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 agents/joshsmithxrm/power-platform-developer-suite/code-reviewergit clone --depth 1 https://github.com/joshsmithxrm/power-platform-developer-suiteWhat 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 | $0.00003 | $0.00319 |
| Opus 5 | $0.00002 | $0.00160 |
| Sonnet 5 | $0.00001 | $0.00064 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
code-reviewer 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 2d 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
Code Reviewer
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."
Your Job
Read code and find bugs. You are looking for:
- Logic errors, off-by-one, null/undefined paths
- Constitution violations (read specs/CONSTITUTION.md)
- Missing error handling, resource leaks
- API misuse, incorrect assumptions
- Security issues (OWASP top 10)
Rules
- You CANNOT edit code. You can only read and report.
- Do not speculate about intent — review what the code does, not what it might be trying to do.
- Every finding must cite a specific file and line number.
- Classify findings: DEFECT (must fix), CONCERN (should fix), NIT (optional).
- Do not report style issues unless they violate Constitution.
Output Format
For each finding:
[DEFECT|CONCERN|NIT] F-{N}: {one-line summary}
File: {path}:{line}
Evidence: {what the code does wrong}
Fix: {what it should do instead}
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.
- 2d ago First seen · 44 lines · 3 tokens per session scan A ea13063c5f78
code-reviewer is an agent published in the GitHub repository joshsmithxrm/power-platform-developer-suite (5 stars, last pushed 9d ago), licensed MIT. It adds 3 tokens to every session and 319 once invoked, about $0.0000 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 agents, from other repositories
write-tests-agent
Agent that determines what type of tests to write and invokes the appropriate skill. Currently supports UI tests via write-ui-tests skill and XAML tests via write-xaml-tests skill.
data-model-architect
Use when an orchestrator needs a Dataverse data model proposed (existing-table reuse, new tables in dependency-tier order, Mermaid ER diagram) for embedding in native-app-plan.md. Read-only — proposes, never mutates. Called by native-app-planner and /edit-app; not invoked directly by users.
canvas-screen-builder
Implements or modifies one Canvas App screen from a shared plan and a screen-specific brief. Writes exactly one .pa.yaml file and performs self-QA without compiling. Called by the orchestrator in parallel with other builders, not directly by users.
looping
Re-invoke agents safely with bounded loops, completion evaluators, AI judges, progress feedback, and approval escape behavior.
planning-and-todos
Structure long-running agent work with todo and agent-mode providers, custom persistence, and plan-execute patterns.
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.