multi-llm-consensus

multi-llm-consensus is a skill for Claude Code from verivus-oss/llm-cli-gateway. It costs 49 tokens per session (2,442 once invoked), scanned A, original, MIT.

A process for asking a required group of language-model providers to independently review work and reach an evidence-backed agreement. Every required reviewer must give an unconditional approval for consensus to succeed.

In plain words
What is it for?
High-stakes generated work, resolving conflicting reviews, and applying a final quality gate with a fixed reviewer roster, shared criteria, and machine-readable verdicts.
Why use it?
It reduces the risk of relying on one reviewer's mistake or silently ignoring disagreement or an unavailable required reviewer.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

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

Good fit High-stakes generated work, resolving conflicting reviews, and applying a final quality gate with a fixed reviewer roster, shared criteria, and machine-readable verdicts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/verivus-oss/llm-cli-gateway/multi-llm-consensus
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.

Any agent
npx skills add verivus-oss/llm-cli-gateway --skill multi-llm-consensus
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-consensus

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/multi-llm-consensus"><img src="https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/multi-llm-consensus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,442 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: 4 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 71
    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 73
    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 74
    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 75
    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 $0.00049 $0.02442
Opus 5 $0.00024 $0.01221
Sonnet 5 $0.00010 $0.00488
Haiku 4.5 $0.00005 $0.00244

Measured 9d ago against content hash 37cc41fde14c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

multi-llm-consensus 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 9d 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.

skills/multi-llm-consensus/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-LLM Consensus

Use the local gtwy stdio MCP server to obtain independent evidence from the required provider roster, reconcile disagreements, and continue until every required reviewer gives an unconditional verdict. Do not invoke provider CLIs directly for consensus or review requests.

The complete CLI roster is Claude, Codex, Gemini, Grok, Mistral, Devin, and Cursor. Confirm the live usable roster first with provider_tool_capabilities. A deliberately scoped subset is valid only when the user or governing process explicitly chose it. A required provider that is unavailable is a blocker, not a successful consensus with fewer voters.

Configured API providers are dynamic rather than members of this canonical CLI roster. Discover them with list_models and reported capabilities. They do not have a local CLI checkout/worktree or native ACP guarantee and must not silently replace a required source-inspecting CLI consensus reviewer.

Consensus Contract

For a mandatory approval review:

  1. Give every required reviewer the same target, revision, acceptance criteria, and evidence requirements.
  2. Require the terminal JSON verdict APPROVED_UNCONDITIONALLY, CHANGES_REQUIRED, or BLOCKED_EXTERNAL with evidence-backed findings.
  3. Use approvalStrategy: "legacy" for Codex, Gemini, Grok, Mistral, Devin, and Cursor. They reject mcp_managed and their approvalPolicy fields have no effect. Use mcp_managed only for a deliberately configured Claude request.
  4. Use sandboxMode: "read-only" for an inspection-only Codex review, or sandboxMode: "workspace-write" only when it must create build or test artifacts. Do not use fullAuto.
  5. Do not impose a review-round, turn, token, price, cost, or wallclock cap. The configured idle-timeout safeguard is only for lack of process output on incremental providers. For terminal-burst providers (gemini, mistral, devin, cursor) it is instead a total-runtime bound, since those emit nothing until exit. That classification is each provider's default invocation; cursor with outputFormat: "stream-json" streams, so there it is a real idle window.
  6. Accept the gate only when every required reviewer gives explicit, evidence-backed APPROVED_UNCONDITIONALLY. Conditional approval, residual issues, a malformed response, inability to verify, cancellation, timeout, or provider failure is not approval.

Read the full file on GitHub · 226 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. 9d ago First seen · 226 lines · 49 tokens per session scan A 37cc41fde14c

Subscribe to this mod's changes

multi-llm-consensus is a skill published in the GitHub repository verivus-oss/llm-cli-gateway (15 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 2,442 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.