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 agentmods add skills/boulea7/agy-mcp/codexnpx skills add Boulea7/agy-mcp --skill codexgit 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/codex)<a href="https://agentmods.dev/skills/boulea7/agy-mcp/codex"><img src="https://agentmods.dev/badge/skills/boulea7/agy-mcp/codex.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 | $0.00071 | $0.00869 |
| Opus 5 | $0.00036 | $0.00434 |
| Sonnet 5 | $0.00014 | $0.00174 |
| Haiku 4.5 | $0.00007 | $0.00087 |
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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Collaborating with Antigravity (Codex edition)
agy-bridge is a thin JSON wrapper around the Google Antigravity (agy)
CLI plus a gemini CLI fallback. The bridge returns stable
BridgeResponse envelopes designed to drop cleanly into Codex's
exec-json protocol via --output-protocol codex.
When to use
- You want a second opinion from Antigravity / Gemini on a tricky bug, design call, or code review.
- You want to prototype a change in an isolated worktree before touching the main checkout.
- You want a long-running agent loop to run in the background while Codex continues other work.
Avoid for trivial single-step questions — the round-trip is overkill.
Quick start
python scripts/agy_bridge.py \
--cd "/path/to/project" \
--PROMPT "Find every place that calls db.commit() without a try/except." \
--mode review \
--output-protocol codex
The bridge prints one JSON line on stdout: {"success": true, "SESSION_ID": "…", "agent_messages": "…", "adapter": {…}}. With
--output-protocol codex the event log conforms to Codex exec-json
(thread.started, item.completed, turn.completed).
Modes
| Mode | Use it for | Worktree | Writes |
|---|---|---|---|
ask (default) |
Q&A, code reading | no | no |
plan |
Multi-step planning | no | no |
prototype |
Diff-only suggestions | optional | no |
review |
Critique a staged change | no | no |
execute |
Apply edits in a worktree | yes | requires --allow-write |
browser |
Research with browsing | no | no |
long |
Detached agent loop | no | varies |
Multi-turn
Capture and reuse SESSION_ID:
# Turn 1
python scripts/agy_bridge.py --cd /proj --PROMPT "Find race conditions in src/queue/"
# → {"SESSION_ID": "abc-123", ...}
# Turn 2
python scripts/agy_bridge.py --cd /proj --SESSION_ID abc-123 \
--PROMPT "Propose a minimal fix for the worst one."
Detached long jobs
Codex projects that run long agent loops should prefer the MCP tool
surface (agy_start / agy_status / agy_result / agy_read /
agy_cancel / agy_sessions) over polling the CLI in a shell loop. The supervisor
handles worker thread lifecycle, log spooling, and cross-platform
process-group cleanup.
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.
- 4d ago First seen · 95 lines · 71 tokens per session scan A e79b2a5b9990
collaborating-with-antigravity is a skill published in the GitHub repository Boulea7/agy-mcp (22 stars, last pushed 22d ago), licensed MIT. It adds 71 tokens to every session and 869 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
antigravity-cli
Internal runtime contract for invoking the Antigravity CLI (agy) from the agy subagent. Not user-invocable.
agy-cli-runtime
Internal helper contract for calling the agy-companion runtime from Claude Code.
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…
gemini-3-prompting
Guidance for writing effective prompts for Antigravity (agy) / Gemini 3 models.
agy-result-handling
Internal guidance for presenting agy output back to the user.
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.