provider-codex

provider-codex is a skill for Claude Code, Codex from verivus-oss/llm-cli-gateway. It costs 73 tokens per session (2,267 once invoked), scanned A, original, MIT.

A maintenance guide for keeping an OpenAI Codex command-line tool's integration aligned with its upstream release contract. The contract describes supported flags, sandbox and approval modes, session continuation, and output structure.

In plain words
What is it for?
It is for checking release changes and investigating contract-check failures for Codex requests.
Why use it?
It helps detect when a Codex CLI release could make the gateway's integration incorrect.

Skill for Claude CodeCodex

Part of the llm-gateway plugin — 24 skills, 4 commands, 2 MCP servers shipped together

Install

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.

agentmods
npx agentmods add skills/verivus-oss/llm-cli-gateway/provider-codex
Any agent
npx skills add verivus-oss/llm-cli-gateway --skill provider-codex
Clone the repo
git clone --depth 1 https://github.com/verivus-oss/llm-cli-gateway

Made for: Claude Code, Codex.

Or install llm-gateway, the plugin that ships this one along with the rest of its 24 skills, 4 commands, 2 MCP servers.

Wrote 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.

agentmods badge for provider-codex

README.md
[![agentmods](https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/provider-codex.svg)](https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/provider-codex)
Your own site
<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>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,267 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured yesterday against content hash b8b285f72fb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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.

.agents/skills/provider-codex/SKILL.md · 159 lines

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 codex request fails the upstream contract check before spawn.
  • npm run upstream:scan -- --live reports a change on the Codex release notes or changelog.

How LLM agents should use Codex through the gateway

  1. Discover the live gateway/provider surface before relying on Codex-specific controls:
    provider_tool_capabilities({cli:"codex"})
    
    For a cached read-only resource, use provider-tools://codex.
  2. Use codex_request for normal implementation/review turns and codex_request_async for long-running work. To continue an existing Codex conversation, pass codex_request a real Codex session UUID from ~/.codex/sessions/, or resumeLatest:true; both route through codex exec resume and work headlessly. codex_fork_session is registered but cannot run from the gateway: codex fork is interactive and requires a controlling terminal, and Codex exposes no non-interactive equivalent (codex exec has only resume/review/help). Re-check that on each Codex release; if a headless fork lands, codexForkCanRunHeadless in src/index.ts is the single predicate to flip.
  3. Omit model unless the caller explicitly asked for a specific variant; the gateway resolves the configured Codex default/profile.
  4. Prefer sandboxMode:"workspace-write" when Codex needs a writable workspace. fullAuto:true is the deprecated compatibility shorthand. Use approvalStrategy:"legacy": Codex rejects mcp_managed before launch because its ambient MCP configuration cannot be isolated, and approvalPolicy has no effect for Codex.
  5. Do not pass Claude-style allowedTools or disallowedTools; Codex does not expose those request fields through the gateway. Codex owns its MCP configuration, and a gateway mcpServers list is descriptive metadata, not an enforceable allowlist.
  6. Use sandboxMode, profile, configOverrides, oss, images, outputFormat, and outputSchema only as reported by provider_tool_capabilities. askForApproval and useLegacyFullAutoFlag are deprecated compatibility inputs: current Codex emits no corresponding argv and the gateway returns a warning. fullAuto:true remains a compatibility shorthand for sandboxMode:"workspace-write". These are provider-native legacy controls, not inputs to the Claude-only gateway approval boundary.
  7. Codex continuity is real through codex exec resume: pass a real Codex UUID from ~/.codex/sessions/, or resumeLatest:true. Gateway gw-* IDs are not Codex sessions. sandboxMode and its deprecated fullAuto:true shorthand are dropped on resume, so those fields cannot select a posture there. That is not a guarantee that the original posture is retained: configOverrides is not filtered and can set sandbox_mode, and Codex re-resolves configuration on a cold resume. resumeLatest is under review (#258): --last is cwd-filtered upstream unless --all is 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-native workingDir and addDir flags 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 verified workspace or gateway worktree can 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.
  8. 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_session uses the distinct codex fork contract, remains argv-bound, and rejects oversized UTF-8 prompts as non-retryable input_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-retryable invalid_input without 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.

Read the full file on GitHub · 159 lines

Changes

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.

  1. yesterday Changed b8b285f72fb9
  2. 5d ago First seen · 159 lines · 73 tokens per session scan A d33a13c26d0a

Subscribe to this mod's changes

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.

Related

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.

iOfficeAI/AionUi · 69 tokens

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.

iOfficeAI/AionUi · 55 tokens

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…

hex/claude-council · 66 tokens

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.

VasiHemanth/tokentelemetry · 0 tokens

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…

hex/claude-council · 74 tokens

architect

System design, tradeoffs, and complex technical decisions.

antonbabenko/deliberation · 13 tokens