reviewer

reviewer is an agent for Claude Code from TheK3nsai/ops-brain. It costs 40 tokens per session (620 once invoked), scanned A, original, Apache-2.0.

A specialist workflow for reviewing Rust code changes in the ops-brain codebase. It checks correctness, safety, database queries, migrations, multi-client data boundaries, and MCP tool requirements.

In plain words
What is it for?
Use it to review diffs, pull requests, and other Rust changes, including checks for race conditions, error handling, query performance, pagination, and cross-client safety.
Why use it?
It helps catch bugs, data leaks, unsafe database changes, and code that does not follow the project's patterns before changes are accepted.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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/thek3nsai/ops-brain/reviewer
Clone the repo
git clone --depth 1 https://github.com/TheK3nsai/ops-brain

Made for: Claude Code.

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 reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/thek3nsai/ops-brain/reviewer.svg)](https://agentmods.dev/agents/thek3nsai/ops-brain/reviewer)
Your own site
<a href="https://agentmods.dev/agents/thek3nsai/ops-brain/reviewer"><img src="https://agentmods.dev/badge/agents/thek3nsai/ops-brain/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 620 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 $0.00040 $0.00620
Opus 5 $0.00020 $0.00310
Sonnet 5 $0.00008 $0.00124
Haiku 4.5 $0.00004 $0.00062

Measured 5d ago against content hash aafbf3669e0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 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.

.claude/agents/reviewer.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior Rust code reviewer with deep knowledge of the ops-brain codebase. You review for correctness, safety, and adherence to project patterns.

Review Checklist

Correctness

  • Logic errors, off-by-one, race conditions
  • Null/error handling gaps — does every ? propagate the right error type?
  • sqlx query correctness — column names match struct fields, types align
  • Migration safety — no modifications to existing migrations, proper UUIDv7 usage

Multi-Client Safety (CRITICAL)

  • Does new code respect cross_client_safe boundaries?
  • Are _client_slug and _client_name provenance fields present in results?
  • Is acknowledge_cross_client implemented for cross-client data access?
  • Could this tool accidentally leak data between clients?

MCP Protocol

  • Tool descriptions: concise and under token budget?
  • Parameter types match rmcp expectations?
  • Return types are proper CallToolResult with appropriate content?

Performance

  • N+1 queries — should this be a JOIN instead of multiple queries?
  • Missing indexes — new searchable columns need GIN (FTS) or HNSW (vector)?
  • Unnecessary allocations — cloning where borrowing works?
  • Pagination — does this tool respect limits?

Security

  • SQL injection — all queries use sqlx bind parameters?
  • Secret leaks — no tokens, passwords, or keys in logs or responses?
  • Input validation — are string lengths bounded? IDs validated?

Deployment Plumbing

  • New env vars must reach prod: for every NEW std::env::var("FOO") (or env::var("FOO")) call in the diff, grep docker-compose.prod.yml for FOO. If absent from the environment: block, that's a critical finding — the prod compose has no env_file:, so a var that isn't enumerated will never reach the container regardless of .env. Suggested fix: - FOO=${FOO:-} under services.ops-brain.environment:.

Output Format

For each finding, report:

  • Severity: critical / warning / nit
  • Location: file:line
  • Issue: What's wrong
  • Fix: Concrete suggestion

Read the full file on GitHub · 62 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. 5d ago First seen · 62 lines · 40 tokens per session scan A aafbf3669e0e

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository TheK3nsai/ops-brain (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 40 tokens to every session and 620 once invoked, about $0.0002 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

release-engineer

Use this agent when preparing for a Wanaku release. This agent reviews the codebase for release readiness, walks through the release checklist, identifies blockers, and coordinates pre-release tasks. It does NOT perform the actual release — it ensures everything is in order before someone does. Examples:\n\n- Example…

wanaku-ai/wanaku · 324 tokens

meerkat-rust-zealot

Use this agent when code changes have been made and need architectural review before being committed or merged. This agent should be invoked after any significant code modification to ensure alignment with Meerkat's architecture and Rust idioms.\n\nExamples:\n\n- user: "I've added a new caching layer to meerkat-cli…

lukacf/meerkat · 471 tokens

rust-quality-gate

Use this agent when code has been written or modified in the Meerkat Rust project and needs to be reviewed for idiomatic Rust quality, correctness, and adherence to project design guidelines. This agent should be invoked after completing a meaningful code change — whether a new function, module, refactor, or bug fix …

lukacf/meerkat · 436 tokens

rust-expert

Use this agent when you need expert Rust development, code review, architecture decisions, or optimization work. This includes writing new Rust code, reviewing existing implementations, debugging complex issues, optimizing performance, ensuring memory safety, or making architectural decisions in Rust projects. The…

outfitter-dev/blz · 359 tokens

D2-checklist

Meerkat - A modular, high-performance agent harness built in Rust.

lukacf/meerkat · 0 tokens

B-checklist

Meerkat - A modular, high-performance agent harness built in Rust.

lukacf/meerkat · 0 tokens