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 tamnguyendinh/Anvien --skill antigravity-call-codexgit clone --depth 1 https://github.com/tamnguyendinh/AnvienWrote 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/tamnguyendinh/anvien/antigravity-call-codex)<a href="https://agentmods.dev/skills/tamnguyendinh/anvien/antigravity-call-codex"><img src="https://agentmods.dev/badge/skills/tamnguyendinh/anvien/antigravity-call-codex/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/tamnguyendinh/anvien/antigravity-call-codex"><img src="https://agentmods.dev/badge/skills/tamnguyendinh/anvien/antigravity-call-codex.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 | $0.00035 | $0.00575 |
| Opus 5 | $0.00017 | $0.00287 |
| Sonnet 5 | $0.00007 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade B, and why
antigravity-call-codex 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
* **Windows Path:** `C:\Users\<USER>\.gemini\config\mcp_config.json` (shorthand: `~/.gemini/config/mcp_config.json`) How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integrate Codex into Antigravity via Native MCP
Purpose
Enable Antigravity and other AI agents to delegate end-to-end technical tasks to Codex to execute directly on the repository via the Model Context Protocol (MCP).
Codex possesses full tools to read/write files and execute shell commands, autonomously closing the self-repair loop (edit → build → test → pass) directly on the repository without requiring the host agent to act as an intermediary for copying and pasting code.
1. Local Global MCP Configuration (One-time Setup)
To make the MCP Server active across all workspaces on this machine, declare it in Antigravity's Global configuration file:
- Windows Path:
C:\Users\<USER>\.gemini\config\mcp_config.json(shorthand:~/.gemini/config/mcp_config.json) - Configuration Content (YOLO Mode - Full execution permissions for Codex):
{
"mcpServers": {
"codex": {
"command": "codex.cmd",
"args": [
"--dangerously-bypass-approvals-and-sandbox",
"--dangerously-bypass-hook-trust",
"mcp-server"
]
}
}
}
- Verify Status: In the Antigravity UI, navigate to Additional Options (
...) > MCP Servers to confirmcodexshows a connected state with 2 tools:codexandcodex-reply.
2. Execution via Dispatcher Script
To trigger Codex immediately without manual protocol handling, run the dispatcher script from the repository root:
# In Antigravity / Codex:
python .agents/skills/antigravity-call-codex/scripts/call_codex.py -p "<task description>"
# In Claude Code:
python .claude/skills/antigravity-call-codex/scripts/call_codex.py -p "<task description>"
Flags:
-p,--prompt: Detailed task description for Codex (required).-c,--cwd: Working directory root for Codex (optional, defaults to current working directory).
3. Direct MCP Native Tool Call (Alternative)
If the active environment provides native MCP tool calling directly:
- ServerName:
codex - ToolName:
codex - Arguments:
What ships with it
1 file 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.
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 · 74 lines · 35 tokens per session scan B 72cb2fc8b803
antigravity-call-codex is a skill published in the GitHub repository tamnguyendinh/Anvien (9 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 575 once invoked, about $0.0002 per session on Opus 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 2026-09-12.
Other skills, from other repositories
react-web
React web development with hooks, React Query, Zustand.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
test-driven-development
Enforces TDD discipline with RED-GREEN-REFACTOR cycle. Use when writing new features, fixing bugs, or refactoring code. Ensures tests genuinely verify behavior.
tdd-cycle
Execute full TDD red-green-refactor cycle with validation gates. Use when saying "TDD cycle", "test-driven development", or "full TDD workflow".
ring:running-dev-cycle
Running the backend dev cycle: implements every task in a rolling-wave plan.md (ring:writing-plans format) for a Go/TS service, driving specialist agents through Gate 0 implementation/TDD, Gate 8 parallel review, and Gate 9 validation per epic, elaborating later phases at each phase boundary. Use when starting or…
ring:instrumenting-streaming-events
Instrumenting streaming events: wires lib-streaming event emission end-to-end into a Lerian Go service via a 13-gate cycle (catalog, Builder bootstrap, Emit sites, outbox, HTTP manifest, NoopEmitter fallback, integration and chaos tests), dispatching ring:backend-go under TDD. Consumes the validated…