smash-os-install 0.3.5 → 0.4.2

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 (4) hide show
  1. package/README.md +137 -135
  2. package/install.mjs +615 -245
  3. package/package.json +18 -2
  4. package/templates.mjs +1258 -1050
package/README.md CHANGED
@@ -1,135 +1,137 @@
1
- # smash-os-install
2
-
3
- Install the SmashOS local AI workflow harness into any repository. No web app, no API keys, no cloud dependencies.
4
-
5
- ```bash
6
- npx smash-os-install
7
- ```
8
-
9
- ---
10
-
11
- ## What SmashOS is
12
-
13
- SmashOS gives Claude Code a coordinated team of 12 AI specialists — each with a defined role, scoring rules, and memory — that work together through structured pipelines to ship features, catch bugs, and audit security. Everything runs locally via Claude Code with no external services.
14
-
15
- ---
16
-
17
- ## Install
18
-
19
- ```bash
20
- # Run inside your repo root
21
- npx smash-os-install
22
- ```
23
-
24
- **Prerequisites:** Node.js 18+ and [Claude Code](https://claude.ai/code)
25
-
26
- The installer asks for your project name and tech stack, then writes all harness files into your repo.
27
-
28
- ---
29
-
30
- ## What gets created
31
-
32
- ```
33
- your-repo/
34
- ├── CLAUDE.md ← harness instructions loaded by Claude on every session
35
- ├── .claude/
36
- ├── hooks/
37
- │ │ ├── boot-hook.mjs ← injects context files at session start
38
- │ └── sync-hook.mjs ← persists memory after each response
39
- └── agents/ 47 sub-agent definitions
40
- ├── ai/
41
- ├── context/
42
- │ │ ├── product.md ← fill in: what your product does
43
- ├── architecture.md ← fill in: your stack and key decisions
44
- │ │ └── coding-standards.md ← fill in: your style rules
45
- │ ├── roles/ 12 role definitions (PM, Staff Eng, Dev, Security, QA, DevOps…)
46
- ├── workflows/ 10 pipeline definitions
47
- └── memory/
48
- ├── decisions.md auto-populated: architectural decisions
49
- ├── lessons.md ← auto-populated: what went wrong + why
50
- └── constraints.md ← auto-populated: hard limits
51
- └── .claude-state/ session breadcrumbs (gitignored)
52
- ├── active-context.md
53
- ├── next-steps.md
54
- └── decisions.md
55
- ```
56
-
57
- Skills install globally to `~/.claude/skills/` and are available in every project.
58
-
59
- ---
60
-
61
- ## First 3 commands
62
-
63
- ```bash
64
- # 1. Open Claude Code in your repo
65
- claude .
66
-
67
- # 2. Verify the installation
68
- /smash-os:status
69
-
70
- # 3. Run your first pipeline
71
- /smash-os:run feature "Add a health check endpoint"
72
- ```
73
-
74
- ---
75
-
76
- ## How a pipeline works
77
-
78
- ```
79
- /smash-os:run feature "your task"
80
-
81
- ├─ Phase 1: Product Manager → spec + acceptance criteria (score ≥ 60 to pass)
82
- ├─ Phase 2: Staff Engineer → architecture review + spec sign-off
83
- ├─ Phase 3: Senior Developer implementation (branch + commits)
84
- ├─ Phase 4: Security Engineer threat model + security_score
85
- ├─ Phase 5: QA Engineer test plan + test_success_score
86
- └─ Phase 6: DevOps Engineer PR + deployment readiness
87
- ```
88
-
89
- Each phase scores its output 0–100. Below 60 halts the pipeline. The blocking reason is written to `ai/memory/` and injected into the next session automatically.
90
-
91
- ---
92
-
93
- ## Architecture
94
-
95
- ```
96
- ┌─────────────────────────────────────────────────────┐
97
- │ Claude Code │
98
- │ │
99
- CLAUDE.md ──→ loads harness instructions
100
- boot-hook ──→ injects ai/context/ + ai/memory/
101
- sync-hook ──→ writes decisions + lessons back
102
-
103
- /smash-os:run feature "task"
104
-
105
- └─→ Pipeline orchestrator
106
-
107
- ├─→ Role loader (ai/roles/)
108
- ├─→ Workflow runner (ai/workflows/)
109
- └─→ Sub-agents (.claude/agents/)
110
-
111
- └─→ Phase outputs → memory
112
- └─────────────────────────────────────────────────────┘
113
- ```
114
-
115
- ---
116
-
117
- ## Slash commands
118
-
119
- | Command | Description |
120
- |---------|-------------|
121
- | `/smash-os:status` | Health check — active pipelines, recent decisions, memory state |
122
- | `/smash-os:run [type]` | Start a pipeline: `feature`, `bug-fix`, `security-audit`, `weekly-improvement` |
123
- | `/smash-os:fast` | Skip the pipeline execute a trivial task inline (≤3 files) |
124
- | `/smash-os:role [name]` | Switch to a specific role |
125
- | `/smash-os:memory` | Show stored decisions, lessons, constraints |
126
- | `/smash-os:audit` | Trigger an immediate security audit |
127
- | `/smash-os:doctor` | Verify the installation is complete and correct |
128
- | `/smash-os:evolve` | Run harness self-improvement on accumulated role learnings |
129
- | `/smash-os:sync` | Manual mid-session checkpoint save current state to memory |
130
-
131
- ---
132
-
133
- ## License
134
-
135
- MIT
1
+ # smash-os-install
2
+
3
+ [![Tests](https://github.com/MrShifu01/SmashOS/actions/workflows/test.yml/badge.svg)](https://github.com/MrShifu01/SmashOS/actions/workflows/test.yml)
4
+
5
+ Install the SmashOS local AI workflow harness into any repository. No web app, no API keys, no cloud dependencies.
6
+
7
+ ```bash
8
+ npx smash-os-install
9
+ ```
10
+
11
+ ---
12
+
13
+ ## What SmashOS is
14
+
15
+ SmashOS gives Claude Code a coordinated team of 12 AI specialists — each with a defined role, scoring rules, and memory — that work together through structured pipelines to ship features, catch bugs, and audit security. Everything runs locally via Claude Code with no external services.
16
+
17
+ ---
18
+
19
+ ## Install
20
+
21
+ ```bash
22
+ # Run inside your repo root
23
+ npx smash-os-install
24
+ ```
25
+
26
+ **Prerequisites:** Node.js 18+ and [Claude Code](https://claude.ai/code)
27
+
28
+ The installer asks for your project name and tech stack, then writes all harness files into your repo.
29
+
30
+ ---
31
+
32
+ ## What gets created
33
+
34
+ ```
35
+ your-repo/
36
+ ├── CLAUDE.md ← harness instructions loaded by Claude on every session
37
+ ├── .claude/
38
+ ├── hooks/
39
+ │ ├── boot-hook.mjs injects context files at session start
40
+ │ │ └── sync-hook.mjs ← persists memory after each response
41
+ └── agents/ ← 47 sub-agent definitions
42
+ ├── ai/
43
+ │ ├── context/
44
+ │ │ ├── product.md ← fill in: what your product does
45
+ ├── architecture.md fill in: your stack and key decisions
46
+ │ └── coding-standards.md fill in: your style rules
47
+ ├── roles/ ← 12 role definitions (PM, Staff Eng, Dev, Security, QA, DevOps…)
48
+ ├── workflows/ 10 pipeline definitions
49
+ └── memory/
50
+ ├── decisions.md ← auto-populated: architectural decisions
51
+ │ ├── lessons.md auto-populated: what went wrong + why
52
+ │ └── constraints.md ← auto-populated: hard limits
53
+ └── .claude-state/ ← session breadcrumbs (gitignored)
54
+ ├── active-context.md
55
+ ├── next-steps.md
56
+ └── decisions.md
57
+ ```
58
+
59
+ Skills install globally to `~/.claude/skills/` and are available in every project.
60
+
61
+ ---
62
+
63
+ ## First 3 commands
64
+
65
+ ```bash
66
+ # 1. Open Claude Code in your repo
67
+ claude .
68
+
69
+ # 2. Verify the installation
70
+ /smash-os:status
71
+
72
+ # 3. Run your first pipeline
73
+ /smash-os:run feature "Add a health check endpoint"
74
+ ```
75
+
76
+ ---
77
+
78
+ ## How a pipeline works
79
+
80
+ ```
81
+ /smash-os:run feature "your task"
82
+
83
+ ├─ Phase 1: Product Manager spec + acceptance criteria (score 60 to pass)
84
+ ├─ Phase 2: Staff Engineer architecture review + spec sign-off
85
+ ├─ Phase 3: Senior Developer implementation (branch + commits)
86
+ ├─ Phase 4: Security Engineer threat model + security_score
87
+ ├─ Phase 5: QA Engineer → test plan + test_success_score
88
+ └─ Phase 6: DevOps Engineer → PR + deployment readiness
89
+ ```
90
+
91
+ Each phase scores its output 0–100. Below 60 halts the pipeline. The blocking reason is written to `ai/memory/` and injected into the next session automatically.
92
+
93
+ ---
94
+
95
+ ## Architecture
96
+
97
+ ```
98
+ ┌─────────────────────────────────────────────────────┐
99
+ Claude Code
100
+
101
+ CLAUDE.md ──→ loads harness instructions
102
+ boot-hook ──→ injects ai/context/ + ai/memory/
103
+ sync-hook ──→ writes decisions + lessons back
104
+
105
+ /smash-os:run feature "task"
106
+
107
+ └─→ Pipeline orchestrator
108
+ │ │
109
+ ├─→ Role loader (ai/roles/)
110
+ ├─→ Workflow runner (ai/workflows/)
111
+ └─→ Sub-agents (.claude/agents/)
112
+ │ │ │
113
+ │ └─→ Phase outputs → memory │
114
+ └─────────────────────────────────────────────────────┘
115
+ ```
116
+
117
+ ---
118
+
119
+ ## Slash commands
120
+
121
+ | Command | Description |
122
+ |---------|-------------|
123
+ | `/smash-os:status` | Health checkactive pipelines, recent decisions, memory state |
124
+ | `/smash-os:run [type]` | Start a pipeline: `feature`, `bug-fix`, `security-audit`, `weekly-improvement` |
125
+ | `/smash-os:fast` | Skip the pipeline execute a trivial task inline (≤3 files) |
126
+ | `/smash-os:role [name]` | Switch to a specific role |
127
+ | `/smash-os:memory` | Show stored decisions, lessons, constraints |
128
+ | `/smash-os:audit` | Trigger an immediate security audit |
129
+ | `/smash-os:doctor` | Verify the installation is complete and correct |
130
+ | `/smash-os:evolve` | Run harness self-improvement on accumulated role learnings |
131
+ | `/smash-os:sync` | Manual mid-session checkpoint — save current state to memory |
132
+
133
+ ---
134
+
135
+ ## License
136
+
137
+ MIT