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 skills/kyopark2014/agent-plugins/myslidenpx skills add kyopark2014/agent-plugins --skill myslidegit clone --depth 1 https://github.com/kyopark2014/agent-pluginsWrote 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/kyopark2014/agent-plugins/myslide)<a href="https://agentmods.dev/skills/kyopark2014/agent-plugins/myslide"><img src="https://agentmods.dev/badge/skills/kyopark2014/agent-plugins/myslide.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 | $0.00117 | $0.11101 |
| Opus 5 | $0.00059 | $0.05550 |
| Sonnet 5 | $0.00023 | $0.02220 |
| Haiku 4.5 | $0.00012 | $0.01110 |
Grade A, and why
myslide 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 3d 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 — 941 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MySlide - AWS-Themed Presentation Generator
Create visually compelling presentations that follow the AWS reInvent 2023 design system. Every slide should look like it was crafted by the AWS brand team.
Quick Start
- Read references/aws-theme.md for colors, fonts, and spacing rules
- Read references/slide-patterns.md for layout templates
- Read references/pptxgenjs.md for PptxGenJS creation guide
- Read references/editing.md for editing existing PPTX files
- Read references/animations.md for animation primitives
- Use
scripts/create_aws_slide.pyto generate background/SVG assets - Official AWS service icons are in
icons/(248 icons extracted from AWS Architecture Icon Deck)
All references and scripts are self-contained within this skill directory. No external skill dependencies required.
Directory Convention — All generated assets go under artifacts/ (sibling to the skill directory), never /tmp:
ASSETS_DIR = {workspace}/artifacts/myslide-assets/ # backgrounds, SVG/PNG assets, generated images
PARTS_DIR = {workspace}/artifacts/myslide-parts/ # individual slide JS snippets
QA_DIR = {workspace}/artifacts/myslide-qa/ # QA render outputs (PDF, JPEG)
{workspace} is the project root (the directory containing application/).
Skill root (this repo)
The system prompt exposes WORKING_DIR as the application/ directory. This skill lives only here:
| Path | Meaning |
|---|---|
{WORKING_DIR}/skills/myslide |
Root of this skill (SKILL.md, scripts/, icons/, references/) |
- Use
{WORKING_DIR}/skills/myslidefor every script path,read_file, andcd. - Optional helper skills (
sd35l,nova2-omni,kiro, etc.) must be resolved under{WORKING_DIR}/skills/<name>(same pattern as myslide).
# Example: locate sd35l under application/skills
SD35L_SCRIPT=$(find "${WORKING_DIR}/skills" -path "*/sd35l/scripts/generate_image.py" 2>/dev/null | head -1)
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .DS_Store 8.0 KB
- icons/acm.svg 1.8 KB
- icons/activate.svg 1.6 KB
- icons/amplify.svg 1.9 KB
- icons/api-gateway.svg 2.2 KB
- icons/app-mesh.svg 6.4 KB
- icons/app-runner.svg 1.3 KB
- icons/appconfig.svg 3.7 KB
- icons/appflow.svg 962 B
- icons/application-composer.svg 3.4 KB
- icons/application-discovery.svg 2.6 KB
- icons/application-migration.svg 2.0 KB
- icons/appstream.svg 1.2 KB
- icons/appsync.svg 2.8 KB
- icons/artifact.svg 1.6 KB
- icons/athena.svg 3.6 KB
- icons/audit-manager.svg 1.8 KB
- icons/augmented-ai.svg 3.9 KB
- icons/aurora.svg 2.8 KB
- icons/auto-scaling.svg 1.7 KB
- icons/b2b-data-interchange.svg 2.0 KB
- icons/backup.svg 3.0 KB
- icons/batch.svg 3.2 KB
- icons/bedrock.svg 3.2 KB
- icons/billing-conductor.svg 1.4 KB
- icons/braket.svg 3.4 KB
- icons/budgets.svg 1.3 KB
- icons/cdk.svg 3.4 KB
- icons/chatbot.svg 3.1 KB
- icons/chime-sdk.svg 3.0 KB
- icons/chime.svg 2.7 KB
- icons/clean-rooms.svg 4.2 KB
- icons/cli.svg 841 B
- icons/client-vpn.svg 3.5 KB
- icons/cloud-control-api.svg 2.4 KB
- icons/cloud-directory.svg 2.3 KB
- icons/cloud-map.svg 4.3 KB
- icons/cloud-wan.svg 4.5 KB
- icons/cloud9.svg 2.7 KB
- icons/cloudformation.svg 1.9 KB
- icons/cloudfront.svg 3.5 KB
- icons/cloudhsm.svg 2.7 KB
- icons/cloudsearch.svg 2.5 KB
- icons/cloudshell.svg 2.3 KB
- icons/cloudtrail.svg 1.7 KB
- icons/cloudwatch.svg 3.0 KB
- icons/codeartifact.svg 1.6 KB
- icons/codebuild.svg 2.3 KB
- icons/codecatalyst.svg 2.6 KB
- icons/codecommit.svg 3.4 KB
- icons/codedeploy.svg 3.1 KB
- icons/codeguru.svg 2.1 KB
- icons/codepipeline.svg 1.4 KB
- icons/cognito.svg 3.4 KB
- icons/comprehend-medical.svg 2.1 KB
- icons/comprehend.svg 2.8 KB
- icons/compute-optimizer.svg 4.3 KB
- icons/config.svg 7.6 KB
- icons/connect.svg 3.7 KB
- icons/control-tower.svg 3.4 KB
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.
- 3d ago First seen · 941 lines · 117 tokens per session scan A 6f75c86a3a70
myslide is a skill published in the GitHub repository kyopark2014/agent-plugins (4 stars, last pushed 26d ago), licensed MIT. It adds 117 tokens to every session and 11,101 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
gpu-document-processing
Use when processing large PDFs, document collections, or bulk text extraction tasks that benefit from GPU-accelerated processing. Triggers when the user provides large documents or needs bulk document analysis.
convex-authz
Audit and harden Convex authorization: identity-from-arg impersonation, missing per-document ownership checks, PII-leaking public queries, and writes into containers the caller doesn't own. Deterministic scan + canonical requireIdentity/requireOwner fix + tsc verify. Use for 'secure my app' / 'audit auth' / 'who can…
iflytek-ocr-invoice
Use when user asks to recognize invoices, extract receipt data, or OCR bills and tickets. Recognize and extract structured data from invoices, receipts, and bills using iFlytek OCR API (科大讯飞票据识别). Supports VAT invoices, taxi receipts, train tickets, toll invoices, medical bills, bank receipts, and more.
ssotize
Audit and consolidate a fact that's scattered across places into one canonical source, after approval, and replace the rest with references. Use when asked to find duplication, check consistency, locate the source of truth, deduplicate, consolidate, unify, or establish SSOT across artifacts or platforms. Starts…
iflytek-pdf-image-ocr
AI-powered OCR service for images and PDF documents using iFlytek's advanced recognition APIs.
iflytek-contract-intelligence-review
Use when user asks to review contracts, detect contract risks, or perform compliance checks. 合同智能审核 - 对合同扫描件、图片合同、双语合同进行完整审核。 覆盖 OCR 识别、条款分析、风险检测、合规校对、翻译摘要全流程。 适用于法务审核、采购合同审查、供应链合规检查等场景。 关键词:合同审核、风险检测、条款分析、合规校对、contract review、risk detection。.