Skip to content

CowboyLogic/ai-dev / skills/client-config-codex

client-config-codex

Flagged

Manage OpenAI Codex CLI configuration files including config.toml, project .codex/config.toml, profiles, model providers, sandbox and approval settings, permission profiles, rules files, MCP servers, hooks, skills, plugins, custom agents, AGENTS.md instructions, and requirements.toml. Use this skill whenever the user wants to view, edit, add, or understand any Codex setting: trusted projects, approval policy, sandbox mode, network access, allow-listing commands, MCP servers, hooks, skills, plugins and marketplaces, model or reasoning effort, custom model providers, authentication, sessions, or AGENTS.md. Trigger on: "configure codex", "codex config.toml", "trust this project in codex", "codex approval policy", "codex sandbox", "add MCP server to codex", "codex hook", "codex rules", "codex profile", "codex plugin", "set codex model", "codex AGENTS.md", or "show my codex config".

FileKindSize
README.mdmarkdown3.0 KB
SKILL.mdskill md8.9 KB
references/agents-plugins.mdmarkdown12.8 KB
references/cli-commands.mdmarkdown21.2 KB
references/config-schema.mdmarkdown43.0 KB
references/hooks.mdmarkdown17.0 KB
references/instructions.mdmarkdown7.5 KB
references/mcp.mdmarkdown12.9 KB
references/permissions.mdmarkdown23.9 KB
references/skills.mdmarkdown6.6 KB
scripts/show-config.pyscript19.1 KB
scripts/update-references.pyscript6.8 KB
sources.jsonconfig3.8 KB

sources.json

View on GitHub
{
  "_comment": "Source URLs for this skill's reference files. Run scripts/update-references.py to refresh. Every page is fetched as Markdown through the learn.chatgpt.com '.md' twin of the page URL (developers.openai.com/codex/... redirects there).",
  "index": "https://learn.chatgpt.com/llms.txt",
  "references": {
    "references/config-schema.md": {
      "urls": [
        "https://learn.chatgpt.com/docs/config-file/config-basic.md",
        "https://learn.chatgpt.com/docs/config-file/config-advanced.md",
        "https://learn.chatgpt.com/docs/config-file/config-reference.md",
        "https://learn.chatgpt.com/docs/config-file/config-sample.md",
        "https://learn.chatgpt.com/docs/config-file/environment-variables.md",
        "https://learn.chatgpt.com/docs/model-selection.md",
        "https://learn.chatgpt.com/docs/auth.md",
        "https://learn.chatgpt.com/docs/enterprise/managed-configuration.md"
      ],
      "covers": "CODEX_HOME layout, config.toml layers and precedence, profiles, project trust, top-level keys, model providers, features, notifications, telemetry, requirements.toml and managed configuration, environment variables, authentication"
    },
    "references/permissions.md": {
      "urls": [
        "https://learn.chatgpt.com/docs/agent-approvals-security.md",
        "https://learn.chatgpt.com/docs/permission-modes.md",
        "https://learn.chatgpt.com/docs/permissions.md",
        "https://learn.chatgpt.com/docs/sandboxing.md",
        "https://learn.chatgpt.com/docs/sandboxing/auto-review.md",
        "https://learn.chatgpt.com/docs/agent-configuration/rules.md"
      ],
      "covers": "sandbox_mode and approval_policy, permission profiles, filesystem and network access, protected paths, auto-review, rules files (.rules) and prefix_rule, trusted projects"
    },
    "references/cli-commands.md": {
      "urls": [
        "https://learn.chatgpt.com/docs/developer-commands.md?surface=cli",
        "https://learn.chatgpt.com/docs/cli-customization.md",
        "https://learn.chatgpt.com/docs/notifications.md"
      ],
      "covers": "Terminal subcommands, command-line options, -c overrides, sessions (resume, fork, archive, delete), slash commands, CLI customization"
    },
    "references/mcp.md": {
      "urls": [
        "https://learn.chatgpt.com/docs/extend/mcp.md?surface=cli"
      ],
      "covers": "[mcp_servers.<name>] tables in config.toml, STDIO and streamable HTTP transports, OAuth, tool filtering, timeouts, codex mcp commands"
    },
    "references/hooks.md": {
      "urls": [
        "https://learn.chatgpt.com/docs/hooks.md"
      ],
      "covers": "Hook sources (hooks.json and config.toml), file format, handler types, events, matchers, input payloads, decision output, trust and review of hooks, debugging"
    },
    "references/skills.md": {
      "urls": [
        "https://learn.chatgpt.com/docs/build-skills.md"
      ],
      "covers": "SKILL.md format, skill locations and precedence, agents/openai.yaml metadata, enabling and disabling skills, invocation"
    },
    "references/agents-plugins.md": {
      "urls": [
        "https://learn.chatgpt.com/docs/agent-configuration/subagents.md",
        "https://learn.chatgpt.com/docs/plugins.md",
        "https://learn.chatgpt.com/docs/build-plugins.md"
      ],
      "covers": "Subagents and the [agents] table, custom agent TOML files, plugins, marketplaces, the ChatGPT no-code plugin guide (build-plugins.md is not the plugin.json or marketplace schema; those and the codex plugin commands come from cli-commands.md and config-schema.md), [plugins.*] enablement"
    },
    "references/instructions.md": {
      "urls": [
        "https://learn.chatgpt.com/docs/agent-configuration/agents-md.md"
      ],
      "covers": "AGENTS.md and AGENTS.override.md discovery and layering, global instructions in CODEX_HOME, fallback filenames, project_doc_max_bytes"
    }
  }
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 470kUpdated Claude CodeCodexUnverifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall