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.
npx skills add verivus-oss/llm-cli-gateway --skill multi-llm-consensusgit clone --depth 1 https://github.com/verivus-oss/llm-cli-gatewayWrote 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/skills/verivus-oss/llm-cli-gateway/multi-llm-consensus)<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.
<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>- NVIDIA SkillSpector warn
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
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 | $0.00049 | $0.02442 |
| Opus 5 | $0.00024 | $0.01221 |
| Sonnet 5 | $0.00010 | $0.00488 |
| Haiku 4.5 | $0.00005 | $0.00244 |
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.
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:
- Give every required reviewer the same target, revision, acceptance criteria, and evidence requirements.
- Require the terminal JSON verdict
APPROVED_UNCONDITIONALLY,CHANGES_REQUIRED, orBLOCKED_EXTERNALwith evidence-backed findings. - 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.
- 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.
- 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. - 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.
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.
- 9d ago First seen · 226 lines · 49 tokens per session scan A 37cc41fde14c
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.
Other skills, from other repositories
architect
System design, tradeoffs, and complex technical decisions.
scope-analyst
Catch ambiguities and hidden requirements before planning.
security-analyst
Threat-model and find vulnerabilities, with practical remediation.
code-reviewer
Find bugs, security holes, and maintainability issues in a diff or file.
plan-reviewer
Validate that a work plan is executable before work starts.
researcher
Research external libraries, APIs, and best practices, with evidence.