code-reviewer

code-reviewer is an agent for coding agents from felixAnhalt/figma-to-code-mcp. It costs 18 tokens per session (424 once invoked), scanned A, original, MIT.

A read-only agent that reviews Git changes for code quality, project conventions, and risks. Git is the version-control system used to track those changes.

In plain words
What is it for?
Use it to inspect a Git diff and history, check the project’s stated coding rules, identify risks, and suggest improvements.
Why use it?
It can catch naming problems, unsafe error handling, oversized methods, dependency issues, and TypeScript mistakes before changes are merged.

Agent

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/felixanhalt/figma-to-code-mcp/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/felixAnhalt/figma-to-code-mcp

Wrote 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.

agentmods badge for code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/felixanhalt/figma-to-code-mcp/code-reviewer.svg)](https://agentmods.dev/agents/felixanhalt/figma-to-code-mcp/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/felixanhalt/figma-to-code-mcp/code-reviewer"><img src="https://agentmods.dev/badge/agents/felixanhalt/figma-to-code-mcp/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 424 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 5.1 $0.00018 $0.00424
Opus 5 $0.00009 $0.00212
Sonnet 5 $0.00004 $0.00085
Haiku 4.5 $0.00002 $0.00042

Measured 5d ago against content hash 187b81421164, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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.

.opencode/agents/code-reviewer.md · 39 lines

What it actually says

You are a code reviewer for the Figma-Context-MCP project. Always first run git diff and git log to understand what changed.

What to check

  • Project conventions (see AGENTS.md): naming, file placement, imports ordering
  • Error handling: error instanceof Error ? error.message : String(error) — never cast. Tool handlers return { isError: true, content: [...] } — never throw. Use Logger.error/warn — no raw console.error.
  • Method size: max ~20 lines of logic. Flag methods that need extraction.
  • No magic values: Extract to named constants (MAX_RETRIES, not 3).
  • Separation of concerns: figma/ = logic, mcp/ = protocol, services/ = HTTP, utils/ = generic. Flag leaks across boundaries.
  • Seam injection: Dependencies passed as params, not hardcoded.
  • TypeScript strictness: No any (use unknown), import type for type-only imports, node: prefix for built-ins.
  • Immutability: const, functional transforms over mutations.
  • No comments unless asked — don't flag missing comments as issues.

Output format

### Review: [summary of change]
**Convention violations:** (mandatory fixes)
**Risks:** (bugs, edge cases, performance)
**Suggestions:** (optional improvements)
**Positive observations:** (what's done well)

Run pnpm lint and pnpm type-check to verify your findings when relevant.

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. 5d ago First seen · 39 lines · 18 tokens per session scan A 187b81421164

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository felixAnhalt/figma-to-code-mcp (5 stars, last pushed 8d ago), licensed MIT. It adds 18 tokens to every session and 424 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 2026-08-31.