qwen-review

qwen-review is a command for Claude Code from xiaolai/cc-suite. It costs 31 tokens per session (1,032 once invoked), scanned A, original, ISC.

A command that sends a limited, read-only code review request to Qwen Code, an AI coding tool. It gives Qwen access only to specifically allowed workspace files and does not let it change code.

In plain words
What is it for?
Use it to review selected files with an optional model and background mode. The runner uses sandboxing, isolated copies, strict completion checks, verified hashes, and limited session resumption.
Why use it?
It provides an independent critique while keeping implementation authority with the main agent and limiting what Qwen can read or do.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the cc-suite plugin — 13 skills, 39 commands, 6 agents, 3 hooks shipped together

Good fit Use it to review selected files with an optional model and background mode. The runner uses sandboxing, isolated copies, strict completion checks, verified hashes, and limited session resumption.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add xiaolai/cc-suite
Claude Code
/plugin install cc-suite

Made for: Claude Code.

Or install cc-suite, the plugin that ships this one along with the rest of its 13 skills, 39 commands, 6 agents, 3 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 qwen-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/xiaolai/cc-suite/qwen-review/github.svg)](https://agentmods.dev/commands/xiaolai/cc-suite/qwen-review)
Your own site
<a href="https://agentmods.dev/commands/xiaolai/cc-suite/qwen-review"><img src="https://agentmods.dev/badge/commands/xiaolai/cc-suite/qwen-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for qwen-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/xiaolai/cc-suite/qwen-review"><img src="https://agentmods.dev/badge/commands/xiaolai/cc-suite/qwen-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,032 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00031 $0.01032
Opus 5 $0.00015 $0.00516
Sonnet 5 $0.00006 $0.00206
Haiku 4.5 $0.00003 $0.00103

Measured 10d ago against content hash a233072c50e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

qwen-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 10d 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/qwen-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.

/cc-suite:qwen-review

Ask Qwen Code for independent critique without giving it implementation authority. The runner always uses Safe Mode, Plan mode, and stream-json. There is no write-enabled option.

The command is intentionally narrower than /cc-suite:grok: Qwen is a critic here, not a second editor. Its answer is critique, not evidence. The calling agent must verify material findings and retain final judgment.

User Input

$ARGUMENTS

Workflow

Step 1: Parse the bounded review

Extract these optional flags; the remaining text is the review prompt:

  • --model <id> — Qwen model id. Omit to use Qwen's configured default.
  • --target <workspace-file> — allow one exact file to be opened with read_file. Repeat for multiple files. Directories, globs, symlink escapes, and paths outside the workspace are rejected.
  • --background or --wait — default --wait.
  • --debug-capture — persist raw stdout/stderr for troubleshooting. Warn that raw capture can contain the complete reviewed files; leave it off normally.

If the prompt is empty, ask what Qwen should review and stop if no prompt is provided.

If the user did not explicitly authorize sending each target's contents to Qwen, ask once before continuing. A direct user request naming the target and asking for Qwen review is authorization. Never include .env, credentials, tokens, cookies, private keys, or unrelated workspace files.

Step 2: Check local readiness

bash "${CLAUDE_PLUGIN_ROOT}/scripts/qwen-preflight.sh"

Parse the single JSON object. If status is "error", report error_code and error, then stop. This preflight is local and does not send a model prompt or inspect credentials.

Step 3: Run the review

node "${CLAUDE_PLUGIN_ROOT}/scripts/qwen-runner.mjs" \
  --kind qwen-review \
  {--model "{model}" if given} \
  {--target "{target}" for every exact target} \
  --max-resumes 2 \
  --attempt-timeout-ms 300000 \
  --idle-timeout-ms 240000 \
  --timeout-ms 900000 \
  {--background if selected} \
  {--debug-capture only if explicitly selected} \
  --summary "qwen review: {short prompt summary}" \
  -- "{prompt}"

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. 10d ago First seen · 110 lines · 31 tokens per session scan A a233072c50e7

Subscribe to this mod's changes

qwen-review is a command published in the GitHub repository xiaolai/cc-suite (44 stars, last pushed 7d ago), licensed ISC. It adds 31 tokens to every session and 1,032 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 2026-08-30.