@contentrain/rules 0.3.1 → 0.3.2

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.
package/README.md CHANGED
@@ -1,10 +1,17 @@
1
1
  # `@contentrain/rules`
2
2
 
3
3
  [![npm version](https://img.shields.io/npm/v/%40contentrain%2Frules?label=%40contentrain%2Frules)](https://www.npmjs.com/package/@contentrain/rules)
4
+ [![Agent Skills](https://img.shields.io/badge/Agent_Skills-compatible-8B5CF6)](https://agentskills.io)
4
5
  [![GitHub source](https://img.shields.io/badge/source-Contentrain%2Fai-181717?logo=github)](https://github.com/Contentrain/ai/tree/main/packages/rules)
6
+ [![Docs](https://img.shields.io/badge/docs-ai.contentrain.io-0f172a)](https://ai.contentrain.io/packages/rules)
5
7
 
6
8
  Shared AI-agent rules for Contentrain.
7
9
 
10
+ Start here:
11
+
12
+ - [2-minute product demo](https://ai.contentrain.io/demo)
13
+ - [Rules & skills docs](https://ai.contentrain.io/packages/rules)
14
+
8
15
  This package is the policy layer of the Contentrain ecosystem. It defines how agents should behave when they work with:
9
16
 
10
17
  - Contentrain MCP tools
@@ -89,6 +96,8 @@ Rule of thumb:
89
96
  - `rules` = essential guardrails (always loaded, ~86 lines)
90
97
  - `skills` = detailed procedures and reference docs (on-demand)
91
98
 
99
+ See [`AGENTS.md`](../../AGENTS.md) at the repo root for agent-level project guidance.
100
+
92
101
  ## Build
93
102
 
94
103
  From the monorepo root:
@@ -52,6 +52,7 @@ MCP is **deterministic infrastructure**. The agent (you) is the **intelligence l
52
52
  | `contentrain_apply` | Apply normalize (extract/reuse) |
53
53
  | `contentrain_validate` | Validate content against schemas |
54
54
  | `contentrain_submit` | Push branches to remote |
55
+ | `contentrain_merge` | Merge a review-mode branch into contentrain locally |
55
56
  | `contentrain_bulk` | Batch operations (copy_locale/update_status/delete_entries) |
56
57
 
57
58
  ## Mandatory Protocols
@@ -77,6 +78,33 @@ MCP is **deterministic infrastructure**. The agent (you) is the **intelligence l
77
78
  - Never create branches manually, never commit directly to main or the `contentrain` branch
78
79
  - 50+ active branches = warning, 80+ = blocked
79
80
 
81
+ ## CLI Serve — Review & Approval
82
+
83
+ Normalize and review workflows often need browser-based approval:
84
+
85
+ ```bash
86
+ contentrain serve # starts http://localhost:3333
87
+ ```
88
+
89
+ Key pages: `/normalize` (extraction approval), `/branches` (merge/delete), `/validate` (error review), `/content` (browse).
90
+
91
+ Agent should start or ensure serve is running when:
92
+ - Normalize extraction needs user approval
93
+ - Multiple branches await review
94
+ - Validation errors need visual inspection
95
+
96
+ Branch merge options: CLI serve UI (localhost:3333/branches), `contentrain_merge` MCP tool, or git platform PR.
97
+
98
+ ## SDK Regeneration
99
+
100
+ After model/content changes or normalize reuse, run:
101
+
102
+ ```bash
103
+ npx contentrain generate
104
+ ```
105
+
106
+ This regenerates `.contentrain/client/` — required for `#contentrain` imports to work.
107
+
80
108
  ## Localization
81
109
 
82
110
  - All supported locales must have entries for every content item
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@contentrain/rules",
3
- "version": "0.3.1",
3
+ "version": "0.3.2",
4
4
  "license": "MIT",
5
5
  "description": "AI agent rules for Contentrain — quality standards, architecture conventions, IDE integration",
6
6
  "type": "module",
@@ -9,7 +9,7 @@
9
9
  "url": "git+https://github.com/Contentrain/ai.git",
10
10
  "directory": "packages/rules"
11
11
  },
12
- "homepage": "https://github.com/Contentrain/ai/tree/main/packages/rules",
12
+ "homepage": "https://ai.contentrain.io/packages/rules",
13
13
  "bugs": {
14
14
  "url": "https://github.com/Contentrain/ai/issues"
15
15
  },
@@ -17,11 +17,15 @@
17
17
  "contentrain",
18
18
  "ai",
19
19
  "rules",
20
+ "agent-skills",
21
+ "agent-rules",
20
22
  "mcp",
21
23
  "prompt-engineering",
22
24
  "claude-code",
23
25
  "cursor",
24
- "windsurf"
26
+ "windsurf",
27
+ "copilot",
28
+ "codex"
25
29
  ],
26
30
  "sideEffects": false,
27
31
  "publishConfig": {