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 smartdatabrokers/slideforge-mcp --skill inspect-repairgit clone --depth 1 https://github.com/smartdatabrokers/slideforge-mcpWrote 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/smartdatabrokers/slideforge-mcp/inspect-repair)<a href="https://agentmods.dev/skills/smartdatabrokers/slideforge-mcp/inspect-repair"><img src="https://agentmods.dev/badge/skills/smartdatabrokers/slideforge-mcp/inspect-repair/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/smartdatabrokers/slideforge-mcp/inspect-repair"><img src="https://agentmods.dev/badge/skills/smartdatabrokers/slideforge-mcp/inspect-repair.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 | $0.00087 | $0.00921 |
| Opus 5 | $0.00044 | $0.00461 |
| Sonnet 5 | $0.00017 | $0.00184 |
| Haiku 4.5 | $0.00009 | $0.00092 |
Grade A, and why
inspect-repair scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST https://api.slideforge.dev/v1/inspect \ How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inspect & repair any deck (Deck Doctor)
POST /v1/inspect returns a Deck Quality Report for any .pptx — decks SlideForge never
rendered included. Free, deterministic, no LLM: the file is analyzed with real font metrics
and geometry, never sent to a model. Repair is $0.02 per repaired slide, and its dry_run
returns the exact fix plan (and therefore the exact price) free.
Inspect
curl -X POST https://api.slideforge.dev/v1/inspect \
-H "Authorization: Bearer sf_live_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"pptx_base64": "'"$(base64 -w0 deck.pptx)"'"}'
Sources (exactly one): pptx_base64 (≤25 MB), pptx_url (https), or job_id (a SlideForge
render). First 50 slides; 30 requests/hour.
What it finds — each with a machine code, severity, message, remedy, and the offending
shape_id: text overflow / clipping (measured with real font metrics, autofit-aware), content
hidden behind opaque shapes (z-order), off-canvas leftovers (parked notes leak content!),
WCAG contrast, sub-9pt fonts, image-only slides, empty slides, hidden slides (marked; they
never fail the deck), density.
Read it honestly: status is clean | review | failed. summary.font_size_coverage /
contrast_coverage state how much of the deck the checks could actually resolve — inherited
theme values it can't resolve are skipped, never guessed. Report findings to the user by
slide number with the remedy; don't paraphrase severities up or down.
Repair (deterministic, never your words)
# free exact quote first
curl -X POST https://api.slideforge.dev/v1/repair -H "Authorization: Bearer sf_live_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"pptx_url": "https://…/deck.pptx", "dry_run": true}'
# then apply
curl -X POST https://api.slideforge.dev/v1/repair -H "Authorization: Bearer sf_live_YOUR_KEY" \
-H "Content-Type: application/json" -d '{"pptx_url": "https://…/deck.pptx"}'
Actions (subset via actions[], default all): shrink_to_fit (measured, floor 9pt),
raise_min_font (only when it still fits), remove_off_canvas (fully-invisible junk only),
fix_contrast (WCAG AA, hue-preserving). No characters are ever altered — the response
carries a computed visible_text_untouched proof, a before/after report diff, and
flagged_not_fixed[] for anything ambiguous (with remedies). A run that fixes nothing bills
nothing; the repaired deck persists as a job — download it with your API key via GET /v1/jobs/{id}/pptx.
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.
- 10d ago First seen · 67 lines · 87 tokens per session scan A bdbea6e921cc
inspect-repair is a skill published in the GitHub repository smartdatabrokers/slideforge-mcp (4 stars, last pushed 10d ago), licensed MIT. It adds 87 tokens to every session and 921 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
n8n-binary-and-data
Handle files and binary data in n8n correctly. Use when working with files, images, PDFs, attachments, uploads or downloads, base64, vision/multimodal input, or when an AI agent needs a file as tool input or output — and whenever the user mentions $binary, binaryPropertyName, "read the PDF", "attach the file", "send…
markdown-to-pdf
Convert a markdown file to PDF using mistune + reportlab. Use when the user wants to convert a .md file to PDF, or when another skill needs to produce a PDF from markdown output.
document-query
Use when reading, extracting, summarizing, comparing, or answering questions over local or remote documents, code files, PDFs, Office files, HTML/text files, large text-heavy files, and fallback OCR for document images or scans when vision tools are unavailable or insufficient.
pdf-guide
Searches and reads Riksarkivet's archival PDF guides (medieval Sweden, governance 1520-1920, Sami history). Use when user asks about Swedish history, archives, medieval charters, governance, Sami, or wants to open/search PDF guides. Provides section-level references with page numbers for citation.
orchardcore-ai-documents-extractors
Skill for adding PDF and OpenXml text extraction to CrestApps Orchard Core AI Documents. Covers PDF, DOCX, XLSX, PPTX, processor registration, supported file types, upload processing, and extraction troubleshooting. Use this skill when requests mention AI Documents extractors, PDF document processing, OpenXml document…