oh-my-agent 4.2.0 → 4.3.0

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 +70 -101
  2. package/bin/cli.js +91 -91
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -6,112 +6,17 @@
6
6
 
7
7
  The portable, role-based agent harness for serious AI-assisted engineering.
8
8
 
9
- Orchestrate 10 specialized domain agents (PM, Frontend, Backend, DB, Mobile, QA, Debug, Brainstorm, DevWorkflow, Terraform) via **Serena Memory**. `oh-my-agent` uses `.agents/` as the source of truth for portable skills and workflows, then projects compatibility to other AI IDEs and CLIs. It combines role-based agents, explicit workflows, real-time observability, and standards-aware guidance for teams that want less AI slop and more disciplined execution.
9
+ Orchestrate 10 specialized domain agents (PM, Frontend, Backend, DB, Mobile, QA, Debug, Brainstorm, DevWorkflow, Terraform). `oh-my-agent` works with all major AI IDEs including Antigravity, Claude Code, Cursor, Gemini, OpenCode, and more. It combines role-based agents, explicit workflows, real-time observability, and standards-aware guidance for teams that want less AI slop and more disciplined execution.
10
10
 
11
11
  ## Table of Contents
12
12
 
13
- - [Architecture](#architecture)
14
- - [Why Different](#why-different)
15
- - [Compatibility](#compatibility)
16
- - [The `.agents` Spec](#the-agents-spec)
17
13
  - [What Is This?](#what-is-this)
14
+ - [Why Different](#why-different)
18
15
  - [Quick Start](#quick-start)
16
+ - [Architecture](#architecture)
19
17
  - [Sponsors](#sponsors)
20
18
  - [License](#license)
21
19
 
22
- ## Architecture
23
-
24
- ```mermaid
25
- flowchart TD
26
- subgraph Workflows["Workflows"]
27
- direction TB
28
- W0["/brainstorm"]
29
- W1["/coordinate"]
30
- W1b["/ultrawork"]
31
- W2["/orchestrate"]
32
- W3["/plan"]
33
- W4["/review"]
34
- W5["/debug"]
35
- W6["/deepinit"]
36
- end
37
-
38
- subgraph Orchestration["Orchestration"]
39
- direction TB
40
- PM[oma-pm]
41
- ORC[oma-orchestrator]
42
- end
43
-
44
- subgraph Domain["Domain Agents"]
45
- direction TB
46
- FE[oma-frontend]
47
- BE[oma-backend]
48
- DB[oma-db]
49
- MB[oma-mobile]
50
- TF[oma-tf-infra]
51
- end
52
-
53
- subgraph Quality["Quality"]
54
- direction TB
55
- QA[oma-qa]
56
- DBG[oma-debug]
57
- end
58
-
59
- Workflows --> Orchestration
60
- Orchestration --> Domain
61
- Domain --> Quality
62
- Quality --> CMT([oma-commit])
63
- ```
64
-
65
- ## Why Different
66
-
67
- - **`.agents/` is the source of truth**: skills, workflows, shared resources, and config live in one portable project structure instead of being trapped inside one IDE plugin.
68
- - **Role-shaped agent teams**: PM, QA, DB, Infra, Frontend, Backend, Mobile, Debug, and Workflow agents are modeled like an engineering org, not just a pile of prompts.
69
- - **Workflow-first orchestration**: planning, review, debug, and coordinated execution are first-class workflows, not afterthoughts.
70
- - **Standards-aware by design**: agents now carry focused guidance for ISO-driven planning, QA, database continuity/security, and infrastructure governance.
71
- - **Built for verification**: dashboards, manifest generation, shared execution protocols, and structured outputs favor traceability over vibe-only generation.
72
-
73
- ## Compatibility
74
-
75
- `oh-my-agent` is designed around `.agents/` and then bridges to other tool-specific skill folders when needed.
76
-
77
- | Tool / IDE | Skills Source | Interop Mode | Notes |
78
- |------------|---------------|--------------|-------|
79
- | Antigravity | `.agents/skills/` | Native | Primary source-of-truth layout; no custom subagent spawning |
80
- | Claude Code | `.claude/skills/` + `.claude/agents/` | Native + Adapter | Symlinks for domain skills + thin router workflow skills, subagents generated from `.agents/agents/`, and CLAUDE.md |
81
- | Codex CLI | `.codex/agents/` + `.agents/skills/` | Native + Adapter | Agent TOML generated from `.agents/agents/` (planned) |
82
- | Gemini CLI | `.gemini/agents/` + `.agents/skills/` | Native + Adapter | Agent MD generated from `.agents/agents/` (planned) |
83
- | OpenCode | `.agents/skills/` | Native-compatible | Uses the same project-level skill source |
84
- | Amp | `.agents/skills/` | Native-compatible | Shares the same project-level source |
85
- | Cursor | `.agents/skills/` | Native-compatible | Can consume the same project-level skill source |
86
- | GitHub Copilot | `.github/skills/` | Optional symlink | Installed when selected during setup |
87
-
88
- See [SUPPORTED_AGENTS.md](https://github.com/first-fluke/oh-my-agent/blob/main/docs/SUPPORTED_AGENTS.md) for the current support matrix and interoperability notes.
89
-
90
- ### Claude Code Native Integration
91
-
92
- Claude Code has first-class native integration beyond symlinks:
93
-
94
- - **`CLAUDE.md`** — project identity, architecture, and rules (auto-loaded by Claude Code)
95
- - **`.claude/skills/`** — 12 thin router SKILL.md files that delegate to `.agents/workflows/` (e.g., `/orchestrate`, `/coordinate`, `/ultrawork`). Skills are explicitly invoked via slash commands, not keyword-auto-activated.
96
- - **`.claude/agents/`** — 7 subagent definitions generated from `.agents/agents/*.yaml`, spawned via Task tool (backend-engineer, frontend-engineer, mobile-engineer, db-engineer, qa-reviewer, debug-investigator, pm-planner)
97
- - **Native loop patterns** — Review Loop, Issue Remediation Loop, and Phase Gate Loop using synchronous Task tool results instead of CLI polling
98
-
99
- Domain skills (oma-backend, oma-frontend, etc.) remain as symlinks from `.agents/skills/`. Workflow skills are thin router SKILL.md files that delegate to the corresponding `.agents/workflows/*.md` source of truth.
100
-
101
- ## The `.agents` Spec
102
-
103
- `oh-my-agent` treats `.agents/` as a portable project convention for agent skills, workflows, and shared context.
104
-
105
- - Skills live in `.agents/skills/<skill-name>/SKILL.md`
106
- - Abstract agent definitions live in `.agents/agents/` (vendor-neutral SSOT; the CLI generates `.claude/agents/`, `.codex/agents/` (planned), `.gemini/agents/` (planned) from these)
107
- - Shared resources live in `.agents/skills/_shared/`
108
- and are grouped into `core/`, `conditional/`, and `runtime/`
109
- - Workflows live in `.agents/workflows/*.md`
110
- - Project config lives in `.agents/config/`
111
- - CLI metadata and packaging stay aligned through generated manifests
112
-
113
- See [AGENTS_SPEC.md](https://github.com/first-fluke/oh-my-agent/blob/main/docs/AGENTS_SPEC.md) for the project layout, required files, interoperability rules, and source-of-truth model.
114
-
115
20
  ## What Is This?
116
21
 
117
22
  A collection of **Agent Skills** enabling collaborative multi-agent development. Work is distributed across expert agents with explicit roles, workflows, and verification boundaries:
@@ -128,9 +33,23 @@ A collection of **Agent Skills** enabling collaborative multi-agent development.
128
33
  | **Debug Agent** | Bug diagnosis, root cause analysis, regression tests | "bug", "error", "crash" |
129
34
  | **Developer Workflow** | Monorepo task automation, mise tasks, CI/CD, migrations, release | "dev workflow", "mise tasks", "CI/CD pipeline" |
130
35
  | **TF Infra Agent** | Multi-cloud IaC provisioning (AWS, GCP, Azure, OCI) | "infrastructure", "terraform", "cloud setup" |
131
- | **Orchestrator** | CLI-based parallel agent execution with Serena Memory | "spawn agent", "parallel execution" |
36
+ | **Orchestrator** | CLI-based parallel agent execution | "spawn agent", "parallel execution" |
132
37
  | **Commit** | Conventional Commits with project-specific rules | "commit", "save changes" |
133
38
 
39
+
40
+
41
+ ## Why Different
42
+
43
+ - **`.agents/` is the source of truth**: skills, workflows, shared resources, and config live in one portable project structure instead of being trapped inside one IDE plugin.
44
+ - **Role-shaped agent teams**: PM, QA, DB, Infra, Frontend, Backend, Mobile, Debug, and Workflow agents are modeled like an engineering org, not just a pile of prompts.
45
+ - **Workflow-first orchestration**: planning, review, debug, and coordinated execution are first-class workflows, not afterthoughts.
46
+ - **Standards-aware by design**: agents now carry focused guidance for ISO-driven planning, QA, database continuity/security, and infrastructure governance.
47
+ - **Built for verification**: dashboards, manifest generation, shared execution protocols, and structured outputs favor traceability over vibe-only generation.
48
+
49
+
50
+
51
+
52
+
134
53
  ## Quick Start
135
54
 
136
55
  ### Prerequisites
@@ -173,6 +92,10 @@ Select your project type and skills will be installed to `.agents/skills/`, with
173
92
  To use the core tools globally or run the SubAgent Orchestrator:
174
93
 
175
94
  ```bash
95
+ # Homebrew (macOS/Linux)
96
+ brew install oh-my-agent
97
+
98
+ # npm/bun
176
99
  bun install --global oh-my-agent
177
100
  ```
178
101
 
@@ -219,6 +142,53 @@ You'll also need at least one CLI tool:
219
142
 
220
143
  For dashboard setup and usage details, see [`web/content/en/guide/usage.md`](https://github.com/first-fluke/oh-my-agent/blob/main/web/content/en/guide/usage.md#real-time-dashboards).
221
144
 
145
+
146
+
147
+ ## Architecture
148
+
149
+ ```mermaid
150
+ flowchart TD
151
+ subgraph Workflows["Workflows"]
152
+ direction TB
153
+ W0["/brainstorm"]
154
+ W1["/coordinate"]
155
+ W1b["/ultrawork"]
156
+ W2["/orchestrate"]
157
+ W3["/plan"]
158
+ W4["/review"]
159
+ W5["/debug"]
160
+ W6["/deepinit"]
161
+ end
162
+
163
+ subgraph Orchestration["Orchestration"]
164
+ direction TB
165
+ PM[oma-pm]
166
+ ORC[oma-orchestrator]
167
+ end
168
+
169
+ subgraph Domain["Domain Agents"]
170
+ direction TB
171
+ FE[oma-frontend]
172
+ BE[oma-backend]
173
+ DB[oma-db]
174
+ MB[oma-mobile]
175
+ TF[oma-tf-infra]
176
+ end
177
+
178
+ subgraph Quality["Quality"]
179
+ direction TB
180
+ QA[oma-qa]
181
+ DBG[oma-debug]
182
+ end
183
+
184
+ Workflows --> Orchestration
185
+ Orchestration --> Domain
186
+ Domain --> Quality
187
+ Quality --> CMT([oma-commit])
188
+ ```
189
+
190
+
191
+
222
192
  ## Sponsors
223
193
 
224
194
  This project is maintained thanks to our generous sponsors.
@@ -254,10 +224,9 @@ This project is maintained thanks to our generous sponsors.
254
224
 
255
225
  See [SPONSORS.md](https://github.com/first-fluke/oh-my-agent/blob/main/SPONSORS.md) for a full list of supporters.
256
226
 
257
- ## Star History
258
227
 
259
- [![Star History Chart](https://api.star-history.com/svg?repos=first-fluke/oh-my-agent&type=date&legend=bottom-right)](https://www.star-history.com/#first-fluke/oh-my-agent&type=date&legend=bottom-right)
260
228
 
261
229
  ## License
262
230
 
263
231
  MIT
232
+