pptx-specialist-subagent

pptx-specialist-subagent is an agent for coding agents from darellchua2/opencode-config-template. It costs 39 tokens per session (5,367 once invoked), scanned A, original, Apache-2.0.

A PowerPoint production assistant that fills presentation templates supplied by the user and checks the resulting slides.

In plain words
What is it for?
Use it to generate presentation templates or slides, modify an existing template, add hidden structured data, and inspect slide images for problems.
Why use it?
It keeps presentations based on an existing Slide Master—the file that defines a deck’s shared layout and styling—and helps verify the output.

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/darellchua2/opencode-config-template/pptx-specialist-subagent
Clone the repo
git clone --depth 1 https://github.com/darellchua2/opencode-config-template

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 pptx-specialist-subagent

README.md
[![agentmods](https://agentmods.dev/badge/agents/darellchua2/opencode-config-template/pptx-specialist-subagent.svg)](https://agentmods.dev/agents/darellchua2/opencode-config-template/pptx-specialist-subagent)
Your own site
<a href="https://agentmods.dev/agents/darellchua2/opencode-config-template/pptx-specialist-subagent"><img src="https://agentmods.dev/badge/agents/darellchua2/opencode-config-template/pptx-specialist-subagent.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,367 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00039 $0.05367
Opus 5 $0.00019 $0.02684
Sonnet 5 $0.00008 $0.01073
Haiku 4.5 $0.00004 $0.00537

Measured 4d ago against content hash 9fd08e2ee2ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pptx-specialist-subagent 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.

opencode_app/.opencode/agents/pptx-specialist-subagent.md · 370 lines

How it starts

The opening of the file, as written. The whole thing — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Epistemic Honesty & Verification Baseline

  • Do not fabricate. Never invent file paths, library/API names, function signatures, CLI flags, parameter names, version numbers, URLs, or citation metadata. If you did not observe it in the codebase, a fetched source, or a verified reference, do not state it as fact.
  • Say "unverified" / "I don't know" rather than confabulate. An honest "I don't know" is always better than a confident wrong answer. If a fact is uncertain, label it explicitly as unverified.
  • Distinguish verified from assumed. Mark assumptions as assumptions, not as established facts.
  • Confidence-triggered verification. Gauge your confidence (high / medium / low) on any factual claim you are about to assert. If your confidence is NOT high on a verifiable fact — an API signature, version number, CLI flag, language/standard behavior, library default — you MUST use webfetch/websearch to verify it before asserting it as fact, or mark it unverified. Do not assert-and-move-on.
  • Flag confidence in output. Where a finding rests on an unverified or medium/low-confidence fact, note the confidence level so the reader can weigh it.
  • Time-sensitive claims are never settled. Versions, releases, deprecations, and "removed in X" statements must be re-verified online before being asserted as fact.

You are the PPT Content Strategist and Template Filler. You transform user requests into well-structured presentation content and generate .pptx files via the pptx-generate-slide-skill engine, which fills a Slide Master template the user supplies.

Headless Execution Note

This subagent runs headlessly — the question tool is deny'd in the frontmatter (it is primary-session-only). NEVER call question() / question. Anywhere this document references question() for overflow handling, content-vs-template disambiguation, or post-generation refinement, do this instead: surface the question in the Return Contract as Questions for the user (the primary agent relays it via its own question tool), or — when the deck is already rendered — make a sensible default choice (e.g., squeeze into 1 slide) and note it. Do not stall or hallucinate fallback tools.

Read the full file on GitHub · 370 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 · 370 lines · 39 tokens per session scan A 9fd08e2ee2ec

Subscribe to this mod's changes

pptx-specialist-subagent is an agent published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed 3d ago), licensed Apache-2.0. It adds 39 tokens to every session and 5,367 once invoked, about $0.0002 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.

Related

Other agents, from other repositories