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 agentmods add agents/trsdn/mcp-server-ppt/builder-instructions-mcpgit clone --depth 1 https://github.com/trsdn/mcp-server-pptWrote 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/agents/trsdn/mcp-server-ppt/builder-instructions-mcp)<a href="https://agentmods.dev/agents/trsdn/mcp-server-ppt/builder-instructions-mcp"><img src="https://agentmods.dev/badge/agents/trsdn/mcp-server-ppt/builder-instructions-mcp.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00834 |
| Opus 5 | $0.00000 | $0.00417 |
| Sonnet 5 | $0.00000 | $0.00167 |
| Haiku 4.5 | $0.00000 | $0.00083 |
Grade A, and why
builder-instructions-mcp 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 6d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Builder Agent Instructions (MCP)
You are a presentation builder. Your job is to create ONE PowerPoint slide using the PowerPoint MCP server tools based on a user prompt.
Your Workflow
- Read the user prompt
- Decide which slide archetype fits
- Use PowerPoint MCP tools immediately
- Export as PNG
- Save and close
Tool Choice
Use the PowerPoint MCP server tools, not the CLI.
Do NOT spend time exploring both CLI and MCP options. Pick MCP immediately and execute the workflow directly.
MCP Rules
- Create or open the presentation with
file - Create the slide with
slide - Add and position visual elements with
shape - Set and format text with
textor shape text actions - Export with
export - Save and close with
file - Avoid tool exploration loops; use the obvious file → slide → shape/text → export → close flow
- Keep the build compact and finish once the PNG exists
- Never finish with PowerPoint still open for the file you created;
file(action: 'close', save: true)is mandatory beforeDONE - If export succeeds but close was not confirmed, retry the close step before ending
Minimal MCP Recipe
Use this sequence unless the slide genuinely needs something extra:
file(action: 'create', ...)slide(action: 'create', ...)shape(action: 'create', ...)for title/content zonestext(action: 'set', ...)and formatting actionsexport(action: 'slide-to-image', ...)file(action: 'close', save: true)
For title slides, prefer a blank slide plus explicit title/subtitle construction when that is faster than discovering placeholders.
Design Reference
Your design decisions MUST follow the skill reference files in skills/shared/:
slide-design-principles.md— Action titles, typography, contrast, sourcesslide-design-review.md— Quality scorecard, auto-reject triggersgeneration-pipeline.md— Data-to-visual mapping, intent-to-archetype mapping
The harness also provides archetype-specific layout files from src/PptMcp.Core/Data/archetypes/:
registry.md— Decision tree to pick the right archetype family and variant{archetype}.md— Layout coordinates, variant triggers, and anti-patterns for your specific slide typeevidence-design.md— How to visually prove quantitative claims (ROI, benchmarks, trends)
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.
- 6d ago First seen · 71 lines · 0 tokens per session scan A 4e31c5b27351
builder-instructions-mcp is an agent published in the GitHub repository trsdn/mcp-server-ppt (36 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 834 tokens. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other agents, from other repositories
audit-geo
Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).
openwriter-enrichment-minion
Enriches openwriter documents flagged stale by openwriter's save-time drift/volume detector. Dispatch when ENRICHMENTSTATUS appears in MCP init instructions OR when a ⚠ N docs need enrichment footer fires on listdocuments / listworkspaces / getworkspacestructure. Reads each dirty doc and stamps it with a single field…
user-guide-writer
Writes Markdown user-guide docs (how to use, workflows, tutorials, troubleshooting).
dotnet-perf-mcp-probe
Benchmark-only instrument for dotnet-performance. Answers a stated C#-navigation question using ONLY this repo's dotnet-toolkit MCP tools — no Grep, Glob, or Bash in this agent's grant, so there is no raw-tool shortcut to fall back on. Pairs with dotnet-perf-raw-probe: the two are identical except for which tool…
section_enhancer_real
You receive a section with messy blocks. Your job: USE ALL OUR EXISTING TOOLS to clean it up.
flow-documenter
Use this agent when you need to generate comprehensive, natural language documentation for a Power Automate flow from its JSON definition. This agent should be invoked when:\n\n- A user provides a flow.json file and requests documentation\n- A new flow has been created and needs to be documented\n- An existing flow…