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 davistroy/claude-marketplace --skill sg-draftgit clone --depth 1 https://github.com/davistroy/claude-marketplaceWrote 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/davistroy/claude-marketplace/sg-draft)<a href="https://agentmods.dev/skills/davistroy/claude-marketplace/sg-draft"><img src="https://agentmods.dev/badge/skills/davistroy/claude-marketplace/sg-draft/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/davistroy/claude-marketplace/sg-draft"><img src="https://agentmods.dev/badge/skills/davistroy/claude-marketplace/sg-draft.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 | $0.00050 | $0.00687 |
| Opus 5.5 | $0.00020 | $0.00275 |
| Sonnet 5.5 | $0.00010 | $0.00137 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
sg-draft 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slide Generator: Draft Step
Draft full slide content from an outline. Uses structured single-call generation (one API call per slide) with batching (groups of 4) for efficiency. Produces a complete presentation markdown with titles, bullets, speaker notes, and graphics descriptions.
Pre-loaded Context
Working directory:
!pwd
Available outline files:
!ls -la outline*.json 2>/dev/null || echo "No outline files found"
Prerequisites
- Preflight:
sg --versionmust succeed before proceeding — ifsgis missing, stop and tell the user this requires the privatedavistroy/slide-generatorengine (owner-only; see ADR-0008) slide-generatorpackage installedANTHROPIC_API_KEYset in environment- An
outline.jsonfile from the outline step
Input Validation
Required:
<outline.json>- Path to outline file
Optional:
--output <path>- Output file path (default:presentation.md)--tone <tone>- Content tone: professional, casual, academic, technical (default: professional)--audience <audience>- Target audience description
Instructions
- Verify input: Confirm the outline JSON file exists and is valid
- Run draft generation:
sg draft outline.json --output presentation.md - Verify output: Confirm
presentation.mdwas created with full slide content - Report results: Show slide count, total word count, and a sample slide
How It Works
The draft step uses:
- Structured single-call: Each slide generated in one API call (not 4 separate calls)
- Batch generation: Slides grouped in batches of 4 for efficiency
- Inter-slide context: Rolling 5-slide context window for coherence
- Temperature 0.5: Balanced creativity for content generation
- Research cache: Reuses research findings for factual accuracy
Error Handling
| Error | Cause | Fix |
|---|---|---|
File not found |
Wrong path to outline.json | Check file path |
Rate limit |
Too many API calls in batch | Wait and retry (built-in backoff handles this) |
Content too short |
Outline lacks detail | Re-run outline with more target slides |
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 · 80 lines · 50 tokens per session scan A 44ddecce8e4a
sg-draft is a skill published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 19d ago), licensed MIT. It adds 50 tokens to every session and 687 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 2026-09-04.
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…
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…