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 agentmods add commands/verivus-oss/llm-cli-gateway/codex-requestgit clone --depth 1 https://github.com/verivus-oss/llm-cli-gatewayWhat 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 | $0.00011 | $0.00291 |
| Opus 5 | $0.00005 | $0.00146 |
| Sonnet 5 | $0.00002 | $0.00058 |
| Haiku 4.5 | $0.00001 | $0.00029 |
Grade A, and why
codex-request 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 2d 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.
What it actually says
Send a request through the llm-gateway MCP server's codex_request tool.
Raw arguments: $ARGUMENTS
Use the llm-gateway's codex_request MCP tool to execute this prompt. Pass the raw arguments as the prompt.
Do not pass fullAuto. It is deprecated compatibility shorthand that expands to --sandbox workspace-write, so defaulting to it silently grants write access.
Pass sandboxMode explicitly on a new session. For inspection use sandboxMode: "read-only"; do not rely on omitting the field, because the gateway then emits no --sandbox flag and Codex resolves the policy from configuration, project trust, and its own fallback, so a trusted project can resolve to workspace-write. Pass workspace-write only when the task must edit files.
The gateway filters --sandbox out of a resume argv, so sandboxMode has no effect on a resumed request. That is not a guarantee that the resumed session keeps its original posture: configOverrides still passes through and can set sandbox_mode, and Codex re-resolves configuration on a cold resume. Establish the posture on the first request and verify it when it matters.
Do not pass model unless the caller named one; the gateway resolves the configured Codex default.
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.
- 2d ago First seen · 19 lines · 11 tokens per session scan A d7182be91490
codex-request is a command published in the GitHub repository verivus-oss/llm-cli-gateway (14 stars, last pushed 8d ago), licensed MIT. It adds 11 tokens to every session and 291 once invoked, about $0.0001 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 commands, from other repositories
spec-design
Create comprehensive technical design for a specification.
ox-session-pause
belongs in the ox CLI JSON output (guidance field), not here. Skills are agent-specific wrappers; ox serves all agents (Codex, etc.). --> Suspend the current session recording. Local cache continues to receive entries, but the upload at stop time will exclude the suspended range.
setup_research_plan
Set up or start a research project.
export
GDPR Article 20 — export all memories you own as portable JSON.
search
Search X (Twitter) and the web in real time with Grok, then summarize with sources.
result
Show the final output of a completed Grok job.