oh-my-agent 5.19.0 → 5.20.0
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 +12 -0
- package/bin/cli.js +402 -401
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -64,6 +64,7 @@ Pick a preset and you're ready:
|
|
|
64
64
|
| **oma-architecture** | Architectural tradeoffs, boundaries, ADR/ATAM/CBAM-aware analysis |
|
|
65
65
|
| **oma-backend** | APIs in Python, Node.js, or Rust |
|
|
66
66
|
| **oma-brainstorm** | Explores ideas before you commit to building |
|
|
67
|
+
| **oma-coordination** | Manual step-by-step multi-agent coordination guide |
|
|
67
68
|
| **oma-db** | Schema design, migrations, indexing, vector DB |
|
|
68
69
|
| **oma-debug** | Root cause analysis, fixes, regression tests |
|
|
69
70
|
| **oma-design** | Design systems, tokens, accessibility, responsive |
|
|
@@ -101,16 +102,22 @@ Or use slash commands for structured workflows:
|
|
|
101
102
|
|
|
102
103
|
| Step | Command | What It Does |
|
|
103
104
|
|------|---------|-------------|
|
|
105
|
+
| 0 | `/deepinit` | Bootstrap an existing codebase (AGENTS.md, ARCHITECTURE.md, `docs/`) |
|
|
104
106
|
| 1 | `/brainstorm` | Free-form ideation |
|
|
105
107
|
| 2 | `/architecture` | Software architecture review, tradeoffs, ADR/ATAM/CBAM-style analysis |
|
|
106
108
|
| 2 | `/design` | 7-phase design system workflow |
|
|
107
109
|
| 2 | `/plan` | PM breaks down your feature into tasks |
|
|
110
|
+
| 2 | `/exec-plan` | Track plans as first-class artifacts in `docs/exec-plans/` |
|
|
111
|
+
| 2 | `/stack-set` | Auto-detect tech stack, generate language-specific backend resources |
|
|
108
112
|
| 3 | `/work` | Step-by-step multi-agent execution |
|
|
109
113
|
| 3 | `/orchestrate` | Automated parallel agent spawning |
|
|
110
114
|
| 3 | `/ultrawork` | 5-phase quality workflow with 11 review gates |
|
|
115
|
+
| 3 | `/ralph` | Wraps `/ultrawork` in an independent verifier loop until criteria pass |
|
|
111
116
|
| 4 | `/review` | Security + performance + accessibility audit |
|
|
112
117
|
| 5 | `/debug` | Structured root-cause debugging |
|
|
113
118
|
| 6 | `/scm` | SCM + Git workflow and Conventional Commit support |
|
|
119
|
+
| ⚙ | `/tools` | Toggle MCP tool groups (memory / code-analysis / code-edit / file-ops) |
|
|
120
|
+
| 📄 | `/pdf` | PDF → Markdown via `opendataloader-pdf` |
|
|
114
121
|
|
|
115
122
|
**Auto-detection**: You don't even need slash commands — keywords like "architecture", "plan", "review", and "debug" in your message (in 11 languages!) auto-activate the right workflow.
|
|
116
123
|
|
|
@@ -126,6 +133,11 @@ oma dashboard # Real-time agent monitoring
|
|
|
126
133
|
oma link # Regenerate .claude/.codex/.gemini/etc. from .agents/
|
|
127
134
|
oma agent:spawn backend "Build auth API" session-01
|
|
128
135
|
oma agent:parallel -i backend:"Auth API" frontend:"Login form"
|
|
136
|
+
oma retro 7d --compare # Engineering retrospective with metrics + trends
|
|
137
|
+
oma recap --window 1d # Cross-tool conversation history recap
|
|
138
|
+
oma search fetch <url> # Mechanical search with auto-escalating strategies
|
|
139
|
+
oma image generate "cat" # Multi-vendor AI image generation
|
|
140
|
+
oma export cursor # Project skills as `.cursor/rules` for external IDEs
|
|
129
141
|
```
|
|
130
142
|
|
|
131
143
|
Model selection follows two layers:
|