0.00709
Haiku 4.5	$0.00354	$0.00354

Measured 8d ago against content hash 748ef4878700, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

full-page-pdf-snap 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 8d 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.

AGENTS.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Anleitung für KI-Agenten, die an diesem Projekt arbeiten. Gelesen von Claude Code, Codex, Cursor, Copilot und allem, was der agents.md-Konvention folgt. Menschen lesen besser die README — hier steht, was ein Agent wissen muss, bevor er etwas ändert.

Worum es geht

provinglab.dev veröffentlicht Messungen zu Browser-Werkzeugen und Zitationsdaten und die Erweiterung Full Page PDF Snap. Der Anspruch der Seite ist eng: Jede Zahl hat eine Methode, Rohdaten und einen Kontrolllauf. Was sich nicht nachrechnen lässt, wird nicht geschrieben.

Das ist keine Stilfrage, sondern die Bedingung, unter der die Seite zitiert werden kann. Ein Beitrag, der eine Zahl ohne Beleg einführt, ist schädlicher als kein Beitrag.

Wo du stehst

Der Arbeitsstand und die Reihenfolge der offenen Punkte werden nicht mehr oeffentlich gefuehrt — sie enthielten Betriebsinterna, die niemand ausserhalb des Projekts braucht. Was ein Beitrag wissen muss, steht in dieser Datei, im README und im CHANGELOG.

Vor der ersten Änderung

python3 rechtscheck.py          # muss 0 Fehler melden
python3 tools/daten-pruefen.py  # Rohdaten gegen das Schema
node --test tests/*.mjs         # muss vollstaendig gruen sein
python3 tools/links-pruefen.py  # interne Ziele und Store-Stände

daten-pruefen.py stand hier zuerst nicht mit drin und fehlte deshalb im Vorab-Lauf — die Pipeline meldete am 3. August einen Datensatz ohne Methodenfeld, den ein lokaler Lauf in zwei Sekunden gefunden haette. Was in der Pipeline blockiert, gehoert in diese Liste.

Läuft eines davon schon vorher rot, ist das der erste Befund — melde ihn, statt darauf aufzubauen.

Die Regeln, die hier anders sind als üblich

1. Belegpflicht vor Formulierung. Jede Tatsachenbehauptung braucht Quelle und Abrufdatum, oder sie wird zur Meinung umformuliert, oder sie fällt raus. rechtscheck.py prüft das maschinell und blockiert die Auslieferung.

2. Keine Aussage über Absichten Dritter. „MDPI blockiert absichtlich" ist beweispflichtig und nicht beweisbar. „Der Server antwortete mit 403" ist eine Beobachtung. Der Prüfer kennt das Muster und schlägt an.

Read the full file on GitHub · 281 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.

8d ago First seen · 281 lines · 3,543 tokens per session scan A 748ef4878700

Subscribe to this mod's changes

full-page-pdf-snap AGENTS.md is an instructions file published in the GitHub repository Bubu89/full-page-pdf-snap (2 stars, last pushed yesterday), licensed MIT. It adds 3,543 tokens to every session, about $0.0177 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 2026-08-31.

Browser automation PDF Research firefox-extension full-page-screenshot mit-license privacy screenshot

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

full-page-pdf-snap: Instructions file for Codex