slideforge-mcp AGENTS.md

slideforge-mcp AGENTS.md is an instructions file for Codex, OpenCode from smartdatabrokers/slideforge-mcp. It costs 1,382 tokens per session, scanned A, original, MIT.

Instructions for using SlideForge, a service that turns structured slide requests into editable PowerPoint files. It uses predefined slide layouts and reports which content was used exactly versus completed by the model.

In plain words
What is it for?
Use them when an agent must create .pptx presentations through SlideForge, including charts, timelines, funnels, tables, and organizational diagrams.
Why use it?
They explain how to connect to the service and choose an appropriate slide layout before creating a presentation. This helps an agent produce editable slides with clear content provenance.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/smartdatabrokers/slideforge-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/smartdatabrokers/slideforge-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for slideforge-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/smartdatabrokers/slideforge-mcp/agents-md.svg)](https://agentmods.dev/instructions/smartdatabrokers/slideforge-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/smartdatabrokers/slideforge-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/smartdatabrokers/slideforge-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,382 This file is loaded in full into every session.
When invoked 1,382 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01382 $0.01382
Opus 5 $0.00691 $0.00691
Sonnet 5 $0.00276 $0.00276
Haiku 4.5 $0.00138 $0.00138

Measured 4d ago against content hash 2b9d07171d73, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

slideforge-mcp AGENTS.md 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 4d 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.

AGENTS.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SlideForge — agent instructions

SlideForge (slideforge.dev, by Smart Data Brokers GmbH) turns typed slide intents into native, fully editable PowerPoint files. It is a compiler, not a generator: a deterministic engine renders 200+ catalog patterns from structured content — no LLM in the render path — and every response carries a fidelity manifest stating what was bound verbatim vs. model-completed. Copy this file (or its rules) into a project where an agent produces .pptx deliverables.

Connect

MCP (preferred — tools + schemas are self-describing):

# Claude Code
claude mcp add --transport http slideforge https://api.slideforge.dev/mcp/
# Codex CLI / Cursor / Windsurf: streamable-http MCP server at the same URL,
# header "Authorization: Bearer sf_live_YOUR_KEY"

REST (everything also works without MCP): https://api.slideforge.dev/v1/… with the same Bearer key. Reference: https://slideforge.dev/docs/api — machine-readable rate card at GET /v1/pricing.

The workflow that works

  1. Discover the form. browse_catalog (or GET /v1/catalog) → pick a form (kpi_metrics, waterfall_bridge, gantt_plan, org_structure, funnel, data_table, …). browse_catalog type=schema form=<form> returns the JSON Schema and a copy-pasteable example intent — start from the example, swap in real content, keep the field names. Unsure which form? plan_slide with the brief is free.
  2. Dry-run first. Send the intent with dry_run: true → validation + a fidelity forecast at $0. Fix errors[] (each has a machine code + remedy), then resend without dry_run.
  3. Render. create_slide (one) or create_deck (slides[], parallel, failed slides are isolated and free). $0.05/slide, usable-or-free: a render with blocking errors never bills.
  4. Verify like an agent. The preview PNG is embedded inline in the tool result — look at it before declaring done, no fetch needed. Download the deliverable via header-auth: GET /v1/jobs/<job_id>/pptx with Authorization: Bearer sf_live_YOUR_KEY. To hand off a shareable link, POST /v1/jobs/<job_id>/download-url mints a short-TTL single-use one.
  5. Trust the manifest, not vibes. fidelity: verbatim = every number/word came from your input. ai_completed/mixed = the response names which fields a model filled. partial = some supplied content didn't make it onto the slide — the manifest names what was dropped; never deliver a partial render without telling the user what's missing. Surface fidelity to the user when the content is business data.

Read the full file on GitHub · 82 lines

Changes

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.

  1. 4d ago First seen · 82 lines · 1,382 tokens per session scan A 2b9d07171d73

Subscribe to this mod's changes

slideforge-mcp AGENTS.md is an instructions file published in the GitHub repository smartdatabrokers/slideforge-mcp (4 stars, last pushed 4d ago), licensed MIT. It adds 1,382 tokens to every session, about $0.0069 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.