@nerviq/cli 0.9.1 → 0.9.2

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 (2) hide show
  1. package/README.md +115 -30
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -1,52 +1,137 @@
1
- # claudex-setup → Nerviq
1
+ # Nerviq
2
2
 
3
- > **This project has been renamed and expanded to [Nerviq](https://github.com/nerviq/nerviq).**
3
+ > The intelligent nervous system for AI coding agents — audit, align, and amplify every platform on every project.
4
4
 
5
- ## What changed
5
+ [![npm version](https://img.shields.io/npm/v/@nerviq/cli)](https://www.npmjs.com/package/@nerviq/cli)
6
+ [![License: AGPL-3.0](https://img.shields.io/badge/License-AGPL--3.0-blue.svg)](LICENSE)
6
7
 
7
- `claudex-setup` started as a Claude Code audit tool (85 checks, single platform).
8
+ ---
8
9
 
9
- **Nerviq** is the next generation — the intelligent nervous system for **all** AI coding agents:
10
+ ### ⚠️ Beta — Currently Claude Code only
10
11
 
11
- - **8 platforms**: Claude Code, Codex, Gemini CLI, GitHub Copilot, Cursor, Windsurf, Aider, OpenCode
12
- - **639 checks** across all platforms
13
- - **Harmony**: detect drift between agents on the same project
14
- - **Synergy**: make agents amplify each other (1+1+1 > 3)
15
- - **135 modules**, 172 exports
12
+ Nerviq is in **beta**. The current release fully supports **Claude Code** (90 checks, audit, setup, governance, benchmark).
16
13
 
17
- ## Install the new version
14
+ **Coming soon:**
15
+ - Codex (OpenAI)
16
+ - Gemini CLI (Google)
17
+ - GitHub Copilot
18
+ - Cursor
19
+ - Windsurf
20
+ - Aider
21
+ - OpenCode
22
+ - **Harmony** — cross-platform drift detection
23
+ - **Synergy** — multi-agent amplification
24
+
25
+ ---
26
+
27
+ ## What Nerviq Does
28
+
29
+ Nerviq scores your AI coding agent setup from 0 to 100, finds what's missing, and fixes it — with rollback for every change.
18
30
 
19
- ```bash
20
- npm i -g @nerviq/cli
21
31
  ```
32
+ nerviq audit
33
+ ═══════════════════════════════════════
34
+ Detected: React, TypeScript, Docker
35
+
36
+ ████████████████░░░░ 78/100
37
+
38
+ ✅ CLAUDE.md with architecture diagram
39
+ ✅ Hooks (PreToolUse + PostToolUse)
40
+ ✅ Custom skills (3 skills)
41
+ ✅ MCP servers configured
22
42
 
23
- ## Usage
43
+ ⚡ Top 3 Next Actions
44
+ 1. Add verification commands to CLAUDE.md
45
+ 2. Configure deny rules for dangerous operations
46
+ 3. Add path-specific rules in .claude/rules/
47
+
48
+ Next: nerviq setup
49
+ ```
50
+
51
+ ## Quick Start
24
52
 
25
53
  ```bash
26
- nerviq audit # Audit Claude Code (default)
27
- nerviq audit --platform codex # Audit Codex setup
28
- nerviq audit --platform gemini # Audit Gemini CLI setup
29
- nerviq audit --platform copilot # Audit GitHub Copilot setup
30
- nerviq audit --platform cursor # Audit Cursor setup
31
- nerviq audit --platform windsurf # Audit Windsurf setup
32
- nerviq audit --platform aider # Audit Aider setup
33
- nerviq audit --platform opencode # Audit OpenCode setup
34
-
35
- nerviq harmony-audit # Cross-platform harmony score
36
- nerviq synergy-report # Synergy amplification report
54
+ npx @nerviq/cli audit # Score your project (10 seconds)
55
+ npx @nerviq/cli audit --lite # Quick top-3 scan
56
+ npx @nerviq/cli setup # Generate starter-safe baseline
57
+ npx @nerviq/cli augment # Improvement plan, no writes
58
+ npx @nerviq/cli governance # Permission profiles + policy packs
59
+ npx @nerviq/cli benchmark # Before/after in isolated copy
37
60
  ```
38
61
 
62
+ No install required. Zero dependencies.
63
+
64
+ ## 90 Checks Across 14 Categories
65
+
66
+ | Category | Checks | Examples |
67
+ |----------|--------|---------|
68
+ | Memory & Context | 9 | CLAUDE.md, architecture, @path imports, CLAUDE.local.md |
69
+ | Quality | 8 | verification loops, test/lint/build commands |
70
+ | Security | 7 | permissions, deny rules, secrets detection |
71
+ | Automation | 8 | hooks (30+ event types), notification, subagent tracking |
72
+ | Workflow | 9 | skills, subagents, rules, commands, snapshots |
73
+ | Git & Hygiene | 14 | .gitignore, env protection, README, changelog |
74
+ | Tools & MCP | 4 | .mcp.json, Context7, multi-server |
75
+ | Prompting | 6 | XML tags, constraints, examples, role definition |
76
+ | DevOps | 5 | Docker, CI, Terraform |
77
+ | Design | 2 | frontend anti-slop, Tailwind |
78
+ | Performance | 3 | compaction, context management, effort level |
79
+ | Features | 2 | channels, worktrees |
80
+ | Quality Deep | 9 | freshness, contradictions, deprecated patterns |
81
+
82
+ ## All Commands
83
+
84
+ | Command | What it does |
85
+ |---------|-------------|
86
+ | `nerviq audit` | Score 0-100 against 90 checks |
87
+ | `nerviq audit --lite` | Quick top-3 scan |
88
+ | `nerviq setup` | Generate starter-safe CLAUDE.md + hooks + commands |
89
+ | `nerviq augment` | Repo-aware improvement plan (no writes) |
90
+ | `nerviq suggest-only` | Structured report for sharing |
91
+ | `nerviq plan` | Export proposal bundles with previews |
92
+ | `nerviq apply` | Apply proposals with rollback |
93
+ | `nerviq governance` | Permission profiles, hooks, policy packs |
94
+ | `nerviq benchmark` | Before/after in isolated temp copy |
95
+ | `nerviq deep-review` | AI-powered config review (opt-in) |
96
+ | `nerviq interactive` | Step-by-step guided wizard |
97
+ | `nerviq watch` | Live monitoring with score delta |
98
+ | `nerviq history` | Score history from snapshots |
99
+ | `nerviq compare` | Compare latest vs previous |
100
+ | `nerviq trend` | Export trend report |
101
+ | `nerviq feedback` | Record recommendation outcomes |
102
+ | `nerviq badge` | shields.io badge for README |
103
+ | `nerviq scan dir1 dir2` | Compare multiple repos |
104
+
105
+ ## Options
106
+
107
+ | Flag | Effect |
108
+ |------|--------|
109
+ | `--threshold N` | Exit 1 if score < N (for CI) |
110
+ | `--json` | Machine-readable JSON output |
111
+ | `--out FILE` | Write output to file |
112
+ | `--snapshot` | Save audit snapshot for trending |
113
+ | `--lite` | Compact top-3 quick scan |
114
+ | `--dry-run` | Preview apply without writing |
115
+ | `--auto` | Apply without prompts |
116
+ | `--verbose` | Show all recommendations |
117
+ | `--format sarif` | SARIF output for code scanning |
118
+
119
+ ## Privacy
120
+
121
+ - **Zero dependencies** — nothing to audit
122
+ - **Runs locally** — audit, setup, plan, apply, governance, benchmark all run on your machine
123
+ - **Deep review is opt-in** — only `deep-review` sends selected config for AI analysis
124
+ - **AGPL-3.0 Licensed** — open source
125
+
39
126
  ## Links
40
127
 
41
128
  - **npm**: [@nerviq/cli](https://www.npmjs.com/package/@nerviq/cli)
42
129
  - **GitHub**: [github.com/nerviq/nerviq](https://github.com/nerviq/nerviq)
43
130
  - **Website**: [nerviq.net](https://nerviq.net)
44
131
 
45
- ## Legacy
46
-
47
- The original `claudex-setup` package on npm is deprecated. All future development happens at [@nerviq/cli](https://www.npmjs.com/package/@nerviq/cli).
132
+ ## Previously claudex-setup
48
133
 
49
- If you were using `claudex-setup`, simply switch:
134
+ Nerviq was previously published as `claudex-setup`. If you were using it:
50
135
 
51
136
  ```bash
52
137
  # Old
@@ -56,4 +141,4 @@ npx claudex-setup
56
141
  npx @nerviq/cli audit
57
142
  ```
58
143
 
59
- All features from claudex-setup are preserved and expanded in Nerviq.
144
+ All features are preserved and expanded.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@nerviq/cli",
3
- "version": "0.9.1",
3
+ "version": "0.9.2",
4
4
  "description": "The intelligent nervous system for AI coding agents — audit, align, and amplify every platform on every project.",
5
5
  "main": "src/index.js",
6
6
  "bin": {