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/joshsmithxrm/power-platform-developer-suite/copilot-instructionsgit clone --depth 1 https://github.com/joshsmithxrm/power-platform-developer-suiteWrote 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/joshsmithxrm/power-platform-developer-suite/copilot-instructions)<a href="https://agentmods.dev/instructions/joshsmithxrm/power-platform-developer-suite/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/joshsmithxrm/power-platform-developer-suite/copilot-instructions.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 | $0.00402 | $0.00402 |
| Opus 5 | $0.00201 | $0.00201 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
power-platform-developer-suite copilot-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 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.
What it actually says
Copilot Code Review Instructions
This file guides GitHub Copilot's code review behavior for the PPDS repository.
Architecture (ADRs 0015, 0024, 0025, 0026)
Layer Rules
- CLI/TUI are THIN presentation adapters - no business logic
- Application Services own all business logic
- Services are UI-agnostic - no
Console.WriteLine, no Spectre/Terminal.Gui references
File I/O
- UIs never read/write files directly
- All file access through Application Services
- WRONG:
File.ReadAllTextin command handler - CORRECT:
await _profileService.GetProfilesAsync()
Progress Reporting
- Services accept
IProgressReporter, not write to console - UIs implement adapters for their display medium
- Services return data, presentation layers format it
Error Handling
- Services throw
PpdsExceptionwithErrorCodeandUserMessage - Never expose technical details (GUIDs, stack traces) in
UserMessage - UIs format errors for their medium
Dataverse Patterns
- Use bulk APIs (
CreateMultiple,UpdateMultiple) not loops with single operations - Use FetchXML aggregate for counting, not retrieve-and-count
- Propagate
CancellationTokenthrough all async methods - Get pool client INSIDE parallel loops, not outside
Style Preferences
Do NOT suggest:
- Converting
foreachloops withifconditions to LINQ.Where()chains - Replacing
if/elsewith ternary operators - "Simplifying" explicit control flow
These are intentional style choices per project conventions.
Valuable Findings
DO flag:
- Code duplication across files
- Resource leaks (missing disposal, using statements)
- Missing
CancellationTokenpropagation - Sync-over-async patterns (
.GetAwaiter().GetResult()) - Thread safety issues in async code
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.
- 4d ago First seen · 58 lines · 402 tokens per session scan A e824cfb79f05
power-platform-developer-suite copilot-instructions.md is an instructions file published in the GitHub repository joshsmithxrm/power-platform-developer-suite (5 stars, last pushed 10d ago), licensed MIT. It adds 402 tokens to every session, about $0.0020 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
tools-cli copilot-instructions.md
Instructions for TALXIS/tools-cli, covering copilot instructions for talxis cli (txc), project overview and instructions for copilot.
xrm-mcp CLAUDE.md
Claude Code instructions for jukkan/xrm-mcp, covering xrm mcp — agent guide, decision tree, environment isolation rule, discovery failure rule and revised decision tree.
maui ci-copilot-pipeline-security.instructions.md
Security rules for the Copilot PR-review pipeline. Read before editing.
maui performance-hotpaths.instructions.md
Instructions for dotnet/maui, covering performance-critical path rules, hot paths in maui, allocation avoidance, caching and invalidation and collection iteration.
maui collectionview-windows.instructions.md
Instructions for dotnet/maui, covering collectionview — windows (items/ handler), winui listview/itemsrepeater patterns, data source and change notifications, layout configuration and cross-platform consistency.
codex-provider-sync AGENTS.md
Instructions for Dailin521/codex-provider-sync, covering ai / agent operator guide, vnext architecture baseline, goal, choose the interface and safe operating flow.