oh-my-agent 5.15.0 → 5.18.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +30 -0
- package/bin/cli.js +635 -611
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -29,6 +29,20 @@ bunx oh-my-agent@latest
|
|
|
29
29
|
|
|
30
30
|
`install.sh` supports macOS/Linux only. On Windows, install `bun` and `uv` manually, then run `bunx oh-my-agent@latest`.
|
|
31
31
|
|
|
32
|
+
### Install via Agent Package Manager
|
|
33
|
+
|
|
34
|
+
> Microsoft's [Agent Package Manager](https://github.com/microsoft/apm) (APM) — not to be confused with `oma-observability`'s APM (Application Performance Monitoring).
|
|
35
|
+
|
|
36
|
+
```bash
|
|
37
|
+
# All 22 oma skills across every detected runtime (.claude, .cursor, .codex, .opencode, .github)
|
|
38
|
+
apm install first-fluke/oh-my-agent
|
|
39
|
+
|
|
40
|
+
# A single skill
|
|
41
|
+
apm install first-fluke/oh-my-agent/.apm/skills/oma-frontend
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
Installs the skills only. For hooks, workflows, and `oma-config.yaml`, use the `oh-my-agent` CLI above. Pick one distribution per project to avoid drift.
|
|
45
|
+
|
|
32
46
|
Pick a preset and you're ready:
|
|
33
47
|
|
|
34
48
|
| Preset | What You Get |
|
|
@@ -53,6 +67,7 @@ Pick a preset and you're ready:
|
|
|
53
67
|
| **oma-dev-workflow** | CI/CD, releases, monorepo automation |
|
|
54
68
|
| **oma-frontend** | React/Next.js, TypeScript, Tailwind CSS v4, shadcn/ui |
|
|
55
69
|
| **oma-hwp** | HWP/HWPX/HWPML to Markdown conversion |
|
|
70
|
+
| **oma-image** | Multi-vendor AI image generation |
|
|
56
71
|
| **oma-mobile** | Flutter cross-platform apps |
|
|
57
72
|
| **oma-observability** | Observability router — APM/RUM, metrics/logs/traces/profiles, SLO, incident forensics, transport tuning |
|
|
58
73
|
| **oma-orchestrator** | Parallel agent execution via CLI |
|
|
@@ -114,6 +129,21 @@ Model selection follows two layers:
|
|
|
114
129
|
- Same-vendor native dispatch uses the generated vendor agent definition in `.claude/agents/`, `.codex/agents/`, or `.gemini/agents/`.
|
|
115
130
|
- Cross-vendor or fallback CLI dispatch uses the vendor defaults in `.agents/skills/oma-orchestrator/config/cli-config.yaml`.
|
|
116
131
|
|
|
132
|
+
### Per-Agent Models
|
|
133
|
+
|
|
134
|
+
Pin a specific model and effort per role in `.agents/oma-config.yaml`:
|
|
135
|
+
|
|
136
|
+
```yaml
|
|
137
|
+
agent_cli_mapping:
|
|
138
|
+
backend:
|
|
139
|
+
model: "openai/gpt-5.3-codex"
|
|
140
|
+
effort: "high"
|
|
141
|
+
```
|
|
142
|
+
|
|
143
|
+
- `oma doctor --profile` — prints the per-role CLI auth matrix
|
|
144
|
+
- Runtime profiles: `claude-only`, `codex-only`, `gemini-only`, `antigravity`, `qwen-only`
|
|
145
|
+
- Full guide: [`web/docs/guide/per-agent-models.md`](https://github.com/first-fluke/oh-my-agent/blob/main/web/docs/guide/per-agent-models.md)
|
|
146
|
+
|
|
117
147
|
## Why oh-my-agent?
|
|
118
148
|
|
|
119
149
|
> [Read why →](https://github.com/first-fluke/oh-my-agent/issues/155#issuecomment-4142133589)
|