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.
Files changed (3) hide show
  1. package/README.md +4 -6
  2. package/bin/cli.js +575 -575
  3. 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 & uv if missing
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 & uv if missing
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 Gemini, Claude, Codex, and Qwen per agent type
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