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.
/plugin marketplace add XinyuQu/llm-review/plugin install llm-reviewWrote 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.
[](https://agentmods.dev/commands/xinyuqu/llm-review/deepseek-setup)<a href="https://agentmods.dev/commands/xinyuqu/llm-review/deepseek-setup"><img src="https://agentmods.dev/badge/commands/xinyuqu/llm-review/deepseek-setup.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.00496 |
| Opus 5 | $0.00011 | $0.00248 |
| Sonnet 5 | $0.00004 | $0.00099 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade C, and why
deepseek-setup scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Advanced — the **user** runs this in their own terminal (never you): `printf %s 'THE_KEY' | node "${CLAUDE_PLUGIN_ROOT}/scripts/llm-review.mjs" config-set --provider deepseek --transport api --api-key-stdin` (key via s Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
**Security — hard rule:** never run any command containing the literal key yourself; a crafted key can inject shell commands. If the user pasted a key into the chat, do NOT put it in a command — tell them it is now expos Copies of this mod
1 near-identical copy found in the catalogue:
- minimax-setup — 86% identical, 12 lines differ
What it actually says
Guided setup for the deepseek provider. Follow this exactly; do not improvise extra steps.
Step 1 — probe status:
node "${CLAUDE_PLUGIN_ROOT}/scripts/llm-review.mjs" setup --provider deepseek --json
Parse the JSON: mode, api (hasKey, primaryEnv, keyHelp), ready, resolvedTransport, reviewCommand. DeepSeek is mode: api-only (no official CLI) — API key only, no subscription option.
Step 2 — if already ready: tell the user it's set up, then AskUserQuestion once: Keep current setup vs Reconfigure. If keep → show status and stop.
Step 3 — API KEY FLOW:
-
Tell the user where to get a key:
api.keyHelp. -
Offer how to provide it, most secure first:
- Recommended: run
/plugin, open llm-review config, paste the key into the secure prompt (stored in the OS keychain). - Or export
api.primaryEnvin their shell for this session. - Advanced — the user runs this in their own terminal (never you):
printf %s 'THE_KEY' | node "${CLAUDE_PLUGIN_ROOT}/scripts/llm-review.mjs" config-set --provider deepseek --transport api --api-key-stdin(key via stdin, never in argv; writes~/.config/llm-review/config.json, chmod 600).
Security — hard rule: never run any command containing the literal key yourself; a crafted key can inject shell commands. If the user pasted a key into the chat, do NOT put it in a command — tell them it is now exposed, to add it via the keychain (
/plugin) or their own shell env, and to rotate it. - Recommended: run
-
Re-run the Step 1 probe and present it.
Step 4 — finish: state whether the provider is now ready and show the exact review command (reviewCommand, i.e. /llm-review:deepseek). Use AskUserQuestion at most once in this flow.
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.
- 7d ago First seen · 29 lines · 22 tokens per session scan C de24bfdf0259
deepseek-setup is a command published in the GitHub repository XinyuQu/llm-review (6 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 496 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (asks for root, unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.
security-review
AI-powered security review of the current git diff (or specified paths). Dispatches the security-reviewer agent and prints findings grouped by severity.