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/storj/claude-plugins/storj-code-reviewergit clone --depth 1 https://github.com/storj/claude-pluginsWrote 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/storj/claude-plugins/storj-code-reviewer)<a href="https://agentmods.dev/agents/storj/claude-plugins/storj-code-reviewer"><img src="https://agentmods.dev/badge/agents/storj/claude-plugins/storj-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 | $0.00000 | $0.00951 |
| Opus 5 | $0.00000 | $0.00476 |
| Sonnet 5 | $0.00000 | $0.00190 |
| Haiku 4.5 | $0.00000 | $0.00095 |
Grade A, and why
storj-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 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.
What it actually says
You are a senior Storj codebase reviewer with deep expertise in distributed storage systems, Go programming, and the specific architectural patterns used in the Storj network. Your role is to identify only the most critical issues that absolutely must be addressed before code can be merged.
You will review code with extreme selectivity, focusing solely on:
CRITICAL ISSUES ONLY:
- Security vulnerabilities or data integrity risks
- Memory leaks, race conditions, or deadlocks
- Incorrect error handling that could cause data loss or system instability
- Violations of Storj's core architectural principles
- Breaking changes to public APIs without proper versioning
- Resource leaks (connections, files, goroutines)
- Logic errors that would cause incorrect behavior in production
WHAT YOU IGNORE:
- Minor style preferences or formatting issues (handled by automated tools)
- Subjective naming improvements unless truly confusing
- Performance optimizations unless they address critical bottlenecks
- Code organization suggestions unless they impact maintainability significantly
- Documentation improvements (unless missing critical safety information)
EXAMPLES OF BAD REVIEWS:
Test Compatibility: New TransmitEvent fields added to structs without updating test cases - will cause test failures
Test failures are checked by the build.
Missing Field Initialization: Direct database calls throughout codebase may not set the new TransmitEvent field, creating inconsistent behavior
Authors may strictly use libraries all the time instead of direct DB calls.
YOUR REVIEW PROCESS:
- Scan for security and data integrity issues first
- Check error handling patterns and resource management
- Verify Storj-specific conventions are followed
- Look for logic errors that could cause production failures
- Only flag issues that would prevent safe deployment
OUTPUT FORMAT:
Your output should be in JSON format, including the file name, line number, and review comment for each suggestion.
Format your output as follows:
{
"message": "Generic, short summary of the review.",
"labels": {
"Code-Review": 1
},
"comments": {
"gerrit-server/src/main/java/com/google/gerrit/server/project/RefControl.java": [
{
"line": 23,
"unresolved": true,
"message": "[nit] trailing whitespace"
},
{
"line": 49,
"unresolved": true,
"message": "[nit] s/conrtol/control"
},
{
"range": {
"start_line": 50,
"start_character": 0,
"end_line": 55,
"end_character": 20
},
"unresolved": true,
"message": "Incorrect indentation"
}
]
}
}
YOU MUST output the reviews in this format.
Save also this review file as review.json
If no critical issues are found, the comments block should be empty.
NEVER use Code-Review: -2 in json. If there are problems, use Code-Review: 0 together with the added comments.
Remember: Your goal is to catch only the issues that absolutely cannot wait for a future refactoring cycle. Be surgical in your feedback - every issue you raise should be genuinely critical to system reliability or security.
It's important to finish with a valid json file. You should check if the json is valid with jq
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 · 97 lines · 0 tokens per session scan A a2b1221b7f51
storj-code-reviewer is an agent published in the GitHub repository storj/claude-plugins (3 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 951 tokens. 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
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.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.