diff --git a/AGENTS.md b/AGENTS.md
index 69651022d..1e3c88503 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -62,7 +62,7 @@ Invoke them by name (e.g., `/office-hours`).
 | `/retro` | Weekly retro with per-person breakdowns and shipping streaks. |
 | `/health` | Code quality dashboard (type checker, linter, tests, dead code). |
 | `/benchmark` | Performance regression detection (page load, Core Web Vitals). |
-| `/benchmark-models` | Cross-model benchmark for skills (Claude, GPT, Gemini side-by-side). |
+| `/benchmark-models` | Cross-model benchmark for skills (Claude, GPT, Gemini, and Agy side-by-side). |
 | `/cso` | OWASP Top 10 + STRIDE security audit. |
 | `/setup-gbrain` | Set up gbrain for cross-machine session memory sync. |
 | `/sync-gbrain` | Keep gbrain current with this repo's code; refresh agent search guidance in CLAUDE.md. |
diff --git a/CLAUDE.md b/CLAUDE.md
index 984844902..8bca27893 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -95,7 +95,7 @@ gstack/
 │   ├── claude.ts    # Primary host config
 │   ├── codex.ts, factory.ts, kiro.ts  # Existing hosts
 │   ├── opencode.ts, slate.ts, cursor.ts, openclaw.ts  # IDE hosts
-│   ├── hermes.ts, gbrain.ts  # Agent runtime hosts
+│   ├── hermes.ts, gbrain.ts, agy.ts  # Agent runtime hosts
 │   └── index.ts     # Registry: exports all, derives Host type
 ├── scripts/         # Build + DX tooling
 │   ├── gen-skill-docs.ts  # Template → SKILL.md generator (config-driven)
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index b75d4a898..65d6320ba 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -308,11 +308,11 @@ worth the review overhead.
 
 ## Multi-host development
 
-gstack generates SKILL.md files for 8 hosts from one set of `.tmpl` templates.
+gstack generates SKILL.md files for 11 hosts from one set of `.tmpl` templates.
 Each host is a typed config in `hosts/*.ts`. The generator reads these configs
 to produce host-appropriate output (different frontmatter, paths, tool names).
 
-**Supported hosts:** Claude (primary), Codex, Factory, Kiro, OpenCode, Slate, Cursor, OpenClaw.
+**Supported hosts:** Claude (primary), Codex, Factory, Kiro, OpenCode, Slate, Cursor, OpenClaw, Hermes, GBrain, and Agy.
 
 ### Generating for all hosts
 
@@ -321,7 +321,8 @@ to produce host-appropriate output (different frontmatter, paths, tool names).
 bun run gen:skill-docs                    # Claude (default)
 bun run gen:skill-docs --host codex       # Codex
 bun run gen:skill-docs --host opencode    # OpenCode
-bun run gen:skill-docs --host all         # All 8 hosts
+bun run gen:skill-docs --host agy         # Google Antigravity
+bun run gen:skill-docs --host all         # All 11 hosts
 
 # Or use build, which does all hosts + compiles binaries
 bun run build
diff --git a/README.md b/README.md
index 4bb177c3a..574b048e0 100644
--- a/README.md
+++ b/README.md
@@ -101,7 +101,7 @@ These are conversational skills. Your OpenClaw agent runs them directly via chat
 
 ### Other AI Agents
 
-gstack works on 10 AI coding agents, not just Claude. Setup auto-detects which
+gstack works on 11 AI coding agents, not just Claude. Setup auto-detects which
 agents you have installed:
 
 ```bash
@@ -121,10 +121,13 @@ Or target a specific agent with `./setup --host <name>`:
 | Kiro | `--host kiro` | `~/.kiro/skills/gstack-*/` |
 | Hermes | `--host hermes` | `~/.hermes/skills/gstack-*/` |
 | GBrain (mod) | `--host gbrain` | `~/.gbrain/skills/gstack-*/` |
+| Google Antigravity (Agy) | `--host agy` | `~/.gemini/config/plugins/gstack/skills/` |
 
 **Want to add support for another agent?** See [docs/ADDING_A_HOST.md](docs/ADDING_A_HOST.md).
 It's one TypeScript config file, zero code changes.
 
+For Agy plugin registration and model benchmarking, see the [Agy integration guide](docs/AGY.md).
+
 ## See it work
 
 ```
@@ -241,7 +244,7 @@ Beyond the slash-command skills, gstack ships standalone CLIs for workflows that
 
 | Command | What it does |
 |---------|-------------|
-| `gstack-model-benchmark` | **Cross-model benchmark** — run the same prompt through Claude, GPT (via Codex CLI), and Gemini; compare latency, tokens, cost, and (optionally) LLM-judge quality score. Auth detected per provider, unavailable providers skip cleanly. Output as table, JSON, or markdown. `--dry-run` validates flags + auth without spending API calls. |
+| `gstack-model-benchmark` | **Cross-model benchmark** — run the same prompt through Claude, GPT (via Codex CLI), Gemini, and Agy; compare latency, tokens, cost, and (optionally) LLM-judge quality score. Auth detected per provider, unavailable providers skip cleanly. Output as table, JSON, or markdown. `--dry-run` validates flags + auth without spending API calls. See the [Agy integration guide](docs/AGY.md) for Agy setup. |
 | `gstack-taste-update` | **Design taste learning** — writes approvals and rejections from `/design-shotgun` into a persistent per-project taste profile. Decays 5%/week. Feeds back into future variant generation so the system learns what you actually pick. |
 | `gstack-ios-qa-daemon` | **iOS QA daemon** — Mac-side broker between an agent and a connected iPhone over USB CoreDevice. Loopback by default; `--tailnet` opens a Tailscale-facing listener with identity-gated capability tiers. Single-instance via flock on `~/.gstack/ios-qa-daemon.pid`. See [docs/howto-ios-testing-with-gstack.md](docs/howto-ios-testing-with-gstack.md). |
 | `gstack-ios-qa-mint` | **iOS allowlist manager** — owner-grant CLI for the tailnet allowlist. `grant`/`revoke`/`list` against `~/.gstack/ios-qa-allowlist.json` (mode 0600). Remote agents never auto-allowlist; this is the explicit-intent path. |