slides-grab is a tool for creating and editing presentations as HTML and CSS files, with an editor that lets coding agents work on selected parts of a slide and export decks to PDF or experimental PPTX files. It is for people generating presentations with Claude Code, Codex, and related agents. The catalogue entries provide skills, agents, and instructions for its presentation workflow.
Borrowing it
Nothing to install: this file belongs to NomaDamas/slides-grab. 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/NomaDamas/slides-grab/main/AGENTS.mdgit clone --depth 1 https://github.com/NomaDamas/slides-grabWrote 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/nomadamas/slides-grab/agents-md)<a href="https://agentmods.dev/instructions/nomadamas/slides-grab/agents-md"><img src="https://agentmods.dev/badge/instructions/nomadamas/slides-grab/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/nomadamas/slides-grab/agents-md"><img src="https://agentmods.dev/badge/instructions/nomadamas/slides-grab/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 | $0.01543 | $0.01543 |
| Opus 5.5 | $0.00617 | $0.00617 |
| Sonnet 5.5 | $0.00309 | $0.00309 |
| Haiku 4.5 | $0.00154 | $0.00154 |
Grade A, and why
slides-grab 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Contribution Workflow
mainis the only integration branch. Do not create, target, or depend on adevbranch.- Create feature or fix branches from the latest
origin/main. - Open pull requests from those branches directly against
main. - Before opening or updating a pull request, rebase or merge the latest
origin/maininto the working branch and resolve conflicts locally. - Run the relevant tests and report their results before requesting review.
- Do not merge directly to
mainunless the repository owner explicitly requests it; use a pull request and its required checks/reviews.
Project Overview
slides-grab is an agent-first PPT framework. AI agents write HTML slides directly, and a 3-stage pipeline (Planning → Design → Conversion) produces high-quality HTML/PDF output plus experimental / unstable PPTX and Figma export.
Core philosophy: HTML is the design language. Agents write HTML/CSS directly. The framework provides templates, validation, and conversion tools — not abstractions over HTML.
Key Paths
| Path | Purpose |
|---|---|
skills/slides-grab/SKILL.md |
Router skill — picks HTML or image-native pipeline |
skills/slides-grab-html/SKILL.md |
HTML-mode pipeline (semantic slides + bespoke hero imagery) |
skills/slides-grab-image/SKILL.md |
Image-native pipeline (whole-slide rasters via slides-grab image) |
skills/slides-grab-plan/SKILL.md |
Stage 1 plan skill (outline workflow) |
skills/slides-grab-design/SKILL.md |
Codex design skill (HTML slides + viewer loop) |
skills/slides-grab-export/SKILL.md |
Codex conversion skill (PDF + experimental / unstable HTML→PPTX/Figma) |
skills/slides-grab-design/references/design-gate.md |
Design gate spec — severity rubric, seven checks (incl. 6b Korean word-break and Review Litmus), dialectical dual-oracle Visual QA loop (render evidence → Pass A System Contract / Constraint Integrity + Pass B Audience Impact / Expressive Readability → synthesized verdict → fix/re-render/re-review until Proceed or Rethink), rule→side-effect→compensation matrix (12 rows), evidence-before-shipping, design-debt log, gate report/verdict (runs after validate, before export) |
runtimes/claude-code/agents/design-critic-agent.md |
Claude Code adapter that points to the canonical design gate and records slides-grab design-gate evidence |
runtimes/codex/agents/slides-grab-design-critic.md |
Codex adapter that points to the canonical design gate and records slides-grab design-gate evidence |
skills/*/references/ |
Published reference docs bundled with installable skills |
scripts/build-viewer.js |
Builds viewer.html from slide-*.html files in selected --slides-dir |
src/html2pptx.cjs |
Packaged HTML→PPTX conversion runtime |
src/pptx-raster-export.cjs |
Packaged raster PPTX export runtime behind convert.cjs |
slides/ (default) or custom --slides-dir path |
Generated HTML slide workspace |
slide-outline.md |
Presentation outline generated during Stage 1 |
package.json |
Node.js dependencies (playwright, sharp, pptxgenjs) |
convert.cjs |
Legacy experimental / unstable HTML→PPTX converter |
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 First seen · 93 lines · 1,543 tokens per session scan A 8a8e508cedb9
slides-grab AGENTS.md is an instructions file published in the GitHub repository NomaDamas/slides-grab (1,224 stars, last pushed 24d ago), licensed MIT. It adds 1,543 tokens to every session, about $0.0062 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.
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.