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.
curl -O https://raw.githubusercontent.com/verivus-oss/llm-cli-gateway/main/.agents/skills/secure-orchestration/SKILL.mdgit 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/secure-orchestration)<a href="https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/secure-orchestration"><img src="https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/secure-orchestration.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00038 | $0.02815 |
| Opus 5 | $0.00019 | $0.01407 |
| Sonnet 5 | $0.00008 | $0.00563 |
| Haiku 4.5 | $0.00004 | $0.00281 |
Grade A, and why
secure-orchestration 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Secure Orchestration
Use this skill for sensitive code, privileged operations, autonomous changes, and security review. A security review request goes through the installed local stdio gateway MCP surface, never a direct provider binary, SDK, connector/shadow gateway, or shell fallback. If that stdio surface is unavailable, repair it or report the review incomplete.
The approval boundary
approvalStrategy:"mcp_managed" is an enforcement boundary only for Claude.
The gateway creates a request-scoped strict MCP configuration from provisioned
gateway-owned local definitions. Codex, Gemini, Grok, Mistral, Devin, and Cursor
must use approvalStrategy:"legacy"; they reject managed approval before
launch because their ambient MCP configuration cannot be isolated.
For Claude managed requests:
approvalPolicymay bestrict,balanced, orpermissive.- The default policy is
balanced; thresholds are strict2, balanced5, and permissive7. - Full permission bypasses and unverified execution posture are denied by
default. They require the caller's explicit request, an approval decision,
and
LLM_GATEWAY_APPROVAL_ALLOW_BYPASS=1. - Native continuation/fork,
workingDir, tool selectors, settings/plugins, additional directories, prompt-file controls, and other posture changes can require that same decision and operator setting. Do not add them casually. - Under managed approval, only gateway-owned local definitions explicitly provisioned for the request are eligible. Dynamic package execution, ambient PATH, and provider-configuration overrides cannot bypass that boundary.
Do not imply that gateway-managed approval protects a non-Claude legacy request.
Its sandbox, tool, permission, MCP, session, and ACP controls belong to the
provider. Query provider_tool_capabilities({cli:"..."}) before relying on any
of them.
Safe request patterns
Routine Claude managed inspection:
claude_request({
prompt:"Audit the supplied evidence packet for security defects. Inspect available source directly and cite evidence.",
approvalStrategy:"mcp_managed",
approvalPolicy:"strict"
})
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 · 259 lines · 38 tokens per session scan A 80a614803163
secure-orchestration is a skill published in the GitHub repository verivus-oss/llm-cli-gateway (15 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 2,815 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
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.
security-analyst
Threat-model and find vulnerabilities, with practical remediation.
plan-reviewer
Validate that a work plan is executable before work starts.
researcher
Research external libraries, APIs, and best practices, with evidence.
debugger
Rank root-cause hypotheses and propose the smallest safe fix.