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 4,090 This file is loaded in full into every session.

When invoked 4,090 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	$0.04090	$0.04090
Opus 5.5	$0.01636	$0.01636
Sonnet 5.5	$0.00818	$0.00818
Haiku 4.5	$0.00409	$0.00409

Measured 1mo ago against content hash 7deba7658142, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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 · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 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 jeder Auslieferung: Messung, Protokoll, Rückblick (Pflicht seit 27.09.2026)

python3 release.py bricht ab, wenn eine dieser Stufen rot ist:

Tests (node --test tests/*.mjs), darunter app-layout-naht.test.mjs.
Nahtmessung (python3 tools/naht-messung/messen.py): echte Aufnahme dreier Testseiten im headless Chromium — Fenster-Scroll mit fest werdender Leiste, innerer Container mit klebender Kopfzeile und Seitenleiste, innerer Container ohne Kopfzeile. Geprüft wird das Bild: jede Zeile genau einmal, Abstände gleich, Leiste einmal. --ohne-messung gibt es nur mit Begründung im CHANGELOG.

Warum beides: 2.42.0 hat den Maßstab geändert und wurde nur am Fenster-Scroll gemessen. Dort sind Fenster- und Containerbreite gleich; der Fehler lag im zweiten Layout und fiel erst beim Nutzer auf (Gmail, 27.09.2026). Ein Test prüft den Wortlaut des Codes, die Messung prüft das Ergebnis — nur beides zusammen fängt eine plausible, falsche Reparatur.

Read the full file on GitHub · 316 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.

1mo ago Changed · +35 lines · +547 tokens per session 7deba7658142
2mo 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 14d ago), licensed MIT. It adds 4,090 tokens to every session, about $0.0164 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 2026-08-31.

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

full-page-pdf-snap AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
full-page-pdf-snap AGENTS.mdBubu89/full-page-pdf-snap	Instructions file	2	14d ago	MIT	A	4,090	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

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