joshsmithxrm

32 mods across 1 repository, 5 stars between them.

challenger

01

joshsmithxrm/power-platform-developer-suite

Agent Claude Code

You are an adversarial reviewer. You receive an investigation summary and a set of constraints/decisions. Your job is to find blind spots, flawed assumptions, and missing considerations.

5 8d ago A 2 tokens original MIT

code-reviewer

03

joshsmithxrm/power-platform-developer-suite

Agent Claude Code

You are an impartial code reviewer. You receive ONLY the diff, the Constitution, and relevant spec ACs. You have NO implementation context — no plan, no task description, no "what we were trying to do.".

5 8d ago A 3 tokens original MIT

fix-agent

05

joshsmithxrm/power-platform-developer-suite

Agent Claude Code

You receive a specific review finding and make a targeted fix. You do NOT redesign, refactor, or improve surrounding code. You fix exactly what the finding describes.

5 8d ago A 2 tokens original MIT

PreToolUse

07

joshsmithxrm/power-platform-developer-suite

Hook Claude Code

Runs before the agent uses a tool for Edit, Write, Edit, Write, Edit, Write, Bash(rm:*), Bash(rm -rf:*), Bash(rm -fr:*), Bash(Remove-Item:*), Bash(del:*), Bash(rmdir:*), Bash, Bash, Edit, Write, Bash(git worktree remove:*), Write and Edit tool calls, executing protect-main-branch.py, snk-protect.py…

5 8d ago C tokens not measured copy · 86% MIT

PostToolUse

08

joshsmithxrm/power-platform-developer-suite

Hook Claude Code

Runs after a tool call finishes for Bash(git worktree remove:*) tool calls, executing worktree-safety.py via python. From joshsmithxrm/power-platform-developer-suite.

5 8d ago A tokens not measured original MIT

Stop

09

joshsmithxrm/power-platform-developer-suite

Hook Claude Code

Runs when the agent finishes a response, executing shakedown-readonly-guard.py via python. From joshsmithxrm/power-platform-developer-suite.

5 8d ago A tokens not measured original MIT

audit-capture

11

joshsmithxrm/power-platform-developer-suite

Skill Claude CodeCodex

Run manifest-driven PNG captures of TUI and extension surfaces for design audits. Emits a schema-conformant capture tree for consumption by a Claude design-audit session.

5 8d ago A 37 tokens original MIT

backlog

12

joshsmithxrm/power-platform-developer-suite

Skill Claude CodeCodex

Create, triage, and manage GitHub issues per PPDS backlog conventions. Use when creating issues, grooming the backlog, reviewing what to work on next, or filing bugs.

5 8d ago A 39 tokens original MIT

debug

13

joshsmithxrm/power-platform-developer-suite

Skill Claude CodeCodex

Interactive debugging with systematic root-cause analysis. Use when encountering any bug, test failure, or unexpected behavior — before proposing fixes.

5 8d ago A 28 tokens original MIT

dependabot-triage

14

joshsmithxrm/power-platform-developer-suite

Skill Claude CodeCodex

Triage and merge open dependabot PRs per docs/MERGE-POLICY.md — classify each PR (auto-merge / verify-then-merge / manual review), enable auto-merge for safe ones, run targeted test suites for risky ones, and surface anything needing human judgment. Use when there's a backlog of dependabot PRs, after a quiet period…

5 8d ago A 87 tokens original MIT

design

15

joshsmithxrm/power-platform-developer-suite

Skill Claude CodeCodex

Brainstorm ideas into specs and plans through collaborative dialogue. Use when starting a new feature, exploring an idea, or designing a system — before any implementation.

5 8d ago A 33 tokens original MIT

ext-panels

16

joshsmithxrm/power-platform-developer-suite

Skill Claude CodeCodex

Building or modifying VS Code webview panels and multi-surface panel features. Use when creating new panels, adding features to existing panels, designing panel architecture across Extension/TUI/MCP/CLI.

5 8d ago A 43 tokens original MIT

gates

17

joshsmithxrm/power-platform-developer-suite

Skill Claude CodeCodex

Mechanical pass/fail checks. No judgment, no opinions - compiler, linter, and tests either pass or they don't. Run before code reviews, after fix batches, and before PRs.

5 8d ago A 5 tokens original MIT

implement

18

joshsmithxrm/power-platform-developer-suite

Skill Claude CodeCodex

Execute a checked-in implementation plan end-to-end using parallel agents. Use when a spec and plan exist in .plans/ and you're ready to build.

5 8d ago A 32 tokens original MIT

pr

19

joshsmithxrm/power-platform-developer-suite

Skill Claude CodeCodex

Create PR, wait for the configured automated review, triage every comment, and present a summary. Use when work is ready to ship — after gates, verify, QA, and review are complete.

5 8d ago A 42 tokens original MIT

qa

20

joshsmithxrm/power-platform-developer-suite

Skill Claude CodeCodex

QA — Three-Agent Blind Verification. Use when making code changes that need product-level validation — after implementation, after fix rounds, before PRs. Dispatches agents that test the running product without seeing source code.

5 8d ago A 44 tokens original MIT

release

21

joshsmithxrm/power-platform-developer-suite

Skill Claude CodeCodex

Cut a PPDS release — CHANGELOG refresh, version bump, tag push sequence, CI monitoring, post-publish verification. Use when preparing a new prerelease or stable release across CLI, TUI, MCP, Extension, and NuGet libraries.

5 8d ago A 52 tokens original MIT

review

22

joshsmithxrm/power-platform-developer-suite

Skill Claude CodeCodex

Bias-isolated code review — reviewer sees only the diff, constitution, and spec ACs, never the implementation plan or task context.

5 8d ago A 28 tokens original MIT

shakedown

24

joshsmithxrm/power-platform-developer-suite

Skill Claude CodeCodex

Structured multi-surface product validation — systematically test Extension, TUI, MCP, and CLI with parity comparison and architecture audit. Use before releases, after large features, or to kick the tires.

5 8d ago A 43 tokens original MIT