What is Deckbuilder CLAUDE.md?

Project instructions for Deckbuilder, a Python library and MCP server that generates PowerPoint presentations. They define rules for AI-assisted coding, including working on branches and keeping tests and code checks intact.

Guiding work on Deckbuilder code, documentation, tests, branches, and presentation-generation features.

They give an agent clear project rules so its changes follow the repository's quality, language, testing, and workflow requirements.

How teknologika/Deckbuilder configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to teknologika/Deckbuilder. 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/teknologika/Deckbuilder/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/teknologika/Deckbuilder

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/teknologika/deckbuilder/claude-md/github.svg)](https://agentmods.dev/instructions/teknologika/deckbuilder/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/teknologika/deckbuilder/claude-md"><img src="https://agentmods.dev/badge/instructions/teknologika/deckbuilder/claude-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/teknologika/deckbuilder/claude-md"><img src="https://agentmods.dev/badge/instructions/teknologika/deckbuilder/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,922 This file is loaded in full into every session.

When invoked 4,922 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	$0.04922	$0.04922
Opus 5.5	$0.01969	$0.01969
Sonnet 5.5	$0.00984	$0.00984
Haiku 4.5	$0.00492	$0.00492

Measured 2mo ago against content hash 91a29ed0106e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Deckbuilder CLAUDE.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 2mo 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.md · 522 lines

How it starts

The opening of the file, as written. The whole thing — 522 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md or GEMINI.md

Project Overview

THE THREE LAWS OF AI CODING

LAW 1 - An AI may not reduce the quality of a codebase or, through inaction, allow a codebase's quality to be reduced.

LAW 2 - An AI must obey orders from humans, unless such orders are unclear, or conflict with the First Law.

LAW 3 - An AI must follow the prime directives, provided this does not conflict with the First or Second Law.

IMPORTANT AI PRIME DIRECTIVES

1. ALWAYS, ALWAYS WORK ON A BRANCH

2. ALWAYS ENSURE CODE IS HIGH QUALITY, AND MEETS DRY PRINCIPLES

3. MAKE CHANGES THAT ENHANCE AND IMPROVE THE CODEBASE

4. ALWAYS TRY AND ENHANCE EXISTING CODE, AND MINIMISE CYCLOMATIC COMPLEXITY, DONT CREATE ALTERNATE CODE PATHS

5. DOCUMENT CODE IN A WAY THAT MAKES IT EASY FOR AI TO NAVIGATE THE CODE BASE

6. TESTS, PRE-CHECKIN HOOKS AND CI ARE GUARDRAILS. NEVER FAKE RESULTS OR WORK AROUND THEM WITH --NO-VERIFY

7. ALWAYS USE AUSTRALIAN ENGLISH, AND THE METRIC SYSTEM

About this project

Deckbuilder is a Python library and accompanying MCP (Model Context Protocol) Server for intelligent PowerPoint presentation generation. The project has evolved beyond initial setup into a comprehensive content-first presentation intelligence system.

Testing the application

The easiset way is to use the CLI drectly then use python-pptx to verify your output e.g.

Bash(source .venv/bin/activate && deckbuilder create tests/output/imput_file.md --output tests/output/ouput_file)

🔄 Project Awareness & Context

Always read PLANNING.md at the start of a new conversation to understand the project's architecture, goals, style, and constraints.
Check TASK.md before starting a new task. If the task isn’t listed, add it with a brief description and today's date.
Use consistent naming conventions, file structure, and architecture patterns as described in PLANNING.md.

🧱 Code Structure & Modularity

Never create a file longer than 500 lines of code. If a file approaches this limit, refactor by splitting it into modules or helper files.
Organize code into clearly separated modules, grouped by feature or responsibility.
Use clear, consistent imports (prefer relative imports within packages).

Read the full file on GitHub · 522 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.

2mo ago First seen · 522 lines · 4,922 tokens per session scan A 91a29ed0106e

Subscribe to this mod's changes

Deckbuilder CLAUDE.md is an instructions file published in the GitHub repository teknologika/Deckbuilder (7 stars, last pushed 1y ago), licensed Apache-2.0. It adds 4,922 tokens to every session, about $0.0197 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.

Deckbuilder CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Deckbuilder CLAUDE.mdteknologika/Deckbuilder	Instructions file	7	1y ago	Apache-2.0	A	4,922	Claude Code
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

Deckbuilder: Instructions file for Claude Code