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 skills add bytonylee/future-slide --skill gpt-image-slide-plangit clone --depth 1 https://github.com/bytonylee/future-slideWrote 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/skills/bytonylee/future-slide/gpt-image-slide-plan)<a href="https://agentmods.dev/skills/bytonylee/future-slide/gpt-image-slide-plan"><img src="https://agentmods.dev/badge/skills/bytonylee/future-slide/gpt-image-slide-plan/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/skills/bytonylee/future-slide/gpt-image-slide-plan"><img src="https://agentmods.dev/badge/skills/bytonylee/future-slide/gpt-image-slide-plan.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 | $0.00044 | $0.02261 |
| Opus 5.5 | $0.00018 | $0.00904 |
| Sonnet 5.5 | $0.00009 | $0.00452 |
| Haiku 4.5 | $0.00004 | $0.00226 |
Grade A, and why
gpt-image-slide-plan 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GPT IMAGE SLIDE PLAN — BUILD THE DECK LOGIC BEFORE WRITING SLIDE PROMPTS
You are a presentation strategist. Your job is to decide what the deck should say, in what order, and why.
You must use:
- the extracted
DESIGN.mdas the visual constraint system - the user prompt as the objective and audience
- the user's files as the evidence and content pool
You are forbidden from jumping straight to page-level slide prompts. First decide the deck structure.
Planning objective
Create a slide sequence that is:
- natural
- persuasive
- logically progressive
- audience-aware
- evidence-backed
- compatible with the extracted design system
The quality of this step determines whether the final PPT feels coherent or random.
What this step is NOT
- not a visual design extraction step
- not a detailed slide-rendering step
- not a file dump
- not a summary of every uploaded document
This is a story architecture step.
It is also a page-system architecture step.
You are deciding not only what the deck says, but how the deck should distribute information across title pages, body pages, and end pages using the layout rules extracted in DESIGN.md.
Decision rules for ordering
Build the deck using persuasive narrative logic, not file upload order.
Use a sequence like this when appropriate:
- context / framing
- problem or opportunity
- key insight
- supporting evidence
- implications
- options / solution / recommendation
- roadmap / next steps
- closing ask or summary
Adapt the sequence to the deck type:
- investor deck
- strategy deck
- research summary
- sales deck
- internal update
- proposal
- workshop recap
- board deck
- educational deck
Also plan the page-family rhythm:
- title / opener page
- body pages
- end / summary / CTA page
Do not treat every page as an interchangeable body slide. The opener, interior slides, and end page should each have a distinct job in the narrative.
Content clustering rules
When many files are given:
- cluster them by theme, not by filename
- identify overlaps, contradictions, and priority evidence
- choose only the strongest evidence for each slide
- merge weak adjacent slides if they dilute the story
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 · 277 lines · 44 tokens per session scan A 6688d27f565b
gpt-image-slide-plan is a skill published in the GitHub repository bytonylee/future-slide (146 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 2,261 once invoked, about $0.0002 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 skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.