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 skills/joshsmithxrm/power-platform-developer-suite/prnpx skills add joshsmithxrm/power-platform-developer-suite --skill prgit 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/skills/joshsmithxrm/power-platform-developer-suite/pr)<a href="https://agentmods.dev/skills/joshsmithxrm/power-platform-developer-suite/pr"><img src="https://agentmods.dev/badge/skills/joshsmithxrm/power-platform-developer-suite/pr.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 | $0.00042 | $0.01006 |
| Opus 5 | $0.00021 | $0.00503 |
| Sonnet 5 | $0.00008 | $0.00201 |
| Haiku 4.5 | $0.00004 | $0.00101 |
Grade A, and why
pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR
End-to-end PR lifecycle: rebase, create, wait for the configured automated review, triage every comment, and present a summary to the user.
Process
Step 1: Rebase and Push
git fetch origin main && git rebase origin/main
Conflicts → present to user, do NOT auto-resolve. Then:
git merge-base --is-ancestor origin/main HEAD
git push --force-with-lease origin HEAD
Step 2: Linked Issues
Include Closes #NNN for each issue this PR resolves. If you do not know the issue numbers (interactive), ask the user.
Step 3: Pre-PR Self-Review
Dispatch the code-reviewer agent against git diff origin/main...HEAD. See REFERENCE.md §2 for inputs and finding triage. DEFECTs must be fixed before opening. Skip with --no-self-review.
Step 4: Create PR (Draft)
Write body to temp file (see REFERENCE.md §3 for template), then:
gh pr create --draft --title "<title>" --body-file "$PR_BODY"
Step 5: Wait for Automated Review and CI
Poll for the configured automated review (e.g. Gemini or CodeRabbit; some repos disable it) and check status directly:
gh pr checks <pr-number> --watch # CI + CodeQL status
gh pr view <pr-number> --json reviews,comments,statusCheckRollup
Review timing is unpredictable (2–10+ minutes). Poll gh pr view <pr-number> --json reviews,comments every ~30s for up to 15 minutes. If the review still has not arrived at the cap, surface that to the user and get explicit confirmation before proceeding — do not silently mark ready while a late review can still land. Skip the wait only after verifying no reviewer app is installed — check recent merged PRs for reviewer-bot activity and the repo for reviewer config (commands in REFERENCE.md §4); if the check is inconclusive, ask the user rather than assuming.
Step 6: Triage Every Comment
Fetch review comments and respond to every one — this is the discipline that captures knowledge:
gh pr view <pr-number> --json reviews,comments
gh api repos/:owner/:repo/pulls/<pr-number>/comments # inline review comments
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 94 lines · 42 tokens per session scan A a3f59e4d4936
pr is a skill published in the GitHub repository joshsmithxrm/power-platform-developer-suite (5 stars, last pushed 10d ago), licensed MIT. It adds 42 tokens to every session and 1,006 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.
Other skills, from other repositories
release-readiness
Assesses ship-readiness for .NET MAUI release branches — Servicing Releases (SR) and Previews — and produces public-safe, copy-ready release handoffs or Loop-page drafts from the resulting evidence. Use for readiness verdicts, release blockers, Preview/SR status, release handoff pages, manual validation instructions…
create-release
Create a versioned GitHub release with changelog.
bump-version
Bump the SSW.VerticalSliceArchitecture.Template NuGet package version to cut a new release. Use when the user says "bump the version", "cut a release", "release a new version", "publish a new package version", or similar for this template repo. Edits the version in VerticalSliceArchitecture.nuspec — which is what…
release-roslynator
Use when shipping a roslynator release, rolling CHANGELOG.md [Unreleased], updating the VS Code extension changelog, creating a GitHub v release, or optionally tagging cli-v.
maf-release-watcher
Detects new MAF releases, extracts breaking changes, and keeps the toolkit's registry/matrix/guide current. Pipeline: (1) deterministic data extraction via GitHub Actions + Python helpers + dotnet-inspect, opens a PR with raw data and TODOs on a per-version branch (never commits direct to main), (2) optionally, a…
release-cut
Use this skill whenever Larry asks to cut a release (e.g., "prep vX.Y.Z release").