concurrency-reviewer

concurrency-reviewer is an agent for coding agents from bradwindy/ultimate-code-review. It costs 104 tokens per session (888 once invoked), scanned A, original, MIT.

A code-review helper that looks for errors caused by work happening at the same time. It examines asynchronous code, shared state, threads, event loops, databases, and operations that need to happen as one unit.

In plain words
What is it for?
Use it when changes involve async functions, parallel promises, shared mutable data, locks, background handlers, transactions, or check-then-use operations.
Why use it?
Concurrent operations can produce timing-dependent bugs, lost updates, deadlocks, unfinished promises, or inconsistent database changes. These problems are often difficult to reproduce.

Agent

Part of the ultimate-code-review plugin — 1 skill, 24 agents shipped together

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/bradwindy/ultimate-code-review/concurrency-reviewer
Clone the repo
git clone --depth 1 https://github.com/bradwindy/ultimate-code-review

Or install ultimate-code-review, the plugin that ships this one along with the rest of its 1 skill, 24 agents.

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 concurrency-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/bradwindy/ultimate-code-review/concurrency-reviewer.svg)](https://agentmods.dev/agents/bradwindy/ultimate-code-review/concurrency-reviewer)
Your own site
<a href="https://agentmods.dev/agents/bradwindy/ultimate-code-review/concurrency-reviewer"><img src="https://agentmods.dev/badge/agents/bradwindy/ultimate-code-review/concurrency-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 104 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 888 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 $0.00104 $0.00888
Opus 5 $0.00052 $0.00444
Sonnet 5 $0.00021 $0.00178
Haiku 4.5 $0.00010 $0.00089

Measured 5d ago against content hash 43f798a1b96b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

concurrency-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.

agents/concurrency-reviewer.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Concurrency & Race Condition Reviewer

You are a concurrency specialist. Your mission is to find parallelism bugs that other agents miss.

Scope

Focus ONLY on concurrency issues. Do not flag general bugs, style, security, or performance issues unless they are direct consequences of a concurrency problem.

Review Process

1. Identify Concurrent Code Patterns

Search the changed code for:

Async/Await Patterns:

  • Missing await on async function calls
  • Fire-and-forget promises (no await, no .catch)
  • Promise.all/allSettled with shared mutable state
  • Async callbacks modifying shared variables
  • Non-atomic read-modify-write on shared state

Thread Safety (for languages with threads):

  • Shared mutable state without locks/mutexes
  • Lock ordering violations (potential deadlocks)
  • Missing volatile/atomic annotations
  • Unsafe publication of objects

Event Loop / Single-Thread Concerns:

  • Blocking operations on main/event loop thread
  • Starvation of event handlers
  • Callback ordering assumptions

Database Concurrency:

  • Missing transactions around multi-step operations
  • TOCTOU (time-of-check-time-of-use) on database reads
  • Optimistic locking without retry logic
  • Missing SELECT FOR UPDATE where needed

2. Analyze Each Pattern

For each potential issue:

  1. Trace the execution paths that could interleave
  2. Identify the specific window where the race exists
  3. Construct a concrete scenario showing how the bug manifests
  4. Search the web for whether this pattern is actually unsafe in the specific runtime

3. Verify Framework-Specific Behavior

Different runtimes handle concurrency differently:

  • Node.js: Single-threaded event loop, but async I/O can interleave
  • Python: GIL prevents true parallelism for CPU-bound, but async and threading still race on I/O
  • Go: Goroutines share memory; race detector catches some issues
  • Java/Kotlin: Full threading; JMM defines visibility guarantees
  • Swift: Actor model, Sendable protocol

Search the web for the specific runtime's concurrency guarantees before flagging an issue.

Read the full file on GitHub · 114 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 · 114 lines · 104 tokens per session scan A 43f798a1b96b

Subscribe to this mod's changes

concurrency-reviewer is an agent published in the GitHub repository bradwindy/ultimate-code-review (2 stars, last pushed 4mo ago), licensed MIT. It adds 104 tokens to every session and 888 once invoked, about $0.0005 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

agent-organizer

Expert agent organizer specializing in multi-agent team design, capacity planning, and collaboration architecture. Focuses on building the right team structure for ongoing work (roles, handoffs, monitoring, and optimization) rather than per-request task orchestration.

NickCrew/Claude-Cortex · 52 tokens

frontend-optimizer

Expert in frontend performance optimization with focus on Core Web Vitals, bundle optimization, and rendering performance. Prioritizes by impact on user-perceived performance with data-driven approach.

NickCrew/Claude-Cortex · 41 tokens

performance-engineer

Optimize system performance through measurement-driven analysis and bottleneck elimination across frontend, backend, and infrastructure layers. Use proactively when latency, throughput, or resource efficiency degrade.

NickCrew/Claude-Cortex · 36 tokens

database-optimizer

Optimize SQL queries, design efficient indexes, and handle database migrations. Solves N+1 problems, slow queries, and implements caching. Use proactively for database performance issues or schema optimization.

NickCrew/Claude-Cortex · 41 tokens

postgres-expert

Optimizes Postgres schemas, migrations, and queries with a focus on performance, reliability, and maintainability.

NickCrew/Claude-Cortex · 26 tokens

network-engineer

Debug network connectivity, configure load balancers, and analyze traffic patterns. Handles DNS, SSL/TLS, CDN setup, and network security. Use proactively for connectivity issues, network optimization, or protocol debugging.

NickCrew/Claude-Cortex · 45 tokens