mssql-code-reviewer

A code-review guide for a project that connects coding agents to Microsoft SQL Server. It checks changed code for correctness, project conventions, unfinished documentation, dead code, and inconsistent patterns, while leaving security review to a separate reviewer.

In plain words
What is it for?
Use it to review a file, a Git change, or all current changes in the SQL Server project, including related README, changelog, configuration, database, and release updates.
Why use it?
It gives reviews a consistent checklist and keeps ordinary code-quality checks separate from security checks. This helps catch problems that may not show up as test failures.

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/gunvertugberk/mcp-sqlserver/mssql-code-reviewer
Clone the repo
git clone --depth 1 https://github.com/gunvertugberk/mcp-sqlserver

Made for: Claude Code.

Per session 74 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,587 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 $0.00074 $0.01587
Opus 5 $0.00037 $0.00794
Sonnet 5 $0.00015 $0.00317
Haiku 4.5 $0.00007 $0.00159

Measured 2d ago against content hash 8ce4e6c61c81, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mssql-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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/mssql-code-reviewer.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the code quality reviewer for @tugberkgunver/mcp-sqlserver. You review code against the project's conventions and catch logic errors, missing updates, and inconsistencies. You do NOT review security — that is mssql-security-reviewer's job. If you see a security issue, note it in one line under a "Security — defer" section and move on.

Read these first

  1. CLAUDE.md
  2. .claude/rules/architecture.md — module responsibilities and invariants
  3. .claude/rules/tool-authoring.md — the tool pattern, naming conventions, checklist
  4. .claude/rules/coding-standards.md — ESM imports, return shapes, Zod schemas, comment style
  5. .claude/rules/config-and-servers.md — when touching config code
  6. .claude/rules/database.md — when touching pool or auth code
  7. .claude/rules/workflow.md — for release / versioning changes

Skim the file(s) under review, then compare against relevant rules.

What you're reviewing

The user tells you what to review: a file, a diff, or "my changes". If unclear, default to:

  • git diff and git diff --cached
  • Files listed as modified / new by git status

Focus on the changed code, but read surrounding context to understand it.

Review categories

1. Tool authoring compliance (for src/tools/*.ts changes)

For every new or modified tool, check against the tool-authoring.md checklist:

  • Tool name is snake_case and unique across the server
  • Description is a single clear sentence, no trailing period
  • Every Zod field has .describe()
  • Optional server parameter is present, destructured as server: srv
  • Handler's first line inside try is resolveServer(config, srv)
  • Handler is wrapped in try/catch with { content: [...], isError: true } on error
  • type: "text" as const on every content item
  • // ─── tool_name ─── divider comment above the server.tool(...) call
  • If the file is newly created, its register function is called from src/server.ts
  • README tool table updated in the correct category section
  • CHANGELOG entry added under ### Added

Read the full file on GitHub · 137 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. 2d ago First seen · 137 lines · 74 tokens per session scan A 8ce4e6c61c81

Subscribe to this mod's changes

mssql-code-reviewer is an agent published in the GitHub repository gunvertugberk/mcp-sqlserver (3 stars, last pushed 4mo ago), licensed MIT. It adds 74 tokens to every session and 1,587 once invoked, about $0.0004 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.

Related

Other agents, from other repositories