@hopla/claude-setup 1.11.1 → 1.11.3

package/.claude-plugin/marketplace.json

@@ -9,7 +9,7 @@
     {
       "name": "hopla",
       "description": "Agentic coding system: PIV loop, TDD, debugging, brainstorming, subagent execution, and team workflows",
-      "version": "1.11.0",
+      "version": "1.11.2",
       "source": "./",
       "author": {
         "name": "Hopla Tools",

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "hopla",
   "description": "Agentic coding system for Claude Code: PIV loop (Plan → Implement → Validate), TDD, debugging, brainstorming, subagent execution, and team workflows",
-  "version": "1.11.0",
+  "version": "1.11.3",
   "author": {
     "name": "Hopla Tools",
     "email": "julio@hopla.tools"

package/README.md

@@ -9,7 +9,7 @@ Hopla team agentic coding system for Claude Code. Installs commands, skills, age
 First, register the HOPLA marketplace (only needed once):
 
 ```
-/plugin marketplace add hopla-marketplace https://github.com/HOPLAtools/claude-setup.git
+/plugin marketplace add hopla-marketplace HOPLAtools/claude-setup
 ```
 
 Then install the plugin:
@@ -164,10 +164,10 @@ After each PIV loop, run `/hopla-execution-report` + `/hopla-system-review` to f
 
 | Skill | Auto-activates when you say... |
 |---|---|
-| `hopla-git` | "commit this", "create a PR", "guarda los cambios" |
-| `hopla-prime` | "orient yourself", "ponte al día", "what is this project" |
-| `hopla-code-review` | "review the code", "code review", "analiza los cambios" |
-| `hopla-execution-report` | "generate the report", "genera el reporte", "document what was done" |
+| `hopla-git` | "commit this", "create a PR", "save the changes" |
+| `hopla-prime` | "orient yourself", "catch me up", "what is this project" |
+| `hopla-code-review` | "review the code", "code review", "check these changes" |
+| `hopla-execution-report` | "generate the report", "document what was done", "summarize the work" |
 | `hopla-verify` | "verify it works", "make sure it's correct", "check before finishing" |
 | `hopla-brainstorm` | "let's brainstorm", "explore approaches", "design this before coding" |
 | `hopla-debug` | "debug this", "find the bug", "why is this failing" |
@@ -249,7 +249,7 @@ After each PIV loop, run `/hopla-execution-report` + `/hopla-system-review` to f
 
 ### Feature development (PIV loop)
 ```
-"ponte al día"          → hopla-prime skill auto-loads project context
+"catch me up"           → hopla-prime skill auto-loads project context
 /hopla-plan-feature     → research codebase and create plan
 /hopla-review-plan      → review plan summary and approve
 /hopla-execute          → implement the plan with validation
@@ -257,7 +257,7 @@ After each PIV loop, run `/hopla-execution-report` + `/hopla-system-review` to f
 "review the code"       → hopla-code-review skill runs automatically
 /hopla-code-review-fix  → fix issues found
 /hopla-rca              → root cause analysis if a bug is found
-"genera el reporte"     → hopla-execution-report skill documents what was built
+"generate the report"     → hopla-execution-report skill documents what was built
 /hopla-git-commit       → save to git
 /hopla-git-pr           → open pull request on GitHub
 ```
@@ -319,7 +319,7 @@ Commands are modular — the output of one becomes the input of the next. Some c
 # 6. Fix issues
 /hopla-code-review-fix .agents/code-reviews/add-user-authentication.md
 
-# 7. Document (auto-triggered skill — just say "genera el reporte")
+# 7. Document (auto-triggered skill — just say "generate the report")
 → saves: .agents/execution-reports/add-user-authentication.md
 
 # 8. Commit

package/agents/code-reviewer.md

@@ -1,7 +1,6 @@
 ---
 name: code-reviewer
 description: "Senior code reviewer agent for thorough code quality analysis. Use this agent to review completed code changes with fresh context, catching issues the implementer might miss."
-model: sonnet
 allowed-tools: Read, Grep, Glob, Bash
 ---
 

package/agents/codebase-researcher.md

@@ -1,7 +1,6 @@
 ---
 name: codebase-researcher
 description: "Fast codebase exploration agent for research tasks. Use this agent to investigate code, find patterns, map dependencies, or gather context without polluting the main conversation."
-model: haiku
 allowed-tools: Read, Grep, Glob, Bash
 ---
 

package/agents/system-reviewer.md

@@ -1,7 +1,6 @@
 ---
 name: system-reviewer
 description: "System review agent that analyzes execution reports against plans to identify process improvements. Use after feature completion to find patterns and improve the development system."
-model: sonnet
 allowed-tools: Read, Grep, Glob, Bash
 ---
 

package/commands/guides/write-skill.md

@@ -20,7 +20,7 @@ skill-name/
 name: skill-name
 description: "100-150 words. Start with what it does, then 'Use when...' + specific triggers. End with 'Do NOT use for...' anti-triggers."
 allowed-tools: Read, Grep, Glob, Bash  # Optional: restrict tools
-model: sonnet  # Optional: force specific model
+# Do NOT hardcode `model:` — let skills inherit the user's configured model
 ---
 ```
 
@@ -30,7 +30,7 @@ The description is the MOST CRITICAL field — it determines when the skill acti
 
 ### Pattern
 ```
-[What the skill does]. Use when [trigger phrases, synonyms, variations in English and Spanish]. Do NOT use for [anti-triggers].
+[What the skill does]. Use when [trigger phrases, synonyms, variations]. Do NOT use for [anti-triggers].
 ```
 
 ### Good Example
@@ -47,7 +47,7 @@ The description is the MOST CRITICAL field — it determines when the skill acti
 
 Claude uses SEMANTIC matching, not keyword matching. Cover:
 - Different phrasings of the same intent
-- English AND Spanish triggers (for HOPLA's bilingual users)
+- Multilingual triggers if your team is multilingual
 - Common misspellings or abbreviations
 - Related verbs and nouns
 

package/global-rules.md

@@ -1,10 +1,10 @@
 # Global Rules — Agentic Coding System
 
-> 🌐 **CRITICAL — Language:** Always respond in the same language the user is writing in, regardless of the language of any command or instruction. If the user writes in Spanish, respond in Spanish. If in English, respond in English. This rule overrides everything else.
+> 🌐 **CRITICAL — Language:** Always respond in the same language the user is writing in. Match the user's language — do not default to any specific language. This rule overrides everything else.
 
 ## 1. Communication
 
-- **Always respond in the same language the user writes in** — if the user writes in Spanish, respond in Spanish; if in English, respond in English
+- **Always respond in the language the user writes in** — match their language, never assume a default
 - Code, comments, variable names, and commit messages always in **English** regardless of the conversation language
 - Be concise — avoid unnecessary filler text
 - When reporting results, use ✅/❌ for clarity

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@hopla/claude-setup",
-  "version": "1.11.1",
+  "version": "1.11.3",
   "description": "Hopla team agentic coding system for Claude Code",
   "type": "module",
   "bin": {

package/skills/hopla-execution-report/SKILL.md

@@ -2,7 +2,6 @@
 name: hopla-execution-report
 description: "Post-implementation documentation generator. Use when the user says 'generate report', 'document what was done', 'execution report', 'what changed', or after a feature implementation is complete and validated. Do NOT use during implementation — only after completion."
 allowed-tools: Read, Grep, Glob, Bash
-model: sonnet
 ---
 
 > 🌐 **Language:** All user-facing output must match the user's language. Code, paths, and commands stay in English.

package/skills/hopla-prime/SKILL.md

@@ -2,7 +2,6 @@
 name: hopla-prime
 description: "Project orientation and context loading. Use when starting a session, onboarding to a project, needing to understand the codebase, or when the user says 'orient', 'get context', 'load project', 'what is this project', 'prime', or 'start'. Do NOT use mid-task when the project is already understood."
 allowed-tools: Read, Grep, Glob, Bash
-model: sonnet
 ---
 
 > 🌐 **Language:** All user-facing output must match the user's language. Code, paths, and commands stay in English.