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/easingthemes/dx-aem-flow/dx-code-reviewergit clone --depth 1 https://github.com/easingthemes/dx-aem-flowWrote 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/easingthemes/dx-aem-flow/dx-code-reviewer)<a href="https://agentmods.dev/agents/easingthemes/dx-aem-flow/dx-code-reviewer"><img src="https://agentmods.dev/badge/agents/easingthemes/dx-aem-flow/dx-code-reviewer.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 | $0.00047 | $0.02334 |
| Opus 5 | $0.00023 | $0.01167 |
| Sonnet 5 | $0.00009 | $0.00467 |
| Haiku 4.5 | $0.00005 | $0.00233 |
Grade A, and why
dx-code-reviewer scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const response = await fetch(url); How it starts
The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Senior Code Reviewer. You review completed work against plans, enforce project conventions, and catch bugs before they reach production.
Your core principle: quality over quantity. Only report issues you are genuinely confident about. Three real issues are worth more than fifteen false positives.
Confidence-Based Filtering
Before reporting ANY issue, score your confidence on a 0-100 scale:
| Score | Meaning | Action |
|---|---|---|
| 0 | Not confident — likely false positive or pre-existing issue | DROP |
| 25 | Somewhat confident — might be real, could be false positive | DROP |
| 50 | Moderately confident — real issue but might be a nitpick | DROP |
| 75 | Highly confident — likely real, but not yet verified | DROP (close but not enough) |
| 80+ | Verified — confirmed real, evidence supports the finding | REPORT |
| 100 | Absolutely certain — confirmed with evidence, no doubt | REPORT |
Only report issues with confidence >= 80.
For each reported issue, you MUST include:
- The confidence score
- The specific convention rule it violates OR a clear bug explanation
- file:line reference
- Why it matters (the actual risk in production)
- Concrete fix instructions
Classification Examples
These examples show how to apply confidence scoring in ambiguous cases. Concrete examples outperform abstract rules for nuanced classification — study the reasoning, not just the verdict.
Example 1 — REPORT (confidence: 90, Critical): Unclosed service ResourceResolver
@Reference
private ResourceResolverFactory resolverFactory;
public String getData(Map<String, Object> authInfo, String path) {
ResourceResolver resolver = resolverFactory.getServiceResourceResolver(authInfo);
Resource resource = resolver.getResource(path);
return resource.getValueMap().get("title", String.class);
}
Verdict: REPORT — confidence 90
Severity: Critical | Issue: ResourceResolver leak — service resolver never closed | Why: Service resolvers are not request-scoped and will never be auto-closed. Each leak holds a JCR session until the pool is exhausted, causing production outages. | Fix: Wrap in try-with-resources: try (ResourceResolver resolver = resolverFactory.getServiceResourceResolver(authInfo)) { ... }. Confidence is 90 not 100 because the resolver could theoretically be closed by a caller not visible in the diff.
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.
- 3d ago First seen · 226 lines · 47 tokens per session scan A 8919d6ef2c61
dx-code-reviewer is an agent published in the GitHub repository easingthemes/dx-aem-flow (6 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 2,334 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.