Borrowing it
Nothing to install: this file belongs to Reedtrullz/codex-antigravity-auth. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Reedtrullz/codex-antigravity-auth/main/AGENTS.mdgit clone --depth 1 https://github.com/Reedtrullz/codex-antigravity-authWrote 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/instructions/reedtrullz/codex-antigravity-auth/agents-md)<a href="https://agentmods.dev/instructions/reedtrullz/codex-antigravity-auth/agents-md"><img src="https://agentmods.dev/badge/instructions/reedtrullz/codex-antigravity-auth/agents-md/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/instructions/reedtrullz/codex-antigravity-auth/agents-md"><img src="https://agentmods.dev/badge/instructions/reedtrullz/codex-antigravity-auth/agents-md.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 | $0.01193 | $0.01193 |
| Opus 5.5 | $0.00477 | $0.00477 |
| Sonnet 5.5 | $0.00239 | $0.00239 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade B, and why
codex-antigravity-auth AGENTS.md scanned grade B with 1 finding 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 10d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.codex/config.toml`: How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Codex Antigravity Auth
Start at STATUS.md for current source contracts and evidence boundaries. Historical release claims are preserved in the dated archive; they are not proof for this checkout.
Dated review snapshot: The 2026-10-04 source review and its validation-copy inventory are archived in docs/history/2026-10-04. They describe an older checkout (
027fd313b1f6, package 2.4.2); equal package versions do not establish equal source.
Guidance for AI coding agents (Codex, Claude Code, OpenCode, etc.) working on this project.
Overview
Local gateway server that allows OpenAI Codex (CLI and Desktop) to use Google Antigravity models (Gemini 3.8/3.7/3.1, Claude Sonnet/Opus 4.6) via Google OAuth PKCE and multi-account rotation, plus BYOK OpenAI-compatible providers such as OpenRouter, DeepSeek, xAI, Kimi/Moonshot, Ollama, and OpenCode-compatible endpoints.
Newer models are registered but plan-gated: Gemini 4 Argon (Ultra/Enterprise; the docs list it as not available in Antigravity IDE, which is the client identity this gateway presents) and Claude Sonnet/Opus 5.5 (paid, non-trial Pro or Ultra plans). Their backend wire ids are unverified and they were not offered to the Jio-provided Google AI Pro accounts checked on 2026-10-15. Per Google's in-API notice, third-party model access (Claude 4.6, GPT-OSS) ends on non-paid plans on 2026-11-02, so the anti skill defaults to Gemini 3.8 Flash.
Architecture
STATUS.md maps Google, native OpenAI and BYOK routes to their owning modules. Use the central capability catalog for model aliases/families and adapter support; do not infer support from names or duplicate a model registry in docs.
Key Conventions
- Python 3.10+ — use
python3or activate venv - Virtual env:
source .venv/bin/activate - Install:
uv pip install -e . - Test:
python3 scripts/run_tests.py -q(isolates credentials/state and denies non-fixture sockets before pytest startup; all tests must pass) - Run server:
codex-antigravity start --port 51122 - Credentials:
~/.codex/antigravity-credentials.jsonor env vars - Accounts:
~/.codex/antigravity-accounts.json(Fernet-encrypted) - BYOK providers:
~/.codex/antigravity-providers.json(Fernet-encrypted) or provider API key env vars
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.
- 10d ago Changed · +17 tokens per session a877c07c583e
- 13d ago Changed · +4 lines · +208 tokens per session fe938190920a
- 25d ago Changed · -44 lines · -664 tokens per session 20fa2b07b9b3
- 1mo ago Changed · -44 tokens per session 7ad575e7eac4
- 1mo ago Changed · +71 tokens per session 3934ebe10a81
- 1mo ago Changed · +38 tokens per session b988232f346b
- 1mo ago Changed · +1 lines · +31 tokens per session 446dc6383271
- 1mo ago First seen · 119 lines · 1,536 tokens per session scan B 5ebd369f72e8
codex-antigravity-auth AGENTS.md is an instructions file published in the GitHub repository Reedtrullz/codex-antigravity-auth (2 stars, last pushed 5d ago), licensed MIT. It adds 1,193 tokens to every session, about $0.0048 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.