llm-cli-gateway: Skill for Claude Code

.agents/skills/multi-llm-review/SKILL.md

multi-llm-review is a skill for Claude Code from verivus-oss/llm-cli-gateway. It costs 61 tokens per session (4,889 once invoked), scanned A, original, MIT.

A complete code-review workflow that sends a change through the local gateway to seven independent command-line providers: Claude, Codex, Gemini, Grok, Mistral, Devin, and Cursor.

In plain words
What is it for?
Use it as a required review gate before release or for changes needing independent checks across all supported providers.
Why use it?
It provides broader validation for correctness, security, quality, or release readiness than a single review. The workflow keeps repairing and rechecking findings until every required healthy reviewer gives unconditional approval or a concrete external blocker is reported.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: installed under .agents/ (shared by several agents); mentions Codex; mentions Cursor.

This is verivus-oss/llm-cli-gateway's own configuration. It tells Claude Code how to work on llm-cli-gateway itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llm-cli-gateway configures →

Part of the llm-gateway plugin — 24 skills, 4 commands, 2 MCP servers shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to verivus-oss/llm-cli-gateway. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/verivus-oss/llm-cli-gateway/main/.agents/skills/multi-llm-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/verivus-oss/llm-cli-gateway

Made for: Claude Code.

Or install llm-gateway, the plugin that ships this one along with the rest of its 24 skills, 4 commands, 2 MCP servers.

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 multi-llm-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/multi-llm-review/github.svg)](https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/multi-llm-review)
Your own site
<a href="https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/multi-llm-review"><img src="https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/multi-llm-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 multi-llm-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/multi-llm-review"><img src="https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/multi-llm-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,889 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 8 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Prompt Injection · line 79
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 83
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 84
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 85
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Output Handling · line 109
    Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.
    Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
  • medium Prompt Injection · line 206
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Excessive Agency · line 212
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Prompt Injection · line 214
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
How audits are shown
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 $0.00061 $0.04889
Opus 5 $0.00030 $0.02445
Sonnet 5 $0.00012 $0.00978
Haiku 4.5 $0.00006 $0.00489

Measured 10d ago against content hash 68b80946b1cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

multi-llm-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.

.agents/skills/multi-llm-review/SKILL.md · 398 lines

How it starts

The opening of the file, as written. The whole thing — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-LLM Code Review

Use this skill for a real review gate, not a popularity vote or a summary-only second opinion. Dispatch review requests through the current agent's local stdio gateway MCP surface, never a direct provider CLI, shadow connector, or remote gateway when the requested validation path is stdio.

Completion contract

A required reviewer is complete only when it inspected the target and returned an evidence-backed APPROVED_UNCONDITIONALLY. A qualified approval, a conditional result, missing evidence, a malformed response, a timeout, or a provider error is not approval.

Do not set a review-round, turn, token, price, budget, or wallclock cap. Do not use route_request, select:"cheapest", maxCostUsd, maxOutputTokens, maxTurns, maxPrice, or a provider print deadline to reduce an exhaustive review. Continue evidence-based repair and re-review until every required healthy reviewer returns APPROVED_UNCONDITIONALLY, the user explicitly cancels, or it returns BLOCKED_EXTERNAL with a concrete external error. A blocked reviewer never becomes an implied approval.

Discover the actual roster

The gateway has seven canonical CLI provider types: Claude, Codex, Gemini (Antigravity), Grok, Mistral Vibe, Devin, and Cursor Agent. Start a full CLI review with all seven in its intended roster. Before dispatching, inspect what this gateway can actually run:

cli_versions()
list_models()
provider_tool_capabilities({cli:"claude"})
provider_tool_capabilities({cli:"codex"})
provider_tool_capabilities({cli:"gemini"})
provider_tool_capabilities({cli:"grok"})
provider_tool_capabilities({cli:"mistral"})
provider_tool_capabilities({cli:"devin"})
provider_tool_capabilities({cli:"cursor"})

Use provider-tools://{provider} as a cached read-only alternative. Optional API providers are configured availability discovered through list_models and their reported capabilities. They have no local CLI checkout/worktree or native ACP guarantee, so they are not silently interchangeable with a required source-inspecting CLI reviewer.

Read the full file on GitHub · 398 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 · 398 lines · 61 tokens per session scan A 68b80946b1cd

Subscribe to this mod's changes

multi-llm-review is a skill published in the GitHub repository verivus-oss/llm-cli-gateway (15 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 4,889 once invoked, about $0.0003 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.