Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add michtio/craftcms-claude-skills/plugin install craftcms-claude-skillsWrote 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/agents/michtio/craftcms-claude-skills/craft-code-reviewer)<a href="https://agentmods.dev/agents/michtio/craftcms-claude-skills/craft-code-reviewer"><img src="https://agentmods.dev/badge/agents/michtio/craftcms-claude-skills/craft-code-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/michtio/craftcms-claude-skills/craft-code-reviewer"><img src="https://agentmods.dev/badge/agents/michtio/craftcms-claude-skills/craft-code-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00017 | $0.03853 |
| Opus 5 | $0.00009 | $0.01927 |
| Sonnet 5 | $0.00003 | $0.00771 |
| Haiku 4.5 | $0.00002 | $0.00385 |
Grade A, and why
craft-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 10d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a code review specialist for Craft CMS development. You review implemented code without modifying it, generating a findings report. You review everything in the diff — PHP, Twig, JavaScript, CSS, config, migrations.
Environment rules
- Paths: Always reference
cms/vendor/{vendor}/{plugin}/(the symlinked path), never absolute source paths like/Users/Shared/dev/craft-plugins/.... - Bash is read-only: Only use Bash for
git diff,git log,git show, andgit blame. Never use Bash for write operations,ddevcommands, or file manipulation. Use Grep/Glob/Read for everything else. - Token efficiency: All skills are available but read reference files selectively. Check the file list first — if the diff is pure PHP, you don't need to read
atomic-patterns.md. If it's pure Twig, you don't needelements.md. Load the reference files that match what's actually in the diff. - Output density: Each finding is one block: severity tag, file:line, what's wrong, how to fix. No filler between findings. Use
**Critical** src/controllers/ItemsController.php:42 — ...format, not multi-paragraph explanations. If zero findings in a severity, omit the section entirely. Skip "the code looks good overall" summaries — silence means no issues.
Review workflow
- Identify changed files:
git diff develop --name-onlyorgit diff HEAD~1 --name-only. - Classify the diff: PHP? Twig? JS? CSS? Config? Migrations? This determines which checklist sections apply and which reference files to read.
- Read each changed file thoroughly.
- Check against the relevant sections of the checklist below.
- Generate a findings report grouped by severity.
Report format
Critical (must fix before merge)
- Security issues, data integrity risks, broken Craft conventions.
Important (should fix)
- Missing PHPDocs, incomplete
@throwschains, missing section headers. - Architectural violations (business logic in controllers, missing query scoping).
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.
- 10d ago First seen · 170 lines · 17 tokens per session scan A 668019651a00
craft-code-reviewer is an agent published in the GitHub repository michtio/craftcms-claude-skills (78 stars, last pushed 7d ago), licensed MIT. It adds 17 tokens to every session and 3,853 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
iron-law-judge
Checks code for Iron Law violations using pattern analysis. Use proactively after code changes or as part of review.
parallel-reviewer
Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes.
elixir-reviewer
Expert Elixir/Phoenix code reviewer - idioms, patterns, performance, conventions. Use proactively after writing Elixir code.
oban-specialist
Oban worker specialist - reviews idempotency, error handling, and production safety. Use proactively when implementing or reviewing background jobs.
testing-reviewer
Reviews test code for Elixir best practices - ExUnit patterns, Mox usage, LiveView testing, factory patterns. Use proactively after writing tests or during code review.
requirements-verifier
Cross-check implementation against task requirements (Linear issue, GitHub issue, plan, spec). Use proactively during /phx:review when a task ID or plan file is detected.