parallel-review

parallel-review is a command for coding agents from CloudAI-X/claude-workflow-v2. It costs 19 tokens per session (646 once invoked), scanned A, original, MIT.

A command for reviewing several code directories or files at the same time with separate reviewers, then combining their findings. The review covers quality, bugs, security, performance, and missing tests.

In plain words
What is it for?
Use it for broad code reviews where targets can be examined independently. It is suited to checking multiple files or directories before merging changes.
Why use it?
It shortens the time needed to inspect independent parts of a codebase and produces one prioritized report. Each finding includes a location and severity.

Command

Part of the claude-workflow-v2 plugin — 14 skills, 26 commands, 7 agents, 6 hooks shipped together

About the project

Project Starter is a workflow plugin that equips coding agents with specialized subagents, reusable skills, commands, hooks, and output styles for software projects. It is for developers who want structured assistance with tasks such as planning, debugging, code review, security, and automation across several coding-agent platforms. Catalogue add-ons are components of its own workflow.

CloudAI-X/claude-workflow-v2 · 1,413 stars · on GitHub

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 commands/cloudai-x/claude-workflow-v2/parallel-review
Clone the repo
git clone --depth 1 https://github.com/CloudAI-X/claude-workflow-v2

Or install claude-workflow-v2, the plugin that ships this one along with the rest of its 14 skills, 26 commands, 7 agents, 6 hooks.

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 parallel-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/cloudai-x/claude-workflow-v2/parallel-review.svg)](https://agentmods.dev/commands/cloudai-x/claude-workflow-v2/parallel-review)
Your own site
<a href="https://agentmods.dev/commands/cloudai-x/claude-workflow-v2/parallel-review"><img src="https://agentmods.dev/badge/commands/cloudai-x/claude-workflow-v2/parallel-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 646 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 $0.00019 $0.00646
Opus 5 $0.00010 $0.00323
Sonnet 5 $0.00004 $0.00129
Haiku 4.5 $0.00002 $0.00065

Measured 5d ago against content hash 8fa1994d7318, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

parallel-review 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.

commands/parallel-review.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Parallel Code Review

Review $ARGUMENTS using parallel subagents for maximum speed.

Process

  1. Parse Targets: Split arguments into independent review targets
  2. Spawn Parallel Reviewers: Launch one subagent per target
  3. Collect Results: Each subagent returns its review automatically on completion
  4. Synthesize: Merge findings into prioritized report

Execution Pattern

CRITICAL: Launch ALL Task calls in a SINGLE message for true parallelism.

For each independent target, spawn a subagent with run_in_background: true:

I'm launching N parallel code reviewers:

[Task 1]
description: "Review [target 1]"
prompt: "You are a code reviewer. Analyze [target 1] for:
- Code quality and best practices
- Potential bugs and edge cases
- Security vulnerabilities
- Performance issues
- Test coverage gaps

Provide findings with file:line references and severity levels."
run_in_background: true

[Task 2]
description: "Review [target 2]"
prompt: "You are a code reviewer. Analyze [target 2] for..."
run_in_background: true

[Task 3]
description: "Review [target 3]"
prompt: "You are a code reviewer. Analyze [target 3] for..."
run_in_background: true

Each subagent returns its result automatically when it completes — there is no separate retrieval step. Read each review as it returns.

Output Format

## Parallel Review Results

### Summary

- **Targets reviewed**: N
- **Total findings**: X
- **Critical issues**: Y
- **Execution time**: ~Zs (parallel)

### [Target 1] Findings

#### Critical

- [Issue] at file:line - [Description]

#### Warnings

- [Issue] at file:line - [Description]

#### Suggestions

- [Improvement] at file:line - [Description]

### [Target 2] Findings

...

### Combined Priority List

1. **Critical** - [Target X] - [Issue description]
2. **Critical** - [Target Y] - [Issue description]
3. **High** - [Target Z] - [Issue description]
   ...

### Recommended Actions

1. Fix critical issues in [Target X] first
2. Address security concerns in [Target Y]
3. Consider performance optimizations in [Target Z]

Read the full file on GitHub · 110 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 · 110 lines · 19 tokens per session scan A 8fa1994d7318

Subscribe to this mod's changes

parallel-review is a command published in the GitHub repository CloudAI-X/claude-workflow-v2 (1,413 stars, last pushed 10d ago), licensed MIT. It adds 19 tokens to every session and 646 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 2026-08-30.