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 contrapuntal/antigravity-cli-plugin-cc --skill antigravity-helpergit clone --depth 1 https://github.com/contrapuntal/antigravity-cli-plugin-ccWrote 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/contrapuntal/antigravity-cli-plugin-cc/antigravity-helper)<a href="https://agentmods.dev/skills/contrapuntal/antigravity-cli-plugin-cc/antigravity-helper"><img src="https://agentmods.dev/badge/skills/contrapuntal/antigravity-cli-plugin-cc/antigravity-helper.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.01996 |
| Opus 5 | $0.00035 | $0.00998 |
| Sonnet 5 | $0.00014 | $0.00399 |
| Haiku 4.5 | $0.00007 | $0.00200 |
Grade C, and why
antigravity-helper scanned grade C with 2 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 8d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- **`agy` CLI 1.0.7 or later, installed and authenticated.** Install with `curl -fsSL https://antigravity.google/cli/install.sh | bash` or `brew install --cask antigravity-cli` (agy is not distributed via npm). Older agy Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **`agy` CLI 1.0.7 or later, installed and authenticated.** Install with `curl -fsSL https://antigravity.google/cli/install.sh | bash` or `brew install --cask antigravity-cli` (agy is not distributed via npm). Older agy How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
antigravity-helper
This skill lets any Anthropic-Skill-aware agent (Codex CLI, OpenCode, Pi.dev, plus Claude Code via .claude/skills/) delegate to the Antigravity CLI (agy) for code review and task analysis. It wraps the antigravity-cli-plugin-cc companion script — a stateless Node.js dispatcher that assembles the prompt, writes it to a temp workspace directory, applies read-only or write-capable execution, runs agy in print mode, and extracts the marker-wrapped response so agy's tool-use narration never reaches the user.
If you are running inside Claude Code, prefer the slash-command surface (
/ask-antigravity:review,/ask-antigravity:adversarial-review,/ask-antigravity:rescue,/ask-antigravity:setup) provided by the antigravity-cli-plugin-cc plugin. This skill is the portable fallback for agents without that plugin format.
Prerequisites
agyCLI 1.0.7 or later, installed and authenticated. Install withcurl -fsSL https://antigravity.google/cli/install.sh | bashorbrew install --cask antigravity-cli(agy is not distributed via npm). Older agy hangs in headless print mode; the companion refuses to invoke it and asks for an upgrade. Sign in by runningagyinteractively and completing Google sign-in, or setANTIGRAVITY_API_KEYin the environment.node18.18 or later on PATH.ANTIGRAVITY_CLI_PLUGIN_CC_ROOTenv var pointing at the absolute path of the clonedantigravity-cli-plugin-ccrepository. If that variable is unset, ask the user for the path before running the companion.- Workspace trust. If
agyhas not been interactively trusted in the directory you invoke it from, trust the workspace in agy (it recordstrustedWorkspacesin itssettings.json). Without trust, headlessagymay refuse to proceed.
When to invoke this skill
Trigger on requests that match any of:
- "review my changes / diff / branch with Antigravity"
- "challenge this design choice / pressure-test this implementation"
- "ask Antigravity to investigate / analyze / fix X"
- "give me a second opinion on…" (especially when the question benefits from a large-context single pass)
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.
- 8d ago First seen · 109 lines · 70 tokens per session scan C de7348f5c684
antigravity-helper is a skill published in the GitHub repository contrapuntal/antigravity-cli-plugin-cc (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,996 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
8eyes
Multi-agent adversarial code review via eight-eyes enforcement kernel.
hunt
Finds root cause of errors, crashes, unexpected behavior, and failing tests before applying any fix. Not for code review or new features.
verify-change
A change-checking skill that reviews code differences and checks whether related documentation, tests, and records were updated.
verify-quality
A code-quality checker that measures complexity, size, naming, and common code smells. It reports problems such as duplicated code, unused code, and overly long functions.
code-review-excellence
This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.
agtx-review
Self-review completed work. Check for correctness, edge cases, and code quality. Write review to .agtx/review.md and stop.