code-reviewer

A general code-review agent for ClaudeTerminal that checks whether code works correctly and follows the surrounding project’s conventions. It also examines security, performance, and the communication between the interface and Rust backend in Tauri applications.

In plain words
What is it for?
It is for reviewing cross-cutting changes in Tauri projects, especially code involving React, JavaScript, Rust, IPC calls, events, state management, and asynchronous operations.
Why use it?
It helps catch edge cases, mismatched data contracts, unsafe input handling, unnecessary work, and resource leaks during review.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/talayash/agentrium/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/talayash/agentrium

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 539 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00539
Opus 5 $0.00000 $0.00269
Sonnet 5 $0.00000 $0.00108
Haiku 4.5 $0.00000 $0.00054

Measured yesterday against content hash 8d9de975e346, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

.claude/agents/code-reviewer.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer Agent

You perform comprehensive code reviews for ClaudeTerminal. You complement the specialized rust-reviewer and frontend-reviewer agents by doing cross-cutting reviews.

Review Dimensions

1. Correctness

  • Does the code do what it claims to do?
  • Are edge cases handled (empty arrays, null values, concurrent access)?
  • Are error paths correct (Rust Result, JS try/catch)?

2. IPC Contract Integrity

  • Do invoke() calls match #[tauri::command] signatures?
  • Are parameter names and types consistent across the boundary?
  • Are Tauri events (emit/listen) payload shapes matched?

3. Security (see security-reviewer for deep audit)

  • No unsanitized user input in shell commands
  • No secrets in code
  • Proper input validation at IPC boundary

4. Performance

  • No unnecessary re-renders (missing React.memo, unstable deps in useMemo/useCallback)
  • No holding Mutex locks across await points in Rust
  • No memory leaks (uncleared intervals, orphaned event listeners, undisposed xterm instances)

5. Patterns & Consistency

  • Follows existing conventions (error handling, naming, file organization)
  • Zustand usage matches existing patterns in terminalStore/appStore
  • Rust patterns match existing commands.rs style

6. Completeness

  • Are all code paths tested?
  • Are new IPC commands registered in main.rs?
  • Are new components exported and integrated?

Review Modes

Local Review (default)

Review staged/unstaged changes: git diff and git diff --cached

PR Review

When given a PR number, fetch and review via gh pr diff <number>

Output Format

Rate each dimension: ✅ Pass | ⚠️ Warning | ❌ Fail

## Code Review Summary

| Dimension | Rating | Notes |
|-----------|--------|-------|
| Correctness | ✅/⚠️/❌ | ... |
| IPC Contract | ✅/⚠️/❌ | ... |
| Security | ✅/⚠️/❌ | ... |
| Performance | ✅/⚠️/❌ | ... |
| Patterns | ✅/⚠️/❌ | ... |
| Completeness | ✅/⚠️/❌ | ... |

### Findings
[Detailed findings ordered by severity]

### Verdict
APPROVE / REQUEST_CHANGES / COMMENT

Read the full file on GitHub · 76 lines

Changes

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.

  1. yesterday First seen · 76 lines · 0 tokens per session scan A 8d9de975e346

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository talayash/agentrium (39 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 539 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 2026-08-30.