oh-my-agent 8.2.1 → 8.4.0
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 +4 -6
- package/bin/cli.js +575 -575
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -13,17 +13,17 @@ Works with all major AI IDEs: Antigravity, Claude Code, Cursor, Gemini CLI, Code
|
|
|
13
13
|
## Quick Start
|
|
14
14
|
|
|
15
15
|
```bash
|
|
16
|
-
# macOS / Linux — auto-installs bun &
|
|
16
|
+
# macOS / Linux — auto-installs bun, uv & serena if missing
|
|
17
17
|
curl -fsSL https://raw.githubusercontent.com/first-fluke/oh-my-agent/main/cli/install.sh | bash
|
|
18
18
|
```
|
|
19
19
|
|
|
20
20
|
```powershell
|
|
21
|
-
# Windows (PowerShell) — auto-installs bun &
|
|
21
|
+
# Windows (PowerShell) — auto-installs bun, uv & serena if missing
|
|
22
22
|
irm https://raw.githubusercontent.com/first-fluke/oh-my-agent/main/cli/install.ps1 | iex
|
|
23
23
|
```
|
|
24
24
|
|
|
25
25
|
```bash
|
|
26
|
-
# Or manual (any OS, requires bun + uv)
|
|
26
|
+
# Or manual (any OS, requires bun + uv + serena)
|
|
27
27
|
bunx oh-my-agent@latest
|
|
28
28
|
```
|
|
29
29
|
|
|
@@ -43,8 +43,6 @@ apm install first-fluke/oh-my-agent
|
|
|
43
43
|
apm install first-fluke/oh-my-agent/.agents/skills/oma-frontend
|
|
44
44
|
```
|
|
45
45
|
|
|
46
|
-
APM reads `.claude-plugin/plugin.json`'s `skills: .agents/skills/` pointer, so the `.agents/` SSOT is the only source — no build step or mirror.
|
|
47
|
-
|
|
48
46
|
APM ships skills only. For workflows, rules, `oma-config.yaml`, keyword-detection hooks, and the `oma agent:spawn` CLI, use `bunx oh-my-agent@latest`. Pick one distribution per project to avoid drift.
|
|
49
47
|
|
|
50
48
|
</details>
|
|
@@ -245,7 +243,7 @@ agents:
|
|
|
245
243
|
- `ralph` workflow — independent JUDGE re-verifies every criterion each iteration to catch silent regressions; heavy-test caching for >30s suites
|
|
246
244
|
- Exploration Loop — after 2 retries, `orchestrate` spawns hypothesis variants in parallel and keeps the highest-scoring result
|
|
247
245
|
- Monorepo auto-routing — `detectWorkspace` reads pnpm / nx / turbo / lerna and routes each agent to its workspace
|
|
248
|
-
- **Multi-vendor** — Mix
|
|
246
|
+
- **Multi-vendor** — Mix Claude, Codex, Cursor, and Qwen per agent type
|
|
249
247
|
- **Observable** — Terminal and web dashboards for real-time monitoring
|
|
250
248
|
|
|
251
249
|
## Architecture
|