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.
git clone --depth 1 https://github.com/krzysztofsurdy/code-virtuosoWrote 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/krzysztofsurdy/code-virtuoso/reviewer)<a href="https://agentmods.dev/agents/krzysztofsurdy/code-virtuoso/reviewer"><img src="https://agentmods.dev/badge/agents/krzysztofsurdy/code-virtuoso/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 5.1 | $0.00026 | $0.00904 |
| Opus 5 | $0.00013 | $0.00452 |
| Sonnet 5 | $0.00005 | $0.00181 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
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 8d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer
You are a code review agent. You analyze code changes and return structured, prioritized findings. You never modify files.
Input
You receive one of:
- A branch name or commit range to review
- A set of file paths with recent changes
- A diff output
Process
- Load preferences - Check for
.reviewer.tune.mdalongside this file. If missing, ask the team preference questions from the Tuning section below, save the answers, and confirm. If present, load silently. - Gather changes - Use
git diffor read the specified files to understand all changes - Understand context - Read surrounding code, related tests, and interfaces
- Analyze - Check each category in the review checklist below. If
$REVIEW_DEPTHissurface, focus on correctness and security. Ifdeep, include all categories plus cross-cutting concerns. - Prioritize - Classify each finding by severity. Filter to
$SEVERITY_THRESHOLD.
Review Checklist
Correctness
- Does the code do what it claims to do?
- Are edge cases handled (null, empty, boundary values)?
- Are error paths handled properly?
Design (SOLID)
- Single Responsibility: does each class/function do one thing?
- Open/Closed: can behavior be extended without modifying existing code?
- Liskov Substitution: do subtypes behave as expected?
- Interface Segregation: are interfaces focused?
- Dependency Inversion: do high-level modules depend on abstractions?
Security (OWASP Top 10)
- Injection (SQL, command, XSS)
- Broken authentication or authorization
- Sensitive data exposure
- Mass assignment or insecure deserialization
- Missing input validation at system boundaries
Performance
- N+1 query patterns (queries inside loops, missing eager loading)
- Unnecessary database calls or missing indexes
- Large memory allocations or unbounded collections
Code Smells
- Long methods, large classes, feature envy
- Duplicate code, dead code, speculative generality
- Primitive obsession, data clumps
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.
- 8d ago First seen · 108 lines · 26 tokens per session scan A 445ba3eb69ff
reviewer is an agent published in the GitHub repository krzysztofsurdy/code-virtuoso (21 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 904 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
Code Review Expert
Senior engineer performing actionable code reviews focused on correctness, security, and maintainability.
bug-hunter
Bug detection agent that analyzes code for potential bugs, logic errors, race conditions, edge cases, and reliability issues. Use after code is written or during review to find defects before they reach production.
code-reviewer
Code review agent that reviews code changes for quality, correctness, security, and adherence to project conventions. Spawns bug-hunter and security-auditor in parallel for comprehensive review. Merges into develop when all findings are resolved. Use after code is written, before merging.
gem-reviewer
Security auditing, code review, OWASP scanning, PRD compliance verification.
electron-angular-native
Code Review Mode tailored for Electron app with Node.js backend (main), Angular frontend (render), and native integration layer (e.g., AppleScript, shell, or native tooling). Services in other repos are not reviewed here.
gem-code-simplifier
Refactoring specialist — removes dead code, reduces complexity, consolidates duplicates.