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 agent-codex-gategit 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/agent-codex-gate)<a href="https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/agent-codex-gate"><img src="https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/agent-codex-gate/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/agent-codex-gate"><img src="https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/agent-codex-gate.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00050 | $0.01994 |
| Opus 5.5 | $0.00020 | $0.00798 |
| Sonnet 5.5 | $0.00010 | $0.00399 |
| Haiku 4.5 | $0.00005 | $0.00199 |
Grade A, and why
agent-codex-gate 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 1mo 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent + Codex Gate Pattern
Spawn subagents for independent implementation work, then make each one obtain an unconditional Codex verdict before accepting its result. A Codex-only gate is not a substitute for a required cross-LLM review.
Required Transport and Review Contract
Use the local stdio gateway only. In Codex, the tools normally appear as mcp__gtwy__codex_request, mcp__gtwy__codex_request_async, and mcp__gtwy__llm_job_*. Other MCP clients may display the short names. Do not run the codex CLI directly for a review request.
For every mandatory review:
- Omit model unless the caller explicitly selected a model.
- Pass approvalStrategy: "legacy". Gateway-managed approval is Claude-only; Codex rejects mcp_managed and ignores approvalPolicy.
- Use sandboxMode: "read-only" for normal inspection. Use sandboxMode: "workspace-write" only when the reviewer must produce write-producing build or test artifacts. Do not use fullAuto; it is a deprecated shorthand for workspace-write.
- Require the terminal JSON verdict:
APPROVED_UNCONDITIONALLY,CHANGES_REQUIRED, orBLOCKED_EXTERNAL. - Do not set a review round, turn, token, price, cost, or wallclock limit. The configured idle-timeout safeguard is for a process that produces no output, not a completion deadline.
- Continue until Codex returns explicit, evidence-backed
APPROVED_UNCONDITIONALLY. A conditional verdict, residual finding, malformed response, inability to verify, timeout, cancellation, or provider failure is not approval.
Repair access, targeting, evidence, or findings and resubmit as often as
needed. Stop only on explicit user cancellation or a terminal external provider
failure. Report a terminal failure as BLOCKED_EXTERNAL with its exact error;
never skip the gate or label the work approved.
Explicit user-authorized full-access Codex gate
The preceding read-only and workspace-write defaults are the normal Codex gate,
not a limit on an explicitly authorized full-access review. For that exception,
build the exact target checkout and start node dist/index.js --transport=stdio
from it. Do not use a globally installed or stale gtwy process.
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.
- 1mo ago First seen · 191 lines · 50 tokens per session scan A 97d40a4f2902
agent-codex-gate is a skill published in the GitHub repository verivus-oss/llm-cli-gateway (16 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 1,994 once invoked, about $0.0002 per session on Opus 5.5. 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
master-workflow
Orchestrate a build as orchestrator → worker → critical reviewer, delegating to Codex, Grok, OpenCode, Claude, or Kimi and looping until an independent cross-model reviewer scores the diff 9/10; for long builds with several lines of work in parallel worktrees, drive them all with the run-lines workflow. Use when the…
code-review
Find bugs and potential issues in code changes.
spae-inspect
Optimization & Verification for the SPAE framework. Performs gap analysis on PLAN.md.
clean
Orchestrates purification and refactoring agents sequentially.
improve-codebase-architecture
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
flutter-dart-code-review
Library-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns (BLoC, Riverpod, Provider, GetX, MobX, Signals), Dart idioms, performance, accessibility, security, and clean architecture.