ppt-master: Instructions file for Codex

AGENTS.md

ppt-master AGENTS.md is an instructions file for Codex, OpenCode from hugohe3/ppt-master. It costs 2,606 tokens per session, scanned A, original, MIT.

A set of contributor instructions for ppt-master, a project that creates editable PowerPoint files from source material. It defines the required workflow, repository paths, command rules, and compatibility limits for presentation-generation tasks.

In plain words
What is it for?
Use it before creating a presentation or changing the project, especially when working with PDFs, DOCX files, web pages, Markdown, or the project's Python processing scripts.
Why use it?
It gives agents the project-specific rules needed to modify the repository or generate presentations safely. This helps avoid using the wrong skill, losing machine-readable output, or relying on incorrect paths.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is hugohe3/ppt-master's own configuration. It tells Codex and OpenCode how to work on ppt-master itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ppt-master configures →

About the project

PPT Master is an AI tool that turns documents or topics into editable PowerPoint presentations with native slides, charts, tables, animations, narration, and user-provided templates. It is for people who need to create and refine presentation decks, and the catalogue add-ons extend its workflow.

hugohe3/ppt-master · 73,952 stars · on GitHub · hugohe3.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to hugohe3/ppt-master. 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/hugohe3/ppt-master/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/hugohe3/ppt-master

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.

agentmods badge for ppt-master AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hugohe3/ppt-master/agents-md/github.svg)](https://agentmods.dev/instructions/hugohe3/ppt-master/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/hugohe3/ppt-master/agents-md"><img src="https://agentmods.dev/badge/instructions/hugohe3/ppt-master/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.

agentmods 80×15 button for ppt-master AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hugohe3/ppt-master/agents-md"><img src="https://agentmods.dev/badge/instructions/hugohe3/ppt-master/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,606 This file is loaded in full into every session.
When invoked 2,606 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02606 $0.02606
Opus 5.5 $0.01042 $0.01042
Sonnet 5.5 $0.00521 $0.00521
Haiku 4.5 $0.00261 $0.00261

Measured 2d ago against content hash 50d76d4aadec, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ppt-master 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 2d 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 · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file is the project entry point for general AI agents.

You MUST read skills/ppt-master/SKILL.md before any PPT generation task or repo modification. It owns global execution discipline and points to the route selector; after routing, the selected runtime authority owns its steps, gates, and commands.

Repository execution anchor: resolve the absolute repository root from this file's supplied path and retain the absolute skills/ppt-master root before the first command. Paths in this file are repository-relative notation only; invoke them through those absolute roots, retain the absolute project path returned by initialization, and never issue cd skills/ppt-master or cd projects/.... When parsing machine-readable stdout, keep stderr separate and never place 2>&1 upstream of a JSON or XML parser. Invoke each such command once per concrete argument set; never encode its executable or flag list in scalar shell strings, batch it through a shell loop, or add a downstream parser when the command provides a compact view.

Project Overview

PPT Master turns source material into natively editable DrawingML PPTX. Generate has two mutually exclusive runtimes: Default Strategist → Image_Generator → Executor, and self-contained Quick without separate strategy/confirmation. Beautify selects from explicit Quick intent; Image to PPTX always uses Quick.

Route selection authority: skills/ppt-master/workflows/routing.md owns the three top-level artifact routes: Generate PPTX, Create Template, and Edit Native PPTX. Child workflows, profiles, stages, and governance documents refine one selected route; they are not competing top-level routes.

  • Topic-only or fact-insufficient inputs run topic-research inside the selected Generate profile's source intake; its facts URLs are not auto-expanded. After normal image search fails, one relevant webpage may be fetched as a source package and only reviewed selections enter the runtime image pool.
  • Default Generate prepares template candidates internally in Step 3, then confirms the communication contract and free-design/template choice together in Stage 1. A template never rewrites the confirmed communication contract; selected roots are installed before template-aware Stage 2. Quick skips this interaction.
  • Raw PPTX template plus new material/topic routes to edit-native-pptx: a pptx_to_svg.py --roundtrip workspace where unchanged pages are referenced byte-for-byte and only planned pages are edited; it never enters Generate.
  • Raw PPTX cannot be consumed as a Generate template workspace; run create-template first and return with the generated workspace root as a Stage-1 candidate. Never add Master/Layout structure directly to an existing PPTX/SVG; generate new structured SVG pages from the workspace.
  • Explicit quick/fast or skip-strategy generation uses quick-generate: prepare sources/resources as needed, decide without interaction, omit Strategist/confirmation/spec/lock, hand-author svg_output/, pass its lockless final checker, and export.
  • Recorded, self-running, or video-directed Generate work conditionally loads video-design inside the selected Default or explicit Quick runtime before page planning. It changes scene, script, and motion design—not the runtime/profile or artifact route.
  • PPTX beautify is a strict 1:1 Generate profile, not a separate route. Explicit Quick intent uses the Quick runtime; otherwise it uses Default. Any split/merge/drop/reorder disables Beautify and returns to ordinary Generate in the selected runtime.
  • Page-image reconstruction uses the Quick-only image-to-pptx profile on a vision host; generated layers use host reference-image editing or image_gen.py --reference-image. One normalized frame becomes one slide: native text from reviewed OCR over a text-removed base, plus identity-faithful graphics and registered scene layers (checked, padded-bbox-disjoint objects sharing a plate) for objects that must stay independent. Never use a full-slide screenshot skin.
  • Finished PPTX notes / narration / timings / transitions with visible slides untouched also use edit-native-pptx; export must report rebuilt=0.
  • visual-review, customize-animations, and generate-audio are supporting stages; their trigger rules remain explicit/conditional.

Read the full file on GitHub · 90 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.

  1. 2d ago Changed · +10 tokens per session 50d76d4aadec
  2. 1mo ago Changed · +2 tokens per session f48f553993d1
  3. 2mo ago Changed · +34 tokens per session a8cf2ecef1d0
  4. 2mo ago Changed · +48 tokens per session 85430f3bf4af
  5. 2mo ago First seen · 90 lines · 2,512 tokens per session scan A 599af1f43891

Subscribe to this mod's changes

ppt-master AGENTS.md is an instructions file published in the GitHub repository hugohe3/ppt-master (73,952 stars, last pushed yesterday), licensed MIT. It adds 2,606 tokens to every session, about $0.0104 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 2026-08-30.

Related

ppt-master AGENTS.md compared with instructions from other repositories

ppt-master AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ppt-master AGENTS.mdhugohe3/ppt-masterInstructions file74kyesterdayMITA2,606Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode