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/claude-mdgit 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/claude-md)<a href="https://agentmods.dev/instructions/joshsmithxrm/power-platform-developer-suite/claude-md"><img src="https://agentmods.dev/badge/instructions/joshsmithxrm/power-platform-developer-suite/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 | $0.00750 | $0.00750 |
| Opus 5 | $0.00375 | $0.00375 |
| Sonnet 5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
power-platform-developer-suite 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PPDS
Multi-surface platform (CLI / TUI / VS Code Extension / MCP / NuGet). All business logic lives in Application Services — never in UI code.
Read specs/CONSTITUTION.md before any work (Spec Laws SL1–SL5 are non-negotiable).
Governance for THIS file: docs/CLAUDE-MD-GOVERNANCE.md (4-question test, line cap, marker).
The .claude/ tooling is optional; CI is the authoritative gate (see CONTRIBUTING.md "AI-Assisted Development").
NEVER
- Hold a single pooled
IDataverseConnectionPoolclient across multiple parallel queries — defeats pool parallelism. (No analyzer; subtle.) - Write CLI status messages to
stdout— useConsole.Error.WriteLine.stdoutis reserved for data. - Throw raw exceptions from Application Services — wrap in
PpdsExceptionwith anErrorCode. - Trust an agent research summary without reading the underlying code yourself.
- Edit
PublicAPI.Unshipped.txtduring a rebase — accept--theirsand let it regenerate; manual edits produce phantom API-drift conflicts. - Trust a
release/Xbranch as the source of truth for what shipped as version X — verify withgit merge-base --is-ancestor <release-tag> <branch>. Tags are authoritative; the branch tip may sit on a separate lineage. - Use PowerShell cmdlets (
Test-Path,Get-ChildItem, etc.) via the Bash tool, or embed Windows backslash paths in inlinepython -cliterals — see.claude/WORKFLOW.md"Bash Tool Portability".
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.
- 5d ago First seen · 35 lines · 750 tokens per session scan A baebd68f1fba
power-platform-developer-suite CLAUDE.md is an instructions file published in the GitHub repository joshsmithxrm/power-platform-developer-suite (7 stars, last pushed 5d ago), licensed MIT. It adds 750 tokens to every session, about $0.0037 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
AGENTS.md instructions for Dailin521/codex-provider-sync, covering ai / agent operator guide, vnext architecture baseline, goal, choose the interface and safe operating flow.