claude-codex-settings is a collection of configurations and reusable extensions for Claude Code, OpenAI Codex, Cursor, and related coding tools. Developers use its skills, commands, hooks, agents, plugins, and MCP servers to shape coding-agent workflows and connect alternative model APIs. The catalogue entries are components of this collection that can be installed into supported coding tools.
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 fcakyon/claude-codex-settings --skill app-authgit clone --depth 1 https://github.com/fcakyon/claude-codex-settingsWrote 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/fcakyon/claude-codex-settings/app-auth)<a href="https://agentmods.dev/skills/fcakyon/claude-codex-settings/app-auth"><img src="https://agentmods.dev/badge/skills/fcakyon/claude-codex-settings/app-auth/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/fcakyon/claude-codex-settings/app-auth"><img src="https://agentmods.dev/badge/skills/fcakyon/claude-codex-settings/app-auth.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00083 | $0.00668 |
| Opus 5.5 | $0.00033 | $0.00267 |
| Sonnet 5.5 | $0.00017 | $0.00134 |
| Haiku 4.5 | $0.00008 | $0.00067 |
Grade A, and why
app-auth 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 today.
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 — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App authentication
Provide a short returning-user path and a dependable same-tab path. Google and the browser decide whether account selection or reauthentication is required. Do not promise silent login or call a flow fastest without measurements.
- Inspect login, signup, email verification, recovery, session, logout, account linking and authorization. Identify the selected action, locales, design system and registered Google callback.
- Read integration. For React 19.2+, adapt GoogleSignIn.tsx and its styles. Use the optional AuthPanel with panel styles for a Muvisafe-inspired shell. Other frameworks should implement the same contract using their own lifecycle primitives.
- For email/password flows, adapt EmailAuth.tsx and email styles. Read the email adapter section in the integration contract. Use email-design for messages sent by those flows.
- Keep the official Google button with FedCM auto-selection for a remembered account. Always offer a normal same-tab link. GIS sign-in does not provide the OAuth authorization client's
error_callback. Do not invent popup-failure detection, retry timers or user-agent rules. - Resolve return navigation in the auth owner. Both paths must use the same account/session policy, then resume the action once. Only the backend verifies identity and authorizes access.
- Run the applicable journeys through the project's existing QA harness. Keep fixture results, real Google evidence and deployed behavior distinct.
- Record the app commit, runtime versions and actual evidence in its existing tracked guidance. Change the shared recipe only when new evidence changes a shared rule.
The app owns script loading, public client configuration, remembering the successful Google account, sessions, error reporting and navigation. The component owns rendering, pending/error UI and cancelling its credential operation when the auth surface closes.
For architecture standardization, read backend standard. It is a proposed target, not an implemented Go dependency or completed migration.
For web/native/TV clients or another social provider, read platforms and providers. Use one identity store and revocation model per product across its clients. Keep browser cookies and native secure-storage transport distinct.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/auth-panel.css 1.3 KB
- assets/AuthPanel.tsx 672 B
- assets/email-auth.css 2.1 KB
- assets/EmailAuth.tsx 8.9 KB
- assets/google-sign-in.css 809 B
- assets/GoogleSignIn.tsx 3.5 KB
- references/backend-standard.md 5.1 KB
- references/integration.md 12 KB
- references/journeys.md 4.1 KB
- references/platforms.md 7.0 KB
- references/provenance.md 2.6 KB
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.
- today First seen · 27 lines · 83 tokens per session scan A d1a1158af617
app-auth is a skill published in the GitHub repository fcakyon/claude-codex-settings (1,192 stars, last pushed today), licensed Apache-2.0. It adds 83 tokens to every session and 668 once invoked, about $0.0003 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 2026-10-29.
Other skills, from other repositories
lov-optimize-tauri-backend
Optimize Tauri backend architecture and development ergonomics for Tauri 2 apps, especially Rust restart pain, oversized src-tauri/src/lib.rs files, excessive #[tauri::command] surfaces, stringly invoke APIs, long IPC streams, and dev-state recovery. Use when the user asks about Tauri hot reload, Rust-side restarts…
lov-cli-creator
A tool-building workflow that turns a local project into an installable command-line program. The program exposes the project's real backend, returns predictable JSON, documents how it works, and includes runnable tests.
lov-cli2anything
A tool for turning authorized observations of a website’s API into an OpenAPI description, Swagger interface, JavaScript SDK, or local command-line tool. OpenAPI is a machine-readable description of how an API can be called.
lov-api-creator
A development workflow for adding an app's API gateway support to a uni-api FastAPI backend and its uni-app frontend. It creates grouped gateway endpoints and a shared frontend calling layer.
lov-integrate-lovstudio-llm-skill
An integration with LovStudio.AI’s OpenAI-compatible API for text chat, speech-to-text, speech translation, speech generation, and live audio sessions. It returns structured results that other application code can use.
lov-backend
A backend workflow for adding an app's API gateway endpoints to a uni-api project built with FastAPI. It creates the app's package and router, registers them, and places the endpoints in a documented group.