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 Boulea7/agy-mcp --skill claudegit clone --depth 1 https://github.com/Boulea7/agy-mcpWrote 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/boulea7/agy-mcp/claude)<a href="https://agentmods.dev/skills/boulea7/agy-mcp/claude"><img src="https://agentmods.dev/badge/skills/boulea7/agy-mcp/claude/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/boulea7/agy-mcp/claude"><img src="https://agentmods.dev/badge/skills/boulea7/agy-mcp/claude.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 | $0.00067 | $0.01002 |
| Opus 5 | $0.00034 | $0.00501 |
| Sonnet 5 | $0.00013 | $0.00200 |
| Haiku 4.5 | $0.00007 | $0.00100 |
Grade A, and why
collaborating-with-antigravity 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 9d 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.
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.
This is a copy
100% identical to collaborating-with-antigravity — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Collaborating with Antigravity
agy-bridge is a thin JSON wrapper around the Google Antigravity (agy)
CLI plus an optional gemini CLI fallback. It produces stable
BridgeResponse envelopes so this skill can drive Antigravity sessions
deterministically.
When to use
- You need a second opinion on a debugging hypothesis or a code review.
- You need to prototype a change in isolation (auto-worktree).
- You need to run a long agent loop (planning, large refactors) without blocking your own conversation: start a background job and poll.
- You want a sandboxed execution of code Antigravity proposes.
Do not use for trivial one-shot questions — the round-trip overhead is not worth it. Prefer direct work for those.
Quick start
# One-shot synchronous call (ask mode, no write):
python scripts/agy_bridge.py \
--cd "/path/to/project" \
--PROMPT "Explain the auth flow in src/auth/"
Output is a single JSON line on stdout: {"success": true, "SESSION_ID": "…", "agent_messages": "…", "adapter": {…}, …}.
Modes
--mode controls the agent persona and downstream safety policy:
| Mode | Use it for | Worktree? | Writes? |
|---|---|---|---|
ask (default) |
Q&A, code reading, design discussion | no | no |
plan |
Multi-step planning, breakdown | no | no |
prototype |
Generate diffs for review | optional | no |
review |
Code review of staged changes | no | no |
execute |
Make file edits in the workspace | yes | requires --allow-write |
browser |
Interactive browsing / research | no | no |
long |
Multi-hour agent loop, expect to poll status | no | no |
execute always creates a worktree by default; combine with
--allow-write to opt in to mutations. The worktree default is
configurable in ~/.config/agy-mcp/config.toml (see references/security.md).
Multi-turn
Capture SESSION_ID from the first response, then pass it back:
# Turn 1
python scripts/agy_bridge.py --cd "/proj" --PROMPT "Analyse src/auth/"
# → {"SESSION_ID": "abc-123", "agent_messages": "…"}
# Turn 2 (continues the same conversation)
python scripts/agy_bridge.py --cd "/proj" --SESSION_ID abc-123 \
--PROMPT "Now propose a refactor."
What ships with it
4 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.
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.
- 9d ago First seen · 105 lines · 67 tokens per session scan A cbe894007eb2
collaborating-with-antigravity is a skill published in the GitHub repository Boulea7/agy-mcp (23 stars, last pushed 27d ago), licensed MIT. It adds 67 tokens to every session and 1,002 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to collaborating-with-antigravity, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
crosstalk
Consult Antigravity (Gemini) from Claude Code without blocking, and route the answer to whichever of your sessions needs it. Use for wide-context reads a second model should carry (large codebase sweeps, long log or transcript analysis, broad web research), for a genuine second opinion on a design or a diagnosis, and…
agy-result-handling
Internal guidance for presenting agy output back to the user.
gemini-3-prompting
Guidance for writing effective prompts for Antigravity (agy) / Gemini 3 models.
agy-delegation
Use when analyzing large files (>200 lines), more than 3 files at once, deep git/grep searches, web lookups, or adversarial reviews - delegates to the Antigravity CLI via claude-agy-mcp MCP tools to save context.
ag-sdd
Activates the Anti-Gravity Spec-Driven Development (ag-sdd) workflow. Use this skill when the user asks to implement a feature, fix a bug, or write code in a repository that uses ag-sdd. It enforces a strict 4-phase SDD lifecycle: Discovery, Spec Generation, Sequential Execution, and Quality Signoff.
delegate
Use when the user wants to delegate a task to Google's Antigravity desktop app — phrases like "use gemini", "ask antigravity", "have claude in antigravity do this", "offload this", "run N agents/tasks in parallel", or "check antigravity's quota". Explains which model to pick, when to use the batch/parallel tool, and…