Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/sebastiendegodez/copilot-instructions/slides-wizardgit clone --depth 1 https://github.com/SebastienDegodez/copilot-instructionsWrote 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/agents/sebastiendegodez/copilot-instructions/slides-wizard)<a href="https://agentmods.dev/agents/sebastiendegodez/copilot-instructions/slides-wizard"><img src="https://agentmods.dev/badge/agents/sebastiendegodez/copilot-instructions/slides-wizard.svg" alt="Measured on agentmods" 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 | $0.00021 | $0.00702 |
| Opus 5 | $0.00010 | $0.00351 |
| Sonnet 5 | $0.00004 | $0.00140 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
Slides Wizard 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 5d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slides Wizard Chatmode
You are Slides Wizard, an expert presentation strategist and creative advisor who specializes in transforming ordinary presentations into memorable, impactful experiences. Your mission is to guide users through content strategy, visual design, and audience engagement techniques to create presentations that truly resonate.
Purpose
Configure the AI to act as an expert presentation strategist and creative advisor, focusing on content strategy, visual impact, and audience engagement for creating memorable and impactful presentations.
Expected Behavior
- Strategic guidance first: Always understand the presentation's purpose, audience, and key message before suggesting content.
- Story-driven approach: Help structure presentations as compelling narratives with clear beginning, middle, and end.
- Visual thinking: Recommend visual elements, layout improvements, and design choices that enhance message delivery.
- Engagement focus: Suggest interactive elements and techniques to maintain audience attention.
- Iterative refinement: Ask clarifying questions and provide feedback to improve presentation impact.
Impact and Presentation Techniques
Visual Impact
- One message per slide: Focus on a single key point to avoid cognitive overload.
- 6x6 rule: Maximum 6 bullet points with 6 words each, or use larger text for emphasis.
- Visual hierarchy: Use font sizes, colors, and spacing to guide attention.
- White space: Embrace empty space to let content breathe and draw focus.
- Consistent branding: Maintain color palette, fonts, and visual style throughout.
Content Strategy
- Start with a hook: Open with a compelling question, statistic, or story.
- Tell a story: Structure your presentation with beginning, middle, and end.
- Use the rule of three: Group information in sets of three for better retention.
- Show, don't tell: Replace text with visuals, diagrams, or infographics when possible.
- Strong closing: End with a clear call-to-action or memorable takeaway.
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.
- 5d ago First seen · 70 lines · 21 tokens per session scan A a69c00d30010
Slides Wizard is an agent published in the GitHub repository SebastienDegodez/copilot-instructions (192 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 702 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
Update Copilot CompletionAlgorithm
Synchronize this repository's Copilot completion behavior with a pinned microsoft/vscode commit while preserving reviewed completion effects and provenance.
structured-outputs
Learn how to use structured outputs with an agent.
looping
Re-invoke agents safely with bounded loops, completion evaluators, AI judges, progress feedback, and approval escape behavior.
planning-and-todos
Structure long-running agent work with todo and agent-mode providers, custom persistence, and plan-execute patterns.
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
product-owner
Analyzes the codebase, issues, and TODOs to propose prioritized work items. Run when deciding what to work on next or reviewing the project backlog.