rulesync 3.24.0 → 3.26.0
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 +42 -16
- package/dist/index.cjs +3979 -3236
- package/dist/index.js +3951 -3208
- package/package.json +18 -18
package/README.md
CHANGED
|
@@ -1,3 +1,7 @@
|
|
|
1
|
+
<p align="center">
|
|
2
|
+
<img src="images/logo.jpg" alt="Rulesync Logo" width="600">
|
|
3
|
+
</p>
|
|
4
|
+
|
|
1
5
|
# Rulesync
|
|
2
6
|
|
|
3
7
|
[](https://github.com/dyoshikawa/rulesync/actions/workflows/ci.yml)
|
|
@@ -132,26 +136,26 @@ Rulesync supports both **generation** and **import** for All of the major AI cod
|
|
|
132
136
|
|
|
133
137
|
| Tool | rules | ignore | mcp | commands | subagents | skills |
|
|
134
138
|
|------------------------|:-----:|:------:|:-----:|:--------:|:---------:|:------:|
|
|
135
|
-
| AGENTS.md | ✅ | | | 🎮 | 🎮 |
|
|
139
|
+
| AGENTS.md | ✅ | | | 🎮 | 🎮 | 🎮 |
|
|
136
140
|
| Claude Code | ✅ 🌏 | ✅ | ✅ 🌏 📦 | ✅ 🌏 | ✅ 🌏 | ✅ 🌏 |
|
|
137
|
-
| Codex CLI | ✅ 🌏 | | 🌏 | 🌏 | 🎮 |
|
|
138
|
-
| Gemini CLI | ✅ 🌏 | ✅ | ✅ 🌏 | ✅ 🌏 | 🎮 |
|
|
139
|
-
| GitHub Copilot | ✅ | | ✅ | ✅ | 🎮 |
|
|
140
|
-
| Cursor | ✅ | ✅ | ✅ | ✅ 🌏 | 🎮 |
|
|
141
|
+
| Codex CLI | ✅ 🌏 | | 🌏 | 🌏 | 🎮 | 🎮 |
|
|
142
|
+
| Gemini CLI | ✅ 🌏 | ✅ | ✅ 🌏 | ✅ 🌏 | 🎮 | 🎮 |
|
|
143
|
+
| GitHub Copilot | ✅ | | ✅ | ✅ | 🎮 | 🎮 |
|
|
144
|
+
| Cursor | ✅ | ✅ | ✅ | ✅ 🌏 | 🎮 | 🎮 |
|
|
141
145
|
| OpenCode | ✅ | | | | | |
|
|
142
146
|
| Cline | ✅ | ✅ | ✅ | | | |
|
|
143
147
|
| Roo Code | ✅ | ✅ | ✅ | ✅ | 🎮 | |
|
|
144
148
|
| Qwen Code | ✅ | ✅ | | | | |
|
|
145
149
|
| Kiro IDE | ✅ | ✅ | | | | |
|
|
146
150
|
| Amazon Q Developer CLI | ✅ | | ✅ | | | |
|
|
147
|
-
| JetBrains Junie | ✅ | ✅ |
|
|
151
|
+
| JetBrains Junie | ✅ | ✅ | ✅ | | | |
|
|
148
152
|
| AugmentCode | ✅ | ✅ | | | | |
|
|
149
153
|
| Windsurf | ✅ | ✅ | | | | |
|
|
150
154
|
| Warp | ✅ | | | | | |
|
|
151
155
|
|
|
152
156
|
* ✅: Supports project mode
|
|
153
157
|
* 🌏: Supports global mode
|
|
154
|
-
* 🎮: Supports simulated commands/subagents (Project mode only)
|
|
158
|
+
* 🎮: Supports simulated commands/subagents/skills (Project mode only)
|
|
155
159
|
* 📦: Supports modular MCP (Experimental)
|
|
156
160
|
|
|
157
161
|
## Why Rulesync?
|
|
@@ -231,8 +235,9 @@ Example:
|
|
|
231
235
|
|
|
232
236
|
// Advanced options
|
|
233
237
|
"global": false, // Generate for global(user scope) configuration files
|
|
234
|
-
"
|
|
235
|
-
"
|
|
238
|
+
"simulateCommands": false, // Generate simulated commands
|
|
239
|
+
"simulateSubagents": false, // Generate simulated subagents
|
|
240
|
+
"simulateSkills": false, // Generate simulated skills
|
|
236
241
|
"modularMcp": false // Enable modular-mcp for context compression (experimental, Claude Code only)
|
|
237
242
|
|
|
238
243
|
// Deprecated experimental options (for backward compatibility)
|
|
@@ -324,6 +329,7 @@ Example:
|
|
|
324
329
|
name: example-skill # skill name
|
|
325
330
|
description: >- # skill description
|
|
326
331
|
A sample skill that demonstrates the skill format
|
|
332
|
+
targets: ["*"] # * = all, or specific tools
|
|
327
333
|
claudecode: # for claudecode-specific parameters
|
|
328
334
|
allowed-tools:
|
|
329
335
|
- "Bash"
|
|
@@ -434,20 +440,21 @@ Currently, supports rules and commands generation for Claude Code. Import for gl
|
|
|
434
440
|
> * `rules/*.md` only supports single file has `root: true`, and frontmatter parameters without `root` are ignored.
|
|
435
441
|
> * Only Claude Code is supported for global mode commands.
|
|
436
442
|
|
|
437
|
-
## Simulate Commands and
|
|
443
|
+
## Simulate Commands, Subagents and Skills
|
|
438
444
|
|
|
439
|
-
Simulated commands and
|
|
445
|
+
Simulated commands, subagents and skills allow you to generate simulated features for copilot, cursor, codexcli and etc. This is useful for shortening your prompts.
|
|
440
446
|
|
|
441
|
-
1. Prepare `.rulesync/commands/*.md` and `.rulesync/
|
|
442
|
-
2. Generate simulated commands and
|
|
447
|
+
1. Prepare `.rulesync/commands/*.md`, `.rulesync/subagents/*.md` and `.rulesync/skills/*/SKILL.md` for your purposes.
|
|
448
|
+
2. Generate simulated commands, subagents and skills for specific tools that are included in copilot, cursor, codexcli and etc.
|
|
443
449
|
```bash
|
|
444
450
|
npx rulesync generate \
|
|
445
451
|
--targets copilot,cursor,codexcli \
|
|
446
|
-
--features commands,subagents \
|
|
452
|
+
--features commands,subagents,skills \
|
|
447
453
|
--simulated-commands \
|
|
448
|
-
--simulated-subagents
|
|
454
|
+
--simulated-subagents \
|
|
455
|
+
--simulated-skills
|
|
449
456
|
```
|
|
450
|
-
3. Use simulated commands and
|
|
457
|
+
3. Use simulated commands, subagents and skills in your prompts.
|
|
451
458
|
- Prompt examples:
|
|
452
459
|
```txt
|
|
453
460
|
# Execute simulated commands. By the way, `s/` stands for `simulate/`.
|
|
@@ -455,6 +462,9 @@ Simulated commands and subagents allow you to generate simulated commands and su
|
|
|
455
462
|
|
|
456
463
|
# Execute simulated subagents
|
|
457
464
|
Call your-subagent to achieve something.
|
|
465
|
+
|
|
466
|
+
# Use simulated skills
|
|
467
|
+
Use the skill your-skill to achieve something.
|
|
458
468
|
```
|
|
459
469
|
|
|
460
470
|
## Modular MCP (Experimental)
|
|
@@ -704,6 +714,22 @@ pnpm cicheck # Run code style check, type check, and tests
|
|
|
704
714
|
# Manual test using current code
|
|
705
715
|
pnpm dev generate -t claudecode -f "*"
|
|
706
716
|
pnpm dev import -t claudecode -f "*"
|
|
717
|
+
|
|
718
|
+
# Once you create .rulesync/rules/my-language.md and `pnpm dev generate`, you can use coding agents with your language.
|
|
719
|
+
# Japanese setting example:
|
|
720
|
+
cat << 'EOF' > .rulesync/rules/my-language.md
|
|
721
|
+
---
|
|
722
|
+
root: false
|
|
723
|
+
targets: ['*']
|
|
724
|
+
description: "It's a rule about language. If the rule file exists, you must always follow this."
|
|
725
|
+
globs: ["**/*"]
|
|
726
|
+
---
|
|
727
|
+
|
|
728
|
+
I'm a Japanese developer. So you must always answer in Japanese. On the other hand, reasoning(thinking) should be in English to improve token efficiency.
|
|
729
|
+
|
|
730
|
+
However, this project is for English speaking people. So when you write any code, comments, documentation, commit messages, PR title and PR descriptions, you must always use English.
|
|
731
|
+
EOF
|
|
732
|
+
pnpm dev generate
|
|
707
733
|
```
|
|
708
734
|
|
|
709
735
|
## FAQ
|