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.
git clone --depth 1 https://github.com/sbroenne/mcp-server-powerpointWrote 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/rules/sbroenne/mcp-server-powerpoint/cursorrules)<a href="https://agentmods.dev/rules/sbroenne/mcp-server-powerpoint/cursorrules"><img src="https://agentmods.dev/badge/rules/sbroenne/mcp-server-powerpoint/cursorrules/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/rules/sbroenne/mcp-server-powerpoint/cursorrules"><img src="https://agentmods.dev/badge/rules/sbroenne/mcp-server-powerpoint/cursorrules.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 | $0.00731 | $0.00731 |
| Opus 5.5 | $0.00292 | $0.00292 |
| Sonnet 5.5 | $0.00146 | $0.00146 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
cursorrules 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 8d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
.cursorrules — PowerPoint MCP Server Skills
You are assisting with mcp-server-powerpoint, a Windows-only MCP server that drives a live
PowerPoint desktop instance via COM. When using the PowerPoint MCP tools (not when editing this
repo's C# source), follow these rules:
Session Rules
- Call
presentation(action: "open", filePath: ...)before any editing tool; use the returnedpresentation_session_idfor every subsequent call. presentation(action: "create", ...)creates a file and leaves its session open.- Close with
save: trueto persist changes. presentation(action: "close", ...)returns immediately; it does not wait for the PowerPoint process to fully exit. Do not poll for process exit.
Tool Shapes
- Session lifecycle, templates, and document properties use the
presentationaction-dispatch tool withpresentation_session_idfor its session identifier and camelCase for its other arguments. - Domain tools (
slide,shape,textframe,table,chart,image,notes,layout,master,animation,export) are action-dispatch: call astool(action: "kebab-action", presentation_session_id: ..., snake_case_param: ...).
Indexing Rules
slide_index,shape_index, and tablerow/columnare all 1-based. The first slide isslide_index=1, not0.
Verification Rules
- After adding or repositioning any shape, table, chart, or image, call
export(action: "export-slide-to-image", presentation_session_id: ..., slide_index: ..., output_path: ...)and inspect the result before moving on or saving. Do not treatsuccess: truefrom a mutation call as proof the slide looks right. - For a finished multi-slide deck, call
export(action: "export-all-slides-to-images", ...)once as a final pass.
Behavioral Rules
- Never ask the user clarifying questions you can answer yourself — use
list_sessions,slide(action: "get-count", ...),shape(action: "get-count", ...),textframe(action: "get-text", ...),layout(action: "get-layout", ...),master(action: "get-title-font"/ "get-body-font"/"get-background-color", ...),table(action: "get-cell-text", ...),chart(action: "get-chart-data", ...),notes(action: "get-notes-text", ...)to discover current state. - Always finish a task with a plain-text summary (file path, slide count, what changed). Never end a turn with only a tool call.
- Prefer targeted updates (
table(action: "set-cell-text", ...),shape(action: "set-position", ...),shape(action: "set-size", ...)) over delete-and-recreate for small changes. chart(action: "add-chart", ...)supports exactly one data series per call — there is no multi-series parameter.- There is no slide-reorder tool — plan the final slide order before calling
slide(action: "add-blank", ...).
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.
- 8d ago Changed · -2 lines · -54 tokens per session dcd8007f11fe
- 1mo ago First seen · 61 lines · 785 tokens per session scan A ff490ae5071a
cursorrules is a cursor rule published in the GitHub repository sbroenne/mcp-server-powerpoint (33 stars, last pushed yesterday), licensed MIT. It adds 731 tokens to every session, about $0.0029 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 2026-08-30.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).
control-plane-descriptors
Control plane descriptor and instance implementation patterns.