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/trsdn/mcp-server-ppt/critical-rulesgit 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/instructions/trsdn/mcp-server-ppt/critical-rules)<a href="https://agentmods.dev/instructions/trsdn/mcp-server-ppt/critical-rules"><img src="https://agentmods.dev/badge/instructions/trsdn/mcp-server-ppt/critical-rules.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 | $0.12739 | $0.12739 |
| Opus 5 | $0.06370 | $0.06370 |
| Sonnet 5 | $0.02548 | $0.02548 |
| Haiku 4.5 | $0.01274 | $0.01274 |
Grade A, and why
mcp-server-ppt critical-rules.instructions.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 today.
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 — 1,279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRITICAL RULES - MUST FOLLOW
⚠️ NON-NEGOTIABLE rules for all PptMcp development
Rule 0: NEVER Commit Without Running Tests (CRITICAL)
NEVER commit, push, or create PRs without first running tests for the code you changed.
Why Critical: Prevents breaking changes from reaching main, wastes team time debugging failures, violates CI/CD principles.
Enforcement:
- ALWAYS run relevant tests BEFORE committing
- Use
--filter "Feature=<feature-name>&RunType!=OnDemand"for feature-specific tests - Build must pass (0 warnings, 0 errors)
- Pre-commit hooks must pass (COM leaks, success flag, coverage)
- Document test results in commit message
Process:
- Make code changes
- Build:
dotnet build(must succeed with 0 warnings) - Run tests:
dotnet test --filter "Feature=<feature>&RunType!=OnDemand" - Verify all tests pass
- Run pre-commit checks
- THEN commit
Rule 26: No Confidential Information in Commits/PRs (CRITICAL)
NEVER include confidential project names, file names, customer names, or internal references in commit messages, PR descriptions, or issue descriptions.
Why Critical: Git history and GitHub issues/PRs are public or semi-public. Confidential information in commits persists forever in git history and is difficult to remove.
Forbidden in commits/PRs/issues:
- Customer project names (e.g., "CP Toolkit", "Contoso Deal")
- Specific file paths from customer projects (e.g., "MSX Plan.pptx", "Milestone_Export")
- Internal tool names that reveal customer context
- Any information that could identify a specific customer engagement
Allowed:
- Generic descriptions ("a slide shape", "a PowerPoint presentation")
- Technical details that don't identify the source ("a column with a hyphen in the name")
- Error messages and stack traces (sanitized of paths/names)
Example:
# ❌ WRONG: Reveals confidential project
Discovered while debugging Milestone_Export query in CP Toolkit's MSX Plan.pptx
# ✅ CORRECT: Generic description
Discovered while debugging a slide shape that referenced an embedded object
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.
- today Changed · +96 lines · +1,471 tokens per session 85de2a3705bf
- 4d ago First seen · 1,183 lines · 11,268 tokens per session scan A 7b57d4c6f6e7
mcp-server-ppt critical-rules.instructions.md is an instructions file published in the GitHub repository trsdn/mcp-server-ppt (36 stars, last pushed today), licensed MIT. It adds 12,739 tokens to every session, about $0.0637 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other instructions, from other repositories
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
AstrBot copilot-instructions.md
Copilot instructions for AstrBotDevs/AstrBot, covering astrbot development instructions, working effectively, bootstrap and install dependencies, running the application and dashboard build (vue.js/node.js).
mcp-dotnet-samples AGENTS.md
AGENTS.md instructions for microsoft/mcp-dotnet-samples, covering agents.md - mcp .net samples, project overview, project structure and architecture, repository organization and sample components.
chatgpt-cli CLAUDE.md
Claude Code instructions for kardolus/chatgpt-cli, covering chatgpt-cli — release runbook, prerequisites, 1. cut the release, 2. publish the github release + binaries and 3. update the homebrew tap.
NeuroAPI AGENTS.md
Instructions for neurogen-dev/NeuroAPI, a project described as: NeuroAPI: российский AI API для Codex CLI и Claude Code — безопасные one-click установщики для Windows и macOS.
moorestech AGENTS.md
AGENTS.md instructions for moorestech/moorestech, covering コーディングの指針, qa（必須）, 互換性とパフォーマンス, 既知の制約（設計上の割り切り） and regionの活用.