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 skills/verivus-oss/llm-cli-gateway/provider-codexnpx skills add verivus-oss/llm-cli-gateway --skill provider-codexgit 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/provider-codex)<a href="https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/provider-codex"><img src="https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/provider-codex.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00073 | $0.02267 |
| Opus 5 | $0.00036 | $0.01133 |
| Sonnet 5 | $0.00015 | $0.00453 |
| Haiku 4.5 | $0.00007 | $0.00227 |
Grade A, and why
provider-codex 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 yesterday.
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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Provider: OpenAI Codex CLI
Process guidance for keeping the gateway's Codex (codex) integration aligned
with the upstream CLI. This skill does not define argv/env behaviour; the
single mechanical source of truth is UPSTREAM_CLI_CONTRACTS.codex in
src/upstream-contracts.ts, enforced by validateUpstreamCliArgs /
validateUpstreamCliEnv. Never re-encode flags, sandbox/approval modes, or
resume rules here or in TOML.
Identity
| Field | Value |
|---|---|
| CliType | codex |
| Executable | codex |
| Package | @openai/codex (npm) |
| Repo | https://github.com/openai/codex |
| Release API | https://api.github.com/repos/openai/codex/releases/latest |
| Changelog RSS | https://learn.chatgpt.com/docs/changelog/rss.xml |
| Watch categories | flags, sandbox-modes, approval-modes, session-resume, output-schema |
These values mirror UPSTREAM_CLI_CONTRACTS.codex.upstreamMetadata and
docs/upstream/provider-sources.dag.toml ([providers.codex]). The TypeScript
metadata is authoritative; the TOML is scanner input only.
When to use
- An OpenAI Codex CLI release lands and you need to check for contract drift.
- A
codexrequest fails the upstream contract check before spawn. npm run upstream:scan -- --livereports a change on the Codex release notes or changelog.
How LLM agents should use Codex through the gateway
- Discover the live gateway/provider surface before relying on Codex-specific
controls:
For a cached read-only resource, useprovider_tool_capabilities({cli:"codex"})provider-tools://codex. - Use
codex_requestfor normal implementation/review turns andcodex_request_asyncfor long-running work. To continue an existing Codex conversation, passcodex_requesta real Codex session UUID from~/.codex/sessions/, orresumeLatest:true; both route throughcodex exec resumeand work headlessly.codex_fork_sessionis registered but cannot run from the gateway:codex forkis interactive and requires a controlling terminal, and Codex exposes no non-interactive equivalent (codex exechas only resume/review/help). Re-check that on each Codex release; if a headless fork lands,codexForkCanRunHeadlessinsrc/index.tsis the single predicate to flip. - Omit
modelunless the caller explicitly asked for a specific variant; the gateway resolves the configured Codex default/profile. - Prefer
sandboxMode:"workspace-write"when Codex needs a writable workspace.fullAuto:trueis the deprecated compatibility shorthand. UseapprovalStrategy:"legacy": Codex rejectsmcp_managedbefore launch because its ambient MCP configuration cannot be isolated, andapprovalPolicyhas no effect for Codex. - Do not pass Claude-style
allowedToolsordisallowedTools; Codex does not expose those request fields through the gateway. Codex owns its MCP configuration, and a gatewaymcpServerslist is descriptive metadata, not an enforceable allowlist. - Use
sandboxMode,profile,configOverrides,oss, images,outputFormat, andoutputSchemaonly as reported byprovider_tool_capabilities.askForApprovalanduseLegacyFullAutoFlagare deprecated compatibility inputs: current Codex emits no corresponding argv and the gateway returns a warning.fullAuto:trueremains a compatibility shorthand forsandboxMode:"workspace-write". These are provider-native legacy controls, not inputs to the Claude-only gateway approval boundary. - Codex continuity is real through
codex exec resume: pass a real Codex UUID from~/.codex/sessions/, orresumeLatest:true. Gatewaygw-*IDs are not Codex sessions.sandboxModeand its deprecatedfullAuto:trueshorthand are dropped on resume, so those fields cannot select a posture there. That is not a guarantee that the original posture is retained:configOverridesis not filtered and can setsandbox_mode, and Codex re-resolves configuration on a cold resume.resumeLatestis under review (#258):--lastis cwd-filtered upstream unless--allis passed, which the gateway does not emit, and the child is still spawned with the gateway-resolved cwd. Do not rely on which session it selects or on the resumed working directory. The provider-nativeworkingDirandaddDirflags scope new sessions only; the gateway accepts but omits those fields on resume. Omitting them does not pin the resumed directory: the child is still spawned with the gateway-resolved cwd. A verifiedworkspaceor gatewayworktreecan still select the child process launch cwd and bind gateway tracking. Do not rely on a resumed session's directory in any resume form, including a direct UUID resume: the child is spawned with the gateway-resolved cwd even though the flags are filtered. - Codex new and resume requests send the exact prompt through stdin with the
native
-marker. They do not consume the platform's single-argv prompt allowance and are never truncated.codex_fork_sessionuses the distinctcodex forkcontract, remains argv-bound, and rejects oversized UTF-8 prompts as non-retryableinput_too_large. That rejection is deliberately evaluated before the tool's availability check, so argv admission stays observable even though the call cannot ultimately run. An otherwise unscoped child still runs in a fresh neutral temporary cwd, not the gateway repository. All other caller-controlled argv values are admitted in their final encoded form before spawn. Embedded NUL bytes return non-retryableinvalid_inputwithout exposing the rejected value. New and resumed stdin requests complete only after the full payload write callback succeeds; a clean child exit with closed or pending delivery is a fixed non-sensitive failure.
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.
- yesterday Changed b8b285f72fb9
- 5d ago First seen · 159 lines · 73 tokens per session scan A d33a13c26d0a
provider-codex is a skill published in the GitHub repository verivus-oss/llm-cli-gateway (15 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 2,267 once invoked, about $0.0004 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
architecture
Project architecture and file structure conventions for all process types. Use when: (1) Creating new files or modules, (2) Deciding where code should go, (3) Converting single-file components to directories, (4) Reviewing code for structure compliance, (5) Adding new bridges, services, agents, or workers.
testing
Testing workflow and quality standards for writing and running tests. Use when: (1) Writing new tests, (2) Adding a new feature that needs tests, (3) Modifying logic that has existing tests, (4) Before claiming a task is complete.
deep-execution
Executes agent-enhanced council queries as one Workflow of parallel Claude analyst agents that each query a provider, evaluate response quality, ask follow-up questions, and return a schema-enforced analysis with confidence ratings and blind spot analysis. Invoked when the --agents flag is used or when complex…
bug-audit
Weekly multi-agent audit for serious bugs (data integrity, silent caps, staleness, timestamp math, trust boundaries). Fans out Sonnet scanners + Opus deep auditors, adversarially verifies every finding, files GitHub issues for confirmed critical/high bugs. Trigger: /bug-audit.
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.