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 model-routinggit 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/model-routing)<a href="https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/model-routing"><img src="https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/model-routing.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 9 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 26 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 28 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 112 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 29 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 31 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 90 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 108 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 110 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 111 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 | $0.00059 | $0.02237 |
| Opus 5 | $0.00030 | $0.01118 |
| Sonnet 5 | $0.00012 | $0.00447 |
| Haiku 4.5 | $0.00006 | $0.00224 |
Grade A, and why
model-routing 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.
How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Routing
Choose providers from live gateway capability data, not a static claim that one model is universally best. Send every request, including reviews, through the local gtwy stdio MCP server. Do not invoke a provider CLI directly to bypass the gateway's request, session, and audit surfaces.
Discover Before Selecting
- Call provider_tool_capabilities through gtwy for current request surfaces, transports, local configuration, and provider-owned tool availability.
- Call cli_versions when a provider behaves differently from its recorded contract.
- Omit model unless the user explicitly named a model. If an explicit model is needed, use list_models for the target provider first.
- Record why a provider is selected: task scope, required capabilities, target repository access, and safety posture.
The gateway's CLI provider roster is:
| Provider | Gateway request surface | Selection notes |
|---|---|---|
| Claude | claude_request and claude_request_async | The only provider that can use mcp_managed. |
| Codex | codex_request and codex_request_async | Use current sandboxMode values, not fullAuto. |
| Gemini | gemini_request and gemini_request_async | Antigravity owns its native tool configuration; use workingDir to select cwd. |
| Grok | grok_request and grok_request_async | CLI request surface plus native ACP capability. |
| Mistral | mistral_request and mistral_request_async | CLI request surface plus native ACP capability; explicit model selection is injected through VIBE_ACTIVE_MODEL because Vibe has no CLI model flag. |
| Devin | devin_request and devin_request_async | CLI request surface plus native ACP capability; it accepts flat prompt, not promptParts. |
| Cursor | cursor_request and cursor_request_async | CLI request surface plus native ACP capability; it accepts flat prompt, not promptParts. |
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.
- 8d ago First seen · 198 lines · 59 tokens per session scan A 658869a73f44
model-routing is a skill published in the GitHub repository verivus-oss/llm-cli-gateway (15 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 2,237 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.
Other skills, from other repositories
provider-integration
Adds new AI providers to claude-council, configures provider API settings, troubleshoots provider connections, and documents the provider script interface. Covers creating provider shell scripts, setting API keys, and validating connectivity. Triggers on "add provider", "new AI agent", "provider not working", "API…
architect
System design, tradeoffs, and complex technical decisions.
plan-reviewer
Validate that a work plan is executable before work starts.
researcher
Research external libraries, APIs, and best practices, with evidence.
security-analyst
Threat-model and find vulnerabilities, with practical remediation.
debugger
Rank root-cause hypotheses and propose the smallest safe fix.