mirror of https://github.com/garrytan/gstack.git
docs: document Agy host and benchmark support
This commit is contained in:
Mattias Petersson
parent
6e4ed2b292
commit
ea7b46d5a5
|
|
@ -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. |
|
||||
|
|
|
|||
|
|
@ -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)
|
||||
|
|
|
|||
|
|
@ -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
|
||||
|
|
|
|||
|
|
@ -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. |
|
||||
|
|
|
|||
Loading…
Reference in New Issue