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 instructions/photonn/dial-pptx-mcp/claude-mdgit clone --depth 1 https://github.com/photonn/dial-pptx-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/photonn/dial-pptx-mcp/claude-md)<a href="https://agentmods.dev/instructions/photonn/dial-pptx-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/photonn/dial-pptx-mcp/claude-md.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 | $0.05618 | $0.05618 |
| Opus 5 | $0.02809 | $0.02809 |
| Sonnet 5 | $0.01124 | $0.01124 |
| Haiku 4.5 | $0.00562 | $0.00562 |
Grade A, and why
dial-pptx-mcp CLAUDE.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 yesterday.
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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
A remote, multi-tenant PowerPoint-generation MCP server for EPAM AI DIAL. It is a fork of
GongRzhe/Office-PowerPoint-MCP-Server (MIT) with full upstream
history preserved. The ~30 upstream content/formatting tools are essentially unchanged; this project adds the
remote-transport, multi-tenant state, DIAL file I/O, and visual-QA layers. docs/UPSTREAM_README.md is the upstream tool
reference; README.md documents this project's configuration and DIAL integration.
Upstream-inherited code (tools/, utils/, most of ppt_mcp_server.py) follows a different style and quality bar than the
DIAL layers (state.py, dial_client.py, visual_qa.py, visual_fix.py). Match the file you are editing.
Commands
uv venv --python 3.12 .venv && uv pip install -r requirements.txt
.venv/bin/python -m unittest discover -s tests -v # all tests
.venv/bin/python -m unittest tests.test_visual_gate -v # one module
.venv/bin/python -m unittest tests.test_state.TestPresentationStore.test_ttl_expiry -v # one test
.venv/bin/python spike/fidelity_spike.py <template.pptx> [out.pptx] # template-fidelity check
.venv/bin/python spike/http_client_check.py # transport smoke test
.venv/bin/python ppt_mcp_server.py # stdio (local MCP clients)
.venv/bin/python ppt_mcp_server.py -t http --host 0.0.0.0 -p 8000 # /mcp endpoint
docker build -t dial-pptx-mcp . && docker run -p 8000:8000 dial-pptx-mcp
There is no linter or formatter configured. CI (.github/workflows/ci.yml) runs the unittest suite on Python 3.10, 3.12 and 3.14 (3.14 is what the Docker image ships),
the fidelity spike against the bundled demo deck, and a Docker build. Tests requiring LibreOffice self-skip when soffice
is absent, so a green local run may still fail in CI — install LibreOffice or check the CI result.
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.
- yesterday Changed · +2 lines · +578 tokens per session 852a438e899d
- 5d ago First seen · 229 lines · 5,040 tokens per session scan A 9b16d9bd628c
dial-pptx-mcp CLAUDE.md is an instructions file published in the GitHub repository photonn/dial-pptx-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 5,618 tokens to every session, about $0.0281 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.
Other instructions, from other repositories
ppt-master AGENTS.md
AGENTS.md instructions for hugohe3/ppt-master, covering agents.md, project overview, execution requirements, required conventions and compatibility boundary.
ppt-master CLAUDE.md
Claude Code instructions for hugohe3/ppt-master: Claude Code entry point. To avoid maintaining two copies, all project instructions live in a single source of truth — AGENTS.md — imported below (Claude Code inlines @-referenced files into context). Always edit AGENTS.md; never duplicate its content here.
ai-dial-core CLAUDE.md
Claude Code instructions for epam/ai-dial-core, covering claude.md, build & run, set credentials via environment variables, build (skip tests) and run all tests.
codex-ppt-skill AGENTS.md
Instructions for ningzimu/codex-ppt-skill, covering agents.md, contribution flow, changelog, release process and verification.
ai-dial-chat AGENTS.md
AGENTS.md instructions for epam/ai-dial-chat, covering general guidelines for working with nx, scaffolding & generators, when to use nxdocs, architecture context and library isolation.
ai-dial-chat lib-styling.instructions.md
Instructions for epam/ai-dial-chat, a project described as: A default UI for AI DIAL.