deepseek

deepseek is a command for Claude Code from XinyuQu/llm-review. It costs 13 tokens per session (617 once invoked), scanned A, original, Apache-2.0.

A command that sends your current code changes to DeepSeek for an adversarial review, meaning a review focused on finding weaknesses and problems.

In plain words
What is it for?
Use it to review staged changes or changes against a chosen Git reference, optionally limiting the review to the diff.
Why use it?
It gives you an additional model's critique and can run in the background for reviews that take time.

Command for Claude Code

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

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 llm-review plugin — 1 skill, 16 commands shipped together

Good fit Use it to review staged changes or changes against a chosen Git reference, optionally limiting the review to the diff.

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 XinyuQu/llm-review
Claude Code
/plugin install llm-review

Made for: Claude Code.

Or install llm-review, the plugin that ships this one along with the rest of its 1 skill, 16 commands.

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 deepseek

README.md
[![agentmods](https://agentmods.dev/badge/commands/xinyuqu/llm-review/deepseek.svg)](https://agentmods.dev/commands/xinyuqu/llm-review/deepseek)
Your own site
<a href="https://agentmods.dev/commands/xinyuqu/llm-review/deepseek"><img src="https://agentmods.dev/badge/commands/xinyuqu/llm-review/deepseek.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 617 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 $0.00013 $0.00617
Opus 5 $0.00006 $0.00309
Sonnet 5 $0.00003 $0.00123
Haiku 4.5 $0.00001 $0.00062

Measured 8d ago against content hash 7ef550a309e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

deepseek 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 8d 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

2 near-identical copies found in the catalogue:

  • minimax — 89% identical, 12 lines differ
  • gemini — 88% identical, 13 lines differ
commands/deepseek.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.

Get an adversarial code review from DeepSeek of the current changes.

Raw slash-command arguments: $ARGUMENTS

Parse $ARGUMENTS into the engine command (build as separate args, never splice the raw string into a shell line):

  • first bare word not starting with - → base git ref, pass as --base <ref>
  • --staged → review staged changes only
  • --wait → execution mode (don't pass to engine; foreground)
  • --background → execution mode (don't pass to engine; background)

Execution mode

Reviews against large diffs legitimately take several minutes. Default to background so the Claude Code session is not blocked.

  1. If $ARGUMENTS contains --wait: foreground, skip the question.
  2. If $ARGUMENTS contains --background: background, skip the question.
  3. Otherwise, estimate diff size first, then ask:
    • Run git diff --shortstat (or git diff --shortstat --staged if --staged, or git diff --shortstat <base>...HEAD if a base was given).
    • Tiny (≤2 files changed and no large directory rewrite) → recommend wait.
    • Otherwise → recommend background.
    • Call AskUserQuestion once with two options, recommended first and suffixed with (Recommended):
      • Wait for results
      • Run in background

Foreground path

Run synchronously:

node "${CLAUDE_PLUGIN_ROOT}/scripts/llm-review.mjs" review --provider deepseek [--base <ref>] [--staged]

Then present DeepSeek's review to the user verbatim — do not soften, summarize, or re-rank its findings. It is an independent second opinion; preserve its severities and verdict. If the command errored (e.g. missing API key or no changes), relay the error and point the user to /llm-review:setup.

Background path

Launch with Bash(run_in_background: true):

node "${CLAUDE_PLUGIN_ROOT}/scripts/llm-review.mjs" review --provider deepseek --background [--base <ref>] [--staged]

Do not call BashOutput and do not wait for completion in this turn. Tell the user:

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. 8d ago First seen · 62 lines · 13 tokens per session scan A 7ef550a309e1

Subscribe to this mod's changes

deepseek is a command published in the GitHub repository XinyuQu/llm-review (6 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 617 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 2026-08-31.