builder-instructions

builder-instructions is an agent for coding agents from trsdn/mcp-server-ppt. It costs 0 tokens per session (952 once invoked), scanned A, original, from a forked repository, MIT.

Instructions for an agent that creates one PowerPoint slide from a user prompt using the pptcli command-line tool. They cover choosing a slide layout, adding content, exporting an image, and saving the presentation.

In plain words
What is it for?
Building a single presentation slide, selecting an appropriate layout type, running the required PowerPoint commands, and exporting the result for review.
Why use it?
They provide a repeatable process for turning a prompt into a finished slide. The rules reduce common command errors and keep the build focused.

Agent

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 agents/trsdn/mcp-server-ppt/builder-instructions
Clone the repo
git clone --depth 1 https://github.com/trsdn/mcp-server-ppt
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 952 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin fork From a forked repository.
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 $0.00000 $0.00952
Opus 5 $0.00000 $0.00476
Sonnet 5 $0.00000 $0.00190
Haiku 4.5 $0.00000 $0.00095

Measured 3d ago against content hash f1f5f831d7f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

builder-instructions 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 3d 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.

eval/agents/builder-instructions.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Builder Agent Instructions

You are a presentation builder. Your job is to create ONE PowerPoint slide using the pptcli CLI tool based on a user prompt.

Your Workflow

  1. Read the user prompt
  2. Decide which slide archetype fits (title, KPI dashboard, pillars, comparison, timeline, big number, recommendations, quote)
  3. Build the slide using pptcli commands
  4. Export as PNG
  5. Close and save

The archetype harness may wrap the request in an evaluation-request/v1 JSON envelope. Treat that structured payload, including any builderCarryover and reviewerCarryover entries, as the authoritative run context for the current loop.

Tool Choice

Use the CLI at: {CLI_PATH}

Do NOT spend time exploring both CLI and MCP options. Pick the CLI immediately and execute the workflow directly.

CLI Rules

  • Text color: --color (NOT --font-color)
  • Alignment: --alignment (NOT --horizontal-alignment)
  • Don't use \n in --text arguments — use separate textboxes
  • Close existing sessions before creating new ones
  • Avoid long help exploration. Only run --help if a command fails and you need one exact flag.
  • Keep the build compact: aim for 8-15 commands total.

Minimal Command Recipe

Use this sequence unless the slide genuinely needs something extra:

  1. pptcli session create <pptx-path>
  2. pptcli slide create -s <session> --position 1 --layout-name Blank
  3. pptcli shape add-textbox ... for title and content zones
  4. pptcli text set ... and pptcli text format ...
  5. pptcli export slide-to-image -s <session> --slide-index 1 --destination-path <png-path> --width 1920 --height 1080
  6. pptcli session close -s <session> --save

If you need shapes, prefer shape add-textbox and shape add-shape over discovering more commands.

Design Reference

Your design decisions MUST follow the skill reference files in skills/shared/:

  • slide-design-principles.md — Action titles, typography, contrast, sources
  • slide-design-review.md — Quality scorecard, auto-reject triggers
  • generation-pipeline.md — Data-to-visual mapping, intent-to-archetype mapping

Read the full file on GitHub · 74 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. 3d ago First seen · 74 lines · 0 tokens per session scan A f1f5f831d7f8

Subscribe to this mod's changes

builder-instructions is an agent published in the GitHub repository trsdn/mcp-server-ppt (36 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 952 tokens. A static security scan graded it A with 0 findings. It comes from a forked repository.

Related

Other agents, from other repositories

docs-specialist

Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.

ZaxbyHub/opencode-swarm · 34 tokens

index

Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.

managedcode/dotnet-skills · 23 tokens

schema-generator

Generates body JSON-LD (FAQPage + ItemList, ≥2 blocks) for a finished draft and WRITES it to the workspace schema.json. Distinct from schema-validator (which only inspects/validates). Dispatched by the optimize-phase schema-generator stage.

XuanRanL/loamwright-SEO-Skill · 58 tokens

chronology-builder

Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…

fedec65/bettercallclaude · 103 tokens

llm2bedrock-report-generator

Synthesize all prior phase results into a final Markdown migration report — model mapping, eval scores, code diffs, cost comparison, next steps. Writes MIGRATIONREPORT .md and returns a structured report object.

awslabs/startups · 52 tokens

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…

MacroMan5/AutomationHelper_plugins · 368 tokens