Borrowing it
Nothing to install: this file belongs to smartdatabrokers/slideforge-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/smartdatabrokers/slideforge-mcp/main/AGENTS.mdgit 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/instructions/smartdatabrokers/slideforge-mcp/agents-md)<a href="https://agentmods.dev/instructions/smartdatabrokers/slideforge-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/smartdatabrokers/slideforge-mcp/agents-md/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/instructions/smartdatabrokers/slideforge-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/smartdatabrokers/slideforge-mcp/agents-md.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 | $0.01382 | $0.01382 |
| Opus 5.5 | $0.00553 | $0.00553 |
| Sonnet 5.5 | $0.00276 | $0.00276 |
| Haiku 4.5 | $0.00138 | $0.00138 |
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 2mo 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 — 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
- Discover the form.
browse_catalog(orGET /v1/catalog) → pick aform(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_slidewith the brief is free. - Dry-run first. Send the intent with
dry_run: true→ validation + a fidelity forecast at $0. Fixerrors[](each has a machine code + remedy), then resend withoutdry_run. - Render.
create_slide(one) orcreate_deck(slides[], parallel, failed slides are isolated and free). $0.05/slide, usable-or-free: a render with blocking errors never bills. - 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>/pptxwithAuthorization: Bearer sf_live_YOUR_KEY. To hand off a shareable link,POST /v1/jobs/<job_id>/download-urlmints a short-TTL single-use one. - 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 apartialrender without telling the user what's missing. Surface fidelity to the user when the content is business data.
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.
- 2mo ago First seen · 82 lines · 1,382 tokens per session scan A 2b9d07171d73
slideforge-mcp AGENTS.md is an instructions file published in the GitHub repository smartdatabrokers/slideforge-mcp (4 stars, last pushed 2mo ago), licensed MIT. It adds 1,382 tokens to every session, about $0.0055 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.