@the-bearded-bear/claude-craft 5.4.0 → 5.5.0-next.bf37c8b
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/Dev/i18n/de/Common/agents/api-designer.md +1 -1
- package/Dev/i18n/de/Common/agents/database-architect.md +1 -1
- package/Dev/i18n/de/Common/agents/devops-engineer.md +1 -1
- package/Dev/i18n/de/Common/agents/ralph-conductor.md +1 -1
- package/Dev/i18n/de/Common/agents/refactoring-specialist.md +1 -1
- package/Dev/i18n/de/Common/agents/tdd-coach.md +1 -1
- package/Dev/i18n/de/Common/agents/ui-designer.md +1 -1
- package/Dev/i18n/de/Common/agents/uiux-orchestrator.md +1 -1
- package/Dev/i18n/de/Common/agents/ux-ergonome.md +1 -1
- package/Dev/i18n/de/Common/agents/workflow-orchestrator.md +1 -1
- package/Dev/i18n/de/Common/skills/security/SKILL.md +1 -1
- package/Dev/i18n/de/Common/skills/testing/SKILL.md +1 -1
- package/Dev/i18n/de/Common/skills/workflow-analysis/SKILL.md +1 -1
- package/Dev/i18n/de/Common/templates/settings.json.template +1 -1
- package/Dev/i18n/en/Common/agents/api-designer.md +1 -1
- package/Dev/i18n/en/Common/agents/database-architect.md +1 -1
- package/Dev/i18n/en/Common/agents/devops-engineer.md +1 -1
- package/Dev/i18n/en/Common/agents/ralph-conductor.md +1 -0
- package/Dev/i18n/en/Common/agents/refactoring-specialist.md +1 -1
- package/Dev/i18n/en/Common/agents/tdd-coach.md +1 -1
- package/Dev/i18n/en/Common/agents/ui-designer.md +1 -1
- package/Dev/i18n/en/Common/agents/uiux-orchestrator.md +1 -1
- package/Dev/i18n/en/Common/agents/ux-ergonome.md +1 -1
- package/Dev/i18n/en/Common/agents/workflow-orchestrator.md +1 -1
- package/Dev/i18n/en/Common/commands/sub-agents-patterns.md +15 -0
- package/Dev/i18n/en/Common/skills/security/SKILL.md +1 -1
- package/Dev/i18n/en/Common/skills/testing/SKILL.md +1 -1
- package/Dev/i18n/en/Common/skills/workflow-analysis/SKILL.md +1 -1
- package/Dev/i18n/en/Common/templates/settings.json.template +1 -1
- package/Dev/i18n/en/PHP/agents/php-reviewer.md +5 -0
- package/Dev/i18n/en/VueJS/agents/vuejs-reviewer.md +10 -0
- package/Dev/i18n/es/Common/agents/api-designer.md +1 -1
- package/Dev/i18n/es/Common/agents/database-architect.md +1 -1
- package/Dev/i18n/es/Common/agents/devops-engineer.md +1 -1
- package/Dev/i18n/es/Common/agents/ralph-conductor.md +1 -0
- package/Dev/i18n/es/Common/agents/refactoring-specialist.md +1 -1
- package/Dev/i18n/es/Common/agents/tdd-coach.md +1 -1
- package/Dev/i18n/es/Common/agents/ui-designer.md +1 -1
- package/Dev/i18n/es/Common/agents/uiux-orchestrator.md +1 -1
- package/Dev/i18n/es/Common/agents/ux-ergonome.md +1 -1
- package/Dev/i18n/es/Common/agents/workflow-orchestrator.md +1 -1
- package/Dev/i18n/es/Common/skills/security/SKILL.md +1 -1
- package/Dev/i18n/es/Common/skills/testing/SKILL.md +1 -1
- package/Dev/i18n/es/Common/skills/workflow-analysis/SKILL.md +1 -1
- package/Dev/i18n/es/Common/templates/settings.json.template +1 -1
- package/Dev/i18n/fr/Common/agents/api-designer.md +1 -1
- package/Dev/i18n/fr/Common/agents/database-architect.md +1 -1
- package/Dev/i18n/fr/Common/agents/devops-engineer.md +1 -1
- package/Dev/i18n/fr/Common/agents/ralph-conductor.md +1 -1
- package/Dev/i18n/fr/Common/agents/refactoring-specialist.md +1 -1
- package/Dev/i18n/fr/Common/agents/tdd-coach.md +1 -1
- package/Dev/i18n/fr/Common/agents/ui-designer.md +1 -1
- package/Dev/i18n/fr/Common/agents/uiux-orchestrator.md +1 -1
- package/Dev/i18n/fr/Common/agents/ux-ergonome.md +1 -1
- package/Dev/i18n/fr/Common/agents/workflow-orchestrator.md +1 -1
- package/Dev/i18n/fr/Common/skills/security/SKILL.md +1 -1
- package/Dev/i18n/fr/Common/skills/testing/SKILL.md +1 -1
- package/Dev/i18n/fr/Common/skills/workflow-analysis/SKILL.md +1 -1
- package/Dev/i18n/fr/Common/templates/settings.json.template +1 -1
- package/Dev/i18n/pt/Common/agents/api-designer.md +1 -1
- package/Dev/i18n/pt/Common/agents/database-architect.md +1 -1
- package/Dev/i18n/pt/Common/agents/devops-engineer.md +1 -1
- package/Dev/i18n/pt/Common/agents/ralph-conductor.md +1 -1
- package/Dev/i18n/pt/Common/agents/refactoring-specialist.md +1 -1
- package/Dev/i18n/pt/Common/agents/tdd-coach.md +1 -1
- package/Dev/i18n/pt/Common/agents/ui-designer.md +1 -1
- package/Dev/i18n/pt/Common/agents/uiux-orchestrator.md +1 -1
- package/Dev/i18n/pt/Common/agents/ux-ergonome.md +1 -1
- package/Dev/i18n/pt/Common/agents/workflow-orchestrator.md +1 -1
- package/Dev/i18n/pt/Common/skills/security/SKILL.md +1 -1
- package/Dev/i18n/pt/Common/skills/testing/SKILL.md +1 -1
- package/Dev/i18n/pt/Common/skills/workflow-analysis/SKILL.md +1 -1
- package/Dev/i18n/pt/Common/templates/settings.json.template +1 -1
- package/README.md +20 -13
- package/package.json +1 -1
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: workflow-orchestrator
|
|
3
3
|
description: Intelligently routes to appropriate agents and workflows based on project context
|
|
4
|
-
model:
|
|
4
|
+
model: opus
|
|
5
5
|
tools: [Read, Glob, Grep, Edit, Write, Bash, Task, WebFetch, WebSearch]
|
|
6
6
|
permissionMode: default
|
|
7
7
|
skills: [workflow-analysis]
|
|
@@ -131,6 +131,21 @@ Approve all? [y/N/select]
|
|
|
131
131
|
- Full visibility of agent actions before start
|
|
132
132
|
- Granular control over allowed operations
|
|
133
133
|
|
|
134
|
+
### Task Tool Metrics (v2.1.30+)
|
|
135
|
+
|
|
136
|
+
Task tool results now include execution metrics:
|
|
137
|
+
|
|
138
|
+
| Metric | Description |
|
|
139
|
+
|--------|-------------|
|
|
140
|
+
| Token count | Total tokens consumed by the sub-agent |
|
|
141
|
+
| Tool uses | Number of tool invocations during execution |
|
|
142
|
+
| Duration | Total elapsed time for task completion |
|
|
143
|
+
|
|
144
|
+
**Benefits:**
|
|
145
|
+
- Monitor sub-agent cost per task
|
|
146
|
+
- Identify expensive operations
|
|
147
|
+
- Optimize parallel task distribution
|
|
148
|
+
|
|
134
149
|
## Best Practices
|
|
135
150
|
|
|
136
151
|
### Do
|
|
@@ -1,6 +1,11 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: php-reviewer
|
|
3
3
|
description: PHP and Clean Architecture code review specialist
|
|
4
|
+
model: haiku
|
|
5
|
+
tools: [Read, Glob, Grep, WebFetch, WebSearch]
|
|
6
|
+
disallowedTools: [Write, Edit, Bash, NotebookEdit]
|
|
7
|
+
permissionMode: default
|
|
8
|
+
skills: [solid-principles, testing, security]
|
|
4
9
|
---
|
|
5
10
|
|
|
6
11
|
# PHP/Clean Architecture Code Auditor Agent
|
|
@@ -1,3 +1,13 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: vuejs-reviewer
|
|
3
|
+
description: Vue.js code review specialist
|
|
4
|
+
model: haiku
|
|
5
|
+
tools: [Read, Glob, Grep, WebFetch, WebSearch]
|
|
6
|
+
disallowedTools: [Write, Edit, Bash, NotebookEdit]
|
|
7
|
+
permissionMode: default
|
|
8
|
+
skills: [solid-principles, testing, security]
|
|
9
|
+
---
|
|
10
|
+
|
|
1
11
|
# Vue.js Code Reviewer Agent
|
|
2
12
|
|
|
3
13
|
You are an expert Vue.js code reviewer. Your mission is to perform comprehensive code reviews focusing on Vue.js best practices, Composition API patterns, and TypeScript integration.
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: workflow-orchestrator
|
|
3
3
|
description: Intelligently routes to appropriate agents and workflows based on project context
|
|
4
|
-
model:
|
|
4
|
+
model: opus
|
|
5
5
|
tools: [Read, Glob, Grep, Edit, Write, Bash, Task, WebFetch, WebSearch]
|
|
6
6
|
permissionMode: default
|
|
7
7
|
skills: [workflow-analysis]
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: workflow-orchestrator
|
|
3
3
|
description: Intelligently routes to appropriate agents and workflows based on project context
|
|
4
|
-
model:
|
|
4
|
+
model: opus
|
|
5
5
|
tools: [Read, Glob, Grep, Edit, Write, Bash, Task, WebFetch, WebSearch]
|
|
6
6
|
permissionMode: default
|
|
7
7
|
skills: [workflow-analysis]
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: workflow-orchestrator
|
|
3
3
|
description: Intelligently routes to appropriate agents and workflows based on project context
|
|
4
|
-
model:
|
|
4
|
+
model: opus
|
|
5
5
|
tools: [Read, Glob, Grep, Edit, Write, Bash, Task, WebFetch, WebSearch]
|
|
6
6
|
permissionMode: default
|
|
7
7
|
skills: [workflow-analysis]
|
package/README.md
CHANGED
|
@@ -4,20 +4,27 @@ A comprehensive framework for AI-assisted development with [Claude Code](https:/
|
|
|
4
4
|
|
|
5
5
|
**Autonomous Sprint Ready**: Run entire sprints overnight with `/common:ralph-sprint` - auto-claim, error recovery, parallel processing.
|
|
6
6
|
|
|
7
|
-
## What's New in v5.
|
|
7
|
+
## What's New in v5.5 - Claude Code 2.1.32 & Opus 4.6
|
|
8
|
+
|
|
9
|
+
- **Claude Opus 4.6** (v2.1.32): New flagship model with 200K context (1M beta), 128K output, adaptive thinking
|
|
10
|
+
- **Agent Teams** (v2.1.32 Research Preview): Multi-agent coordination with shared task management
|
|
11
|
+
- **Automatic Memory** (v2.1.32): Auto-records session memory for future context
|
|
12
|
+
- **Summarize from Here** (v2.1.32): Partial conversation summarization
|
|
13
|
+
- **Auto Skill Loading** (v2.1.32): Skills from --add-dir auto-discovered
|
|
14
|
+
- **Skill Budget Scaling** (v2.1.32): Content scales to 2% of context window
|
|
15
|
+
- **--resume Agent Inheritance** (v2.1.32): Auto-inherits --agent value
|
|
16
|
+
- **VSCode Session Spinner** (v2.1.32): Loading spinner during session restore
|
|
17
|
+
- See [CHANGELOG](CHANGELOG.md) for full details
|
|
18
|
+
|
|
19
|
+
## What's New in v5.4 - Claude Code 2.1.31 Compatibility
|
|
8
20
|
|
|
21
|
+
- **PDF Page Range** (v2.1.30): Read tool `pages` parameter for PDFs
|
|
22
|
+
- **OAuth Client Credentials for MCP** (v2.1.30): `--client-id` / `--client-secret` for `claude mcp add`
|
|
23
|
+
- **/debug Command** (v2.1.30): Session-specific troubleshooting
|
|
24
|
+
- **Task Tool Metrics** (v2.1.30): Token count, tool uses, duration in sub-agent results
|
|
25
|
+
- **Session Resume Hint** (v2.1.31): Resume hint displayed on exit
|
|
9
26
|
- **PR Integration** (v2.1.27): Resume sessions linked to PRs with `--from-pr`
|
|
10
|
-
- `claude --from-pr 123` or `claude --from-pr <url>`
|
|
11
|
-
- Auto-link when creating PRs via `gh pr create`
|
|
12
|
-
- Status indicators: approved, pending, changes requested, draft, merged
|
|
13
|
-
- **File Tools Preference** (v2.1.21): Claude prefers native tools over bash
|
|
14
|
-
- Use `Read` instead of `cat/head/tail`
|
|
15
|
-
- Use `Edit` instead of `sed/awk`
|
|
16
|
-
- Use `Write` instead of `echo >/cat <<EOF`
|
|
17
27
|
- **spinnerVerbs** (v2.1.23): Customize spinner text in settings.json
|
|
18
|
-
- **Task status `deleted`** (v2.1.20): Permanent task removal via TaskUpdate
|
|
19
|
-
- **Background Agent Permissions** (v2.1.20): Permission prompts before launch
|
|
20
|
-
- **VSCode Python venv** (v2.1.21): Auto-activate virtual environment
|
|
21
28
|
- See [CHANGELOG](CHANGELOG.md) for full details
|
|
22
29
|
|
|
23
30
|
## What's New in v5.1 - QA Recette (Acceptance Testing)
|
|
@@ -67,7 +74,7 @@ A comprehensive framework for AI-assisted development with [Claude Code](https:/
|
|
|
67
74
|
- [TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md): Common problems and solutions
|
|
68
75
|
- [BMAD-PRACTICAL-GUIDE.md](docs/BMAD-PRACTICAL-GUIDE.md): BMAD v6 step-by-step
|
|
69
76
|
- [RALPH-GUIDE.md](docs/RALPH-GUIDE.md): Ralph Wiggum configuration
|
|
70
|
-
- **Complete Reference Documentation**: All 130+ commands and
|
|
77
|
+
- **Complete Reference Documentation**: All 130+ commands and 40 agents documented
|
|
71
78
|
- **Example Projects**: symfony-api, flutter-app, fullstack-saas
|
|
72
79
|
- **Complete Workflow Guides**: Idea → Production in 5 languages
|
|
73
80
|
- **Prerequisites Check Script**: `./Dev/scripts/check-prerequisites.sh`
|
|
@@ -157,7 +164,7 @@ A comprehensive framework for AI-assisted development with [Claude Code](https:/
|
|
|
157
164
|
- **10 Technology Stacks**: Symfony, Flutter, Python, React, React Native, Angular, C#/.NET, Laravel, Vue.js, PHP
|
|
158
165
|
- **Infrastructure Stack**: Docker agents and commands
|
|
159
166
|
- **5 Languages**: English, French, Spanish, German, Portuguese
|
|
160
|
-
- **
|
|
167
|
+
- **40 AI Agents**: Specialized reviewers, architects, coaches, UI/UX, Docker experts, Workflow Orchestrator, Ralph Conductor, **10 BMAD agents**, and QA Recette
|
|
161
168
|
- **130+ Slash Commands**: Automated workflows, code generation, **sprint management, quality gates, batch processing, acceptance testing**
|
|
162
169
|
- **BMAD v6 Framework**: Complete project management with status-based routing, quality gates, and batch execution
|
|
163
170
|
- **Ralph Wiggum**: Continuous loop execution with Definition of Done validation
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@the-bearded-bear/claude-craft",
|
|
3
|
-
"version": "5.
|
|
3
|
+
"version": "5.5.0-next.bf37c8b",
|
|
4
4
|
"description": "A comprehensive framework for AI-assisted development with Claude Code. Install standardized rules, agents, and commands for your projects.",
|
|
5
5
|
"main": "cli/index.js",
|
|
6
6
|
"bin": {
|